From 1648a5f09de8bacd005d383469436f21a73ced7d Mon Sep 17 00:00:00 2001 From: Melanie Plageman Date: Mon, 2 Mar 2026 16:31:33 -0500 Subject: [PATCH v43 08/10] Pass down information on table modification to scan node Pass down information to sequential scan, index [only] scan, bitmap table scan, sample scan, and TID range scan nodes on whether or not the query modifies the relation being scanned. A later commit will use this information to update the VM during on-access pruning only if the relation is not modified by the query. Author: Melanie Plageman Reviewed-by: Andres Freund Reviewed-by: Andrey Borodin Reviewed-by: Chao Li Discussion: https://postgr.es/m/4379FDA3-9446-4E2C-9C15-32EFE8D4F31B%40yandex-team.ru --- src/backend/executor/nodeBitmapHeapscan.c | 6 +++++- src/backend/executor/nodeIndexonlyscan.c | 15 ++++++++++++--- src/backend/executor/nodeIndexscan.c | 18 ++++++++++++++---- src/backend/executor/nodeSamplescan.c | 5 ++++- src/backend/executor/nodeSeqscan.c | 18 +++++++++++++++--- src/backend/executor/nodeTidrangescan.c | 15 ++++++++++++--- src/include/access/tableam.h | 3 +++ src/include/executor/executor.h | 10 ++++++++++ 8 files changed, 75 insertions(+), 15 deletions(-) diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c index 324e2bed22c..aec92c868ac 100644 --- a/src/backend/executor/nodeBitmapHeapscan.c +++ b/src/backend/executor/nodeBitmapHeapscan.c @@ -144,11 +144,15 @@ BitmapTableScanSetup(BitmapHeapScanState *node) */ if (!node->ss.ss_currentScanDesc) { + uint32 flags = ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0; + node->ss.ss_currentScanDesc = table_beginscan_bm(node->ss.ss_currentRelation, node->ss.ps.state->es_snapshot, 0, - NULL, 0); + NULL, + flags); } node->ss.ss_currentScanDesc->st.rs_tbmiterator = tbmiterator; diff --git a/src/backend/executor/nodeIndexonlyscan.c b/src/backend/executor/nodeIndexonlyscan.c index f733be0220c..de9db45322c 100644 --- a/src/backend/executor/nodeIndexonlyscan.c +++ b/src/backend/executor/nodeIndexonlyscan.c @@ -85,6 +85,9 @@ IndexOnlyNext(IndexOnlyScanState *node) if (scandesc == NULL) { + uint32 flags = ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0; + /* * We reach here if the index only scan is not parallel, or if we're * serially executing an index only scan that was planned to be @@ -92,7 +95,7 @@ IndexOnlyNext(IndexOnlyScanState *node) */ scandesc = index_beginscan(node->ss.ss_currentRelation, node->ioss_RelationDesc, - 0, /* flags */ + flags, estate->es_snapshot, node->ioss_Instrument, node->ioss_NumScanKeys, @@ -795,7 +798,10 @@ ExecIndexOnlyScanInitializeDSM(IndexOnlyScanState *node, node->ioss_Instrument, node->ioss_NumScanKeys, node->ioss_NumOrderByKeys, - piscan, 0); + piscan, + ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0); + node->ioss_ScanDesc->xs_want_itup = true; node->ioss_VMBuffer = InvalidBuffer; @@ -861,7 +867,10 @@ ExecIndexOnlyScanInitializeWorker(IndexOnlyScanState *node, node->ioss_Instrument, node->ioss_NumScanKeys, node->ioss_NumOrderByKeys, - piscan, 0); + piscan, + ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0); + node->ioss_ScanDesc->xs_want_itup = true; /* diff --git a/src/backend/executor/nodeIndexscan.c b/src/backend/executor/nodeIndexscan.c index 1a101df492b..9df4a699504 100644 --- a/src/backend/executor/nodeIndexscan.c +++ b/src/backend/executor/nodeIndexscan.c @@ -104,13 +104,16 @@ IndexNext(IndexScanState *node) if (scandesc == NULL) { + uint32 flags = ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0; + /* * We reach here if the index scan is not parallel, or if we're * serially executing an index scan that was planned to be parallel. */ scandesc = index_beginscan(node->ss.ss_currentRelation, node->iss_RelationDesc, - 0, /* flags */ + flags, estate->es_snapshot, node->iss_Instrument, node->iss_NumScanKeys, @@ -201,13 +204,16 @@ IndexNextWithReorder(IndexScanState *node) if (scandesc == NULL) { + uint32 flags = ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0; + /* * We reach here if the index scan is not parallel, or if we're * serially executing an index scan that was planned to be parallel. */ scandesc = index_beginscan(node->ss.ss_currentRelation, node->iss_RelationDesc, - 0, /* flags */ + flags, estate->es_snapshot, node->iss_Instrument, node->iss_NumScanKeys, @@ -1732,7 +1738,9 @@ ExecIndexScanInitializeDSM(IndexScanState *node, node->iss_Instrument, node->iss_NumScanKeys, node->iss_NumOrderByKeys, - piscan, 0); + piscan, + ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0); /* * If no run-time keys to calculate or they are ready, go ahead and pass @@ -1796,7 +1804,9 @@ ExecIndexScanInitializeWorker(IndexScanState *node, node->iss_Instrument, node->iss_NumScanKeys, node->iss_NumOrderByKeys, - piscan, 0); + piscan, + ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0); /* * If no run-time keys to calculate or they are ready, go ahead and pass diff --git a/src/backend/executor/nodeSamplescan.c b/src/backend/executor/nodeSamplescan.c index cc6b23abee0..71c70e5e5c7 100644 --- a/src/backend/executor/nodeSamplescan.c +++ b/src/backend/executor/nodeSamplescan.c @@ -292,13 +292,16 @@ tablesample_init(SampleScanState *scanstate) /* Now we can create or reset the HeapScanDesc */ if (scanstate->ss.ss_currentScanDesc == NULL) { + uint32 flags = ScanRelIsReadOnly(&scanstate->ss) ? + SO_HINT_REL_READ_ONLY : 0; + scanstate->ss.ss_currentScanDesc = table_beginscan_sampling(scanstate->ss.ss_currentRelation, scanstate->ss.ps.state->es_snapshot, 0, NULL, scanstate->use_bulkread, allow_sync, - scanstate->use_pagemode, 0); + scanstate->use_pagemode, flags); } else { diff --git a/src/backend/executor/nodeSeqscan.c b/src/backend/executor/nodeSeqscan.c index c2d9b7293de..79470e6b9b5 100644 --- a/src/backend/executor/nodeSeqscan.c +++ b/src/backend/executor/nodeSeqscan.c @@ -65,13 +65,17 @@ SeqNext(SeqScanState *node) if (scandesc == NULL) { + uint32 flags = ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0; + /* * We reach here if the scan is not parallel, or if we're serially * executing a scan that was planned to be parallel. */ scandesc = table_beginscan(node->ss.ss_currentRelation, estate->es_snapshot, - 0, NULL, 0); + 0, NULL, flags); + node->ss.ss_currentScanDesc = scandesc; } @@ -368,14 +372,18 @@ ExecSeqScanInitializeDSM(SeqScanState *node, { EState *estate = node->ss.ps.state; ParallelTableScanDesc pscan; + uint32 flags = ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0; pscan = shm_toc_allocate(pcxt->toc, node->pscan_len); table_parallelscan_initialize(node->ss.ss_currentRelation, pscan, estate->es_snapshot); shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id, pscan); + node->ss.ss_currentScanDesc = - table_beginscan_parallel(node->ss.ss_currentRelation, pscan, 0); + table_beginscan_parallel(node->ss.ss_currentRelation, pscan, + flags); } /* ---------------------------------------------------------------- @@ -405,8 +413,12 @@ ExecSeqScanInitializeWorker(SeqScanState *node, ParallelWorkerContext *pwcxt) { ParallelTableScanDesc pscan; + uint32 flags = ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0; pscan = shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false); node->ss.ss_currentScanDesc = - table_beginscan_parallel(node->ss.ss_currentRelation, pscan, 0); + table_beginscan_parallel(node->ss.ss_currentRelation, + pscan, + flags); } diff --git a/src/backend/executor/nodeTidrangescan.c b/src/backend/executor/nodeTidrangescan.c index 994f70989bc..4257afd96ed 100644 --- a/src/backend/executor/nodeTidrangescan.c +++ b/src/backend/executor/nodeTidrangescan.c @@ -242,10 +242,13 @@ TidRangeNext(TidRangeScanState *node) if (scandesc == NULL) { + uint32 flags = ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0; + scandesc = table_beginscan_tidrange(node->ss.ss_currentRelation, estate->es_snapshot, &node->trss_mintid, - &node->trss_maxtid, 0); + &node->trss_maxtid, flags); node->ss.ss_currentScanDesc = scandesc; } else @@ -452,15 +455,18 @@ ExecTidRangeScanInitializeDSM(TidRangeScanState *node, ParallelContext *pcxt) { EState *estate = node->ss.ps.state; ParallelTableScanDesc pscan; + uint32 flags = ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0; pscan = shm_toc_allocate(pcxt->toc, node->trss_pscanlen); table_parallelscan_initialize(node->ss.ss_currentRelation, pscan, estate->es_snapshot); shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id, pscan); + node->ss.ss_currentScanDesc = table_beginscan_parallel_tidrange(node->ss.ss_currentRelation, - pscan, 0); + pscan, flags); } /* ---------------------------------------------------------------- @@ -490,9 +496,12 @@ ExecTidRangeScanInitializeWorker(TidRangeScanState *node, ParallelWorkerContext *pwcxt) { ParallelTableScanDesc pscan; + uint32 flags = ScanRelIsReadOnly(&node->ss) ? + SO_HINT_REL_READ_ONLY : 0; pscan = shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false); + node->ss.ss_currentScanDesc = table_beginscan_parallel_tidrange(node->ss.ss_currentRelation, - pscan, 0); + pscan, flags); } diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h index 8357d05d83b..487e38292fa 100644 --- a/src/include/access/tableam.h +++ b/src/include/access/tableam.h @@ -63,6 +63,9 @@ typedef enum ScanOptions /* unregister snapshot at scan end? */ SO_TEMP_SNAPSHOT = 1 << 9, + + /* set if the query doesn't modify the relation */ + SO_HINT_REL_READ_ONLY = 1 << 10, } ScanOptions; /* diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h index 07f4b1f7490..31c4192b67e 100644 --- a/src/include/executor/executor.h +++ b/src/include/executor/executor.h @@ -690,6 +690,16 @@ extern void ExecCreateScanSlotFromOuterPlan(EState *estate, extern bool ExecRelationIsTargetRelation(EState *estate, Index scanrelid); +/* + * Return true if the scan node's relation is not modified by the query. + */ +static inline bool +ScanRelIsReadOnly(ScanState *ss) +{ + return !bms_is_member(((Scan *) ss->ps.plan)->scanrelid, + ss->ps.state->es_plannedstmt->modifiedRelids); +} + extern Relation ExecOpenScanRelation(EState *estate, Index scanrelid, int eflags); extern void ExecInitRangeTable(EState *estate, List *rangeTable, List *permInfos, -- 2.43.0