From 90e9a2935a97ff085f521a34dfd86b9800542ab1 Mon Sep 17 00:00:00 2001 From: Amit Langote Date: Tue, 4 Jul 2023 22:36:45 +0900 Subject: [PATCH v43 4/5] Delay locking of child tables in cached plans until ExecutorStart() Currently, GetCachedPlan() takes a lock on all relations contained in a cached plan before returning it as a valid plan to its callers for execution. One disadvantage is that if the plan contains partitions that are prunable with conditions involving EXTERN parameters and other stable expressions (known as "initial pruning"), many of them would be locked unnecessarily, because only those that survive initial pruning need to have been locked. Locking all partitions this way causes significant delay when there are many partitions. Note that initial pruning occurs during executor's initialization of the plan, that is, InitPlan(). This commit rearranges things to move the locking of child tables referenced in a cached plan to occur during ExecInitNode() so that initial pruning in the ExecInitNode() subroutines of the plan nodes that support pruning can eliminate any child tables that need not be scanned and thus locked. To determine that a given table is a child table, ExecGetRangeTableRelation() now looks at the RTE's inFromCl field, which is only true for tables that are directly mentioned in the query but false for child tables. Note that any tables whose RTEs' inFromCl is true would already have been locked by GetCachedPlan(), so need not be locked again during execution. If the locking of child tables causes the CachedPlan to go stale, that is, its is_valid set to false by PlanCacheRelCallback() when an invalidation message matching some child table contained in the plan is processed, ExecInitNode() abandons the initialization of the remaining nodes in the plan tree. In that case, InitPlan() returns after setting QueryDesc.planstate to NULL to indicate to the caller that no execution is possible with the plan tree as is. Also, ExecutorStart() now returns true or false to indicate whether or not QueryDesc.planstate points to a successfully initialized PlanState tree. Call sites that use GetCachedPlan() to get the plan trees to pass to the executor should now be prepared to retry in the cases where ExecutorStart() returns false. Given this new behavior, PortalStart() now must always perform ExecutorStart() to be able to drop and recreate cached plans if needed, which is currently only done so for single-query portals. For multi-query portals, the QueryDescs that are now created during PortalStart() are remembered in a new List field of Portal called 'qdescs' and allocated in a new memory context 'queryContext'. PortalRunMulti() now simply performs ExecutorRun() on the QueryDescs found in 'qdescs'. Discussion: https://postgr.es/m/CA+HiwqFGkMSge6TgC9KQzde0ohpAycLQuV7ooitEEpbKB0O_mg@mail.gmail.com --- contrib/auto_explain/auto_explain.c | 12 +- .../pg_stat_statements/pg_stat_statements.c | 12 +- contrib/postgres_fdw/postgres_fdw.c | 4 + src/backend/commands/copyto.c | 10 +- src/backend/commands/createas.c | 9 +- src/backend/commands/explain.c | 144 +++++--- src/backend/commands/extension.c | 5 +- src/backend/commands/matview.c | 9 +- src/backend/commands/portalcmds.c | 24 +- src/backend/commands/prepare.c | 32 +- src/backend/executor/README | 39 ++ src/backend/executor/execMain.c | 96 ++++- src/backend/executor/execParallel.c | 18 +- src/backend/executor/execPartition.c | 14 + src/backend/executor/execProcnode.c | 20 +- src/backend/executor/execUtils.c | 63 +++- src/backend/executor/functions.c | 5 +- src/backend/executor/nodeAgg.c | 2 + src/backend/executor/nodeAppend.c | 25 ++ src/backend/executor/nodeBitmapAnd.c | 5 +- src/backend/executor/nodeBitmapHeapscan.c | 4 + src/backend/executor/nodeBitmapIndexscan.c | 9 +- src/backend/executor/nodeBitmapOr.c | 5 +- src/backend/executor/nodeCustom.c | 2 + src/backend/executor/nodeForeignscan.c | 4 + src/backend/executor/nodeGather.c | 3 + src/backend/executor/nodeGatherMerge.c | 2 + src/backend/executor/nodeGroup.c | 2 + src/backend/executor/nodeHash.c | 2 + src/backend/executor/nodeHashjoin.c | 4 + src/backend/executor/nodeIncrementalSort.c | 2 + src/backend/executor/nodeIndexonlyscan.c | 11 +- src/backend/executor/nodeIndexscan.c | 11 +- src/backend/executor/nodeLimit.c | 2 + src/backend/executor/nodeLockRows.c | 2 + src/backend/executor/nodeMaterial.c | 2 + src/backend/executor/nodeMemoize.c | 2 + src/backend/executor/nodeMergeAppend.c | 25 ++ src/backend/executor/nodeMergejoin.c | 4 + src/backend/executor/nodeModifyTable.c | 7 + src/backend/executor/nodeNestloop.c | 4 + src/backend/executor/nodeProjectSet.c | 2 + src/backend/executor/nodeRecursiveunion.c | 4 + src/backend/executor/nodeResult.c | 2 + src/backend/executor/nodeSamplescan.c | 2 + src/backend/executor/nodeSeqscan.c | 2 + src/backend/executor/nodeSetOp.c | 2 + src/backend/executor/nodeSort.c | 2 + src/backend/executor/nodeSubqueryscan.c | 2 + src/backend/executor/nodeTidrangescan.c | 2 + src/backend/executor/nodeTidscan.c | 2 + src/backend/executor/nodeUnique.c | 2 + src/backend/executor/nodeWindowAgg.c | 2 + src/backend/executor/spi.c | 51 ++- src/backend/storage/lmgr/lmgr.c | 45 +++ src/backend/tcop/postgres.c | 19 +- src/backend/tcop/pquery.c | 344 +++++++++--------- src/backend/utils/cache/lsyscache.c | 21 ++ src/backend/utils/cache/plancache.c | 149 +++----- src/backend/utils/mmgr/portalmem.c | 9 + src/include/commands/explain.h | 7 +- src/include/executor/execdesc.h | 4 + src/include/executor/executor.h | 19 +- src/include/nodes/execnodes.h | 2 + src/include/storage/lmgr.h | 1 + src/include/tcop/pquery.h | 2 +- src/include/utils/lsyscache.h | 1 + src/include/utils/plancache.h | 14 + src/include/utils/portal.h | 3 + src/test/modules/delay_execution/Makefile | 3 +- .../modules/delay_execution/delay_execution.c | 67 +++- .../expected/cached-plan-replan.out | 156 ++++++++ .../specs/cached-plan-replan.spec | 61 ++++ 73 files changed, 1251 insertions(+), 410 deletions(-) create mode 100644 src/test/modules/delay_execution/expected/cached-plan-replan.out create mode 100644 src/test/modules/delay_execution/specs/cached-plan-replan.spec diff --git a/contrib/auto_explain/auto_explain.c b/contrib/auto_explain/auto_explain.c index c3ac27ae99..a0630d7944 100644 --- a/contrib/auto_explain/auto_explain.c +++ b/contrib/auto_explain/auto_explain.c @@ -78,7 +78,7 @@ static ExecutorRun_hook_type prev_ExecutorRun = NULL; static ExecutorFinish_hook_type prev_ExecutorFinish = NULL; static ExecutorEnd_hook_type prev_ExecutorEnd = NULL; -static void explain_ExecutorStart(QueryDesc *queryDesc, int eflags); +static bool explain_ExecutorStart(QueryDesc *queryDesc, int eflags); static void explain_ExecutorRun(QueryDesc *queryDesc, ScanDirection direction, uint64 count, bool execute_once); @@ -258,9 +258,11 @@ _PG_init(void) /* * ExecutorStart hook: start up logging if needed */ -static void +static bool explain_ExecutorStart(QueryDesc *queryDesc, int eflags) { + bool plan_valid; + /* * At the beginning of each top-level statement, decide whether we'll * sample this statement. If nested-statement explaining is enabled, @@ -296,9 +298,9 @@ explain_ExecutorStart(QueryDesc *queryDesc, int eflags) } if (prev_ExecutorStart) - prev_ExecutorStart(queryDesc, eflags); + plan_valid = prev_ExecutorStart(queryDesc, eflags); else - standard_ExecutorStart(queryDesc, eflags); + plan_valid = standard_ExecutorStart(queryDesc, eflags); if (auto_explain_enabled()) { @@ -316,6 +318,8 @@ explain_ExecutorStart(QueryDesc *queryDesc, int eflags) MemoryContextSwitchTo(oldcxt); } } + + return plan_valid; } /* diff --git a/contrib/pg_stat_statements/pg_stat_statements.c b/contrib/pg_stat_statements/pg_stat_statements.c index 55b957d251..1160a7326a 100644 --- a/contrib/pg_stat_statements/pg_stat_statements.c +++ b/contrib/pg_stat_statements/pg_stat_statements.c @@ -325,7 +325,7 @@ static PlannedStmt *pgss_planner(Query *parse, const char *query_string, int cursorOptions, ParamListInfo boundParams); -static void pgss_ExecutorStart(QueryDesc *queryDesc, int eflags); +static bool pgss_ExecutorStart(QueryDesc *queryDesc, int eflags); static void pgss_ExecutorRun(QueryDesc *queryDesc, ScanDirection direction, uint64 count, bool execute_once); @@ -963,13 +963,15 @@ pgss_planner(Query *parse, /* * ExecutorStart hook: start up tracking if needed */ -static void +static bool pgss_ExecutorStart(QueryDesc *queryDesc, int eflags) { + bool plan_valid; + if (prev_ExecutorStart) - prev_ExecutorStart(queryDesc, eflags); + plan_valid = prev_ExecutorStart(queryDesc, eflags); else - standard_ExecutorStart(queryDesc, eflags); + plan_valid = standard_ExecutorStart(queryDesc, eflags); /* * If query has queryId zero, don't track it. This prevents double @@ -992,6 +994,8 @@ pgss_ExecutorStart(QueryDesc *queryDesc, int eflags) MemoryContextSwitchTo(oldcxt); } } + + return plan_valid; } /* diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index c5cada55fb..1edd4c3f17 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -2658,7 +2658,11 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) /* Get info about foreign table. */ rtindex = node->resultRelInfo->ri_RangeTableIndex; if (fsplan->scan.scanrelid == 0) + { dmstate->rel = ExecOpenScanRelation(estate, rtindex, eflags); + if (!ExecPlanStillValid(estate)) + return; + } else dmstate->rel = node->ss.ss_currentRelation; table = GetForeignTable(RelationGetRelid(dmstate->rel)); diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index 9e4b2437a5..2b0d0a8ebd 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -558,7 +558,8 @@ BeginCopyTo(ParseState *pstate, ((DR_copy *) dest)->cstate = cstate; /* Create a QueryDesc requesting no output */ - cstate->queryDesc = CreateQueryDesc(plan, pstate->p_sourcetext, + cstate->queryDesc = CreateQueryDesc(plan, NULL, + pstate->p_sourcetext, GetActiveSnapshot(), InvalidSnapshot, dest, NULL, NULL, 0); @@ -568,7 +569,12 @@ BeginCopyTo(ParseState *pstate, * * ExecutorStart computes a result tupdesc for us */ - ExecutorStart(cstate->queryDesc, 0); + { + bool plan_valid PG_USED_FOR_ASSERTS_ONLY; + + plan_valid = ExecutorStart(cstate->queryDesc, 0); + Assert(plan_valid); + } tupDesc = cstate->queryDesc->tupDesc; } diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index e91920ca14..bb359bb190 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -325,12 +325,17 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt, UpdateActiveSnapshotCommandId(); /* Create a QueryDesc, redirecting output to our tuple receiver */ - queryDesc = CreateQueryDesc(plan, pstate->p_sourcetext, + queryDesc = CreateQueryDesc(plan, NULL, pstate->p_sourcetext, GetActiveSnapshot(), InvalidSnapshot, dest, params, queryEnv, 0); /* call ExecutorStart to prepare the plan for execution */ - ExecutorStart(queryDesc, GetIntoRelEFlags(into)); + { + bool plan_valid PG_USED_FOR_ASSERTS_ONLY; + + plan_valid = ExecutorStart(queryDesc, GetIntoRelEFlags(into)); + Assert(plan_valid); + } /* run the plan to completion */ ExecutorRun(queryDesc, ForwardScanDirection, 0, true); diff --git a/src/backend/commands/explain.c b/src/backend/commands/explain.c index 8570b14f62..954d83fb0a 100644 --- a/src/backend/commands/explain.c +++ b/src/backend/commands/explain.c @@ -393,6 +393,7 @@ ExplainOneQuery(Query *query, int cursorOptions, else { PlannedStmt *plan; + QueryDesc *queryDesc; instr_time planstart, planduration; BufferUsage bufusage_start, @@ -415,12 +416,89 @@ ExplainOneQuery(Query *query, int cursorOptions, BufferUsageAccumDiff(&bufusage, &pgBufferUsage, &bufusage_start); } + queryDesc = ExplainQueryDesc(plan, NULL, queryString, into, es, + params, queryEnv); + Assert(queryDesc); + /* run it (if needed) and produce output */ - ExplainOnePlan(plan, into, es, queryString, params, queryEnv, + ExplainOnePlan(queryDesc, into, es, queryString, params, queryEnv, &planduration, (es->buffers ? &bufusage : NULL)); } } +/* + * ExplainQueryDesc + * Set up QueryDesc for EXPLAINing a given plan + * + * This returns NULL if cplan is found to be no longer valid. + */ +QueryDesc * +ExplainQueryDesc(PlannedStmt *stmt, CachedPlan *cplan, + const char *queryString, IntoClause *into, ExplainState *es, + ParamListInfo params, QueryEnvironment *queryEnv) +{ + QueryDesc *queryDesc; + DestReceiver *dest; + int eflags; + int instrument_option = 0; + + /* + * Normally we discard the query's output, but if explaining CREATE TABLE + * AS, we'd better use the appropriate tuple receiver. + */ + if (into) + dest = CreateIntoRelDestReceiver(into); + else + dest = None_Receiver; + + if (es->analyze && es->timing) + instrument_option |= INSTRUMENT_TIMER; + else if (es->analyze) + instrument_option |= INSTRUMENT_ROWS; + + if (es->buffers) + instrument_option |= INSTRUMENT_BUFFERS; + if (es->wal) + instrument_option |= INSTRUMENT_WAL; + + /* + * Use a snapshot with an updated command ID to ensure this query sees + * results of any previously executed queries. + */ + PushCopiedSnapshot(GetActiveSnapshot()); + UpdateActiveSnapshotCommandId(); + + /* Create a QueryDesc for the query */ + queryDesc = CreateQueryDesc(stmt, cplan, queryString, + GetActiveSnapshot(), InvalidSnapshot, + dest, params, queryEnv, instrument_option); + + /* Select execution options */ + if (es->analyze) + eflags = 0; /* default run-to-completion flags */ + else + eflags = EXEC_FLAG_EXPLAIN_ONLY; + if (es->generic) + eflags |= EXEC_FLAG_EXPLAIN_GENERIC; + if (into) + eflags |= GetIntoRelEFlags(into); + + /* + * Call ExecutorStart to prepare the plan for execution. A cached plan + * may get invalidated as we're doing that. + */ + if (!ExecutorStart(queryDesc, eflags)) + { + /* Clean up. */ + ExecutorEnd(queryDesc); + FreeQueryDesc(queryDesc); + PopActiveSnapshot(); + return NULL; + } + + return queryDesc; +} + /* * ExplainOneUtility - * print out the execution plan for one utility statement @@ -524,29 +602,16 @@ ExplainOneUtility(Node *utilityStmt, IntoClause *into, ExplainState *es, * to call it. */ void -ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es, +ExplainOnePlan(QueryDesc *queryDesc, + IntoClause *into, ExplainState *es, const char *queryString, ParamListInfo params, QueryEnvironment *queryEnv, const instr_time *planduration, const BufferUsage *bufusage) { - DestReceiver *dest; - QueryDesc *queryDesc; instr_time starttime; double totaltime = 0; - int eflags; - int instrument_option = 0; - - Assert(plannedstmt->commandType != CMD_UTILITY); - if (es->analyze && es->timing) - instrument_option |= INSTRUMENT_TIMER; - else if (es->analyze) - instrument_option |= INSTRUMENT_ROWS; - - if (es->buffers) - instrument_option |= INSTRUMENT_BUFFERS; - if (es->wal) - instrument_option |= INSTRUMENT_WAL; + Assert(queryDesc->plannedstmt->commandType != CMD_UTILITY); /* * We always collect timing for the entire statement, even when node-level @@ -555,40 +620,6 @@ ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es, */ INSTR_TIME_SET_CURRENT(starttime); - /* - * Use a snapshot with an updated command ID to ensure this query sees - * results of any previously executed queries. - */ - PushCopiedSnapshot(GetActiveSnapshot()); - UpdateActiveSnapshotCommandId(); - - /* - * Normally we discard the query's output, but if explaining CREATE TABLE - * AS, we'd better use the appropriate tuple receiver. - */ - if (into) - dest = CreateIntoRelDestReceiver(into); - else - dest = None_Receiver; - - /* Create a QueryDesc for the query */ - queryDesc = CreateQueryDesc(plannedstmt, queryString, - GetActiveSnapshot(), InvalidSnapshot, - dest, params, queryEnv, instrument_option); - - /* Select execution options */ - if (es->analyze) - eflags = 0; /* default run-to-completion flags */ - else - eflags = EXEC_FLAG_EXPLAIN_ONLY; - if (es->generic) - eflags |= EXEC_FLAG_EXPLAIN_GENERIC; - if (into) - eflags |= GetIntoRelEFlags(into); - - /* call ExecutorStart to prepare the plan for execution */ - ExecutorStart(queryDesc, eflags); - /* Execute the plan for statistics if asked for */ if (es->analyze) { @@ -4865,6 +4896,17 @@ ExplainDummyGroup(const char *objtype, const char *labelname, ExplainState *es) } } +/* + * Discard output buffer for a fresh restart. + */ +void +ExplainResetOutput(ExplainState *es) +{ + Assert(es->str); + resetStringInfo(es->str); + ExplainBeginOutput(es); +} + /* * Emit the start-of-output boilerplate. * diff --git a/src/backend/commands/extension.c b/src/backend/commands/extension.c index 4cc994ca31..477c299112 100644 --- a/src/backend/commands/extension.c +++ b/src/backend/commands/extension.c @@ -795,13 +795,16 @@ execute_sql_string(const char *sql) if (stmt->utilityStmt == NULL) { QueryDesc *qdesc; + bool plan_valid PG_USED_FOR_ASSERTS_ONLY; qdesc = CreateQueryDesc(stmt, + NULL, sql, GetActiveSnapshot(), NULL, dest, NULL, NULL, 0); - ExecutorStart(qdesc, 0); + plan_valid = ExecutorStart(qdesc, 0); + Assert(plan_valid); ExecutorRun(qdesc, ForwardScanDirection, 0, true); ExecutorFinish(qdesc); ExecutorEnd(qdesc); diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index ac2e74fa3f..fb0b29384c 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -408,12 +408,17 @@ refresh_matview_datafill(DestReceiver *dest, Query *query, UpdateActiveSnapshotCommandId(); /* Create a QueryDesc, redirecting output to our tuple receiver */ - queryDesc = CreateQueryDesc(plan, queryString, + queryDesc = CreateQueryDesc(plan, NULL, queryString, GetActiveSnapshot(), InvalidSnapshot, dest, NULL, NULL, 0); /* call ExecutorStart to prepare the plan for execution */ - ExecutorStart(queryDesc, 0); + { + bool plan_valid PG_USED_FOR_ASSERTS_ONLY; + + plan_valid = ExecutorStart(queryDesc, 0); + Assert(plan_valid); + } /* run the plan */ ExecutorRun(queryDesc, ForwardScanDirection, 0, true); diff --git a/src/backend/commands/portalcmds.c b/src/backend/commands/portalcmds.c index 73ed7aa2f0..fdce72c9a5 100644 --- a/src/backend/commands/portalcmds.c +++ b/src/backend/commands/portalcmds.c @@ -143,9 +143,14 @@ PerformCursorOpen(ParseState *pstate, DeclareCursorStmt *cstmt, ParamListInfo pa /* * Start execution, inserting parameters if any. */ - PortalStart(portal, params, 0, GetActiveSnapshot()); + { + bool plan_valid PG_USED_FOR_ASSERTS_ONLY; + + plan_valid = PortalStart(portal, params, 0, GetActiveSnapshot()); - Assert(portal->strategy == PORTAL_ONE_SELECT); + Assert(portal->strategy == PORTAL_ONE_SELECT); + Assert(plan_valid); + } /* * We're done; the query won't actually be run until PerformPortalFetch is @@ -249,6 +254,17 @@ PerformPortalClose(const char *name) PortalDrop(portal, false); } +/* + * Release a portal's QueryDesc. + */ +void +PortalQueryFinish(QueryDesc *queryDesc) +{ + ExecutorFinish(queryDesc); + ExecutorEnd(queryDesc); + FreeQueryDesc(queryDesc); +} + /* * PortalCleanup * @@ -295,9 +311,7 @@ PortalCleanup(Portal portal) if (portal->resowner) CurrentResourceOwner = portal->resowner; - ExecutorFinish(queryDesc); - ExecutorEnd(queryDesc); - FreeQueryDesc(queryDesc); + PortalQueryFinish(queryDesc); CurrentResourceOwner = saveResourceOwner; } diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c index 18f70319fc..07f0421182 100644 --- a/src/backend/commands/prepare.c +++ b/src/backend/commands/prepare.c @@ -183,6 +183,7 @@ ExecuteQuery(ParseState *pstate, paramLI = EvaluateParams(pstate, entry, stmt->params, estate); } +replan: /* Create a new portal to run the query in */ portal = CreateNewPortal(); /* Don't display the portal in pg_cursors, it is for internal use only */ @@ -251,9 +252,16 @@ ExecuteQuery(ParseState *pstate, } /* - * Run the portal as appropriate. + * Run the portal as appropriate. If the portal contains a cached plan, it + * must be recreated if portal->plan_valid is false which tells that the + * cached plan was found to have been invalidated when initializing one of + * the plan trees contained in it. */ - PortalStart(portal, paramLI, eflags, GetActiveSnapshot()); + if (!PortalStart(portal, paramLI, eflags, GetActiveSnapshot())) + { + PortalDrop(portal, false); + goto replan; + } (void) PortalRun(portal, count, false, true, dest, dest, qc); @@ -574,7 +582,7 @@ ExplainExecuteQuery(ExecuteStmt *execstmt, IntoClause *into, ExplainState *es, { PreparedStatement *entry; const char *query_string; - CachedPlan *cplan; + CachedPlan *cplan = NULL; List *plan_list; ListCell *p; ParamListInfo paramLI = NULL; @@ -618,6 +626,7 @@ ExplainExecuteQuery(ExecuteStmt *execstmt, IntoClause *into, ExplainState *es, } /* Replan if needed, and acquire a transient refcount */ +replan: cplan = GetCachedPlan(entry->plansource, paramLI, CurrentResourceOwner, queryEnv); @@ -639,8 +648,21 @@ ExplainExecuteQuery(ExecuteStmt *execstmt, IntoClause *into, ExplainState *es, PlannedStmt *pstmt = lfirst_node(PlannedStmt, p); if (pstmt->commandType != CMD_UTILITY) - ExplainOnePlan(pstmt, into, es, query_string, paramLI, queryEnv, - &planduration, (es->buffers ? &bufusage : NULL)); + { + QueryDesc *queryDesc; + + queryDesc = ExplainQueryDesc(pstmt, cplan, queryString, + into, es, paramLI, queryEnv); + if (queryDesc == NULL) + { + ExplainResetOutput(es); + ReleaseCachedPlan(cplan, CurrentResourceOwner); + goto replan; + } + ExplainOnePlan(queryDesc, into, es, query_string, paramLI, + queryEnv, &planduration, + (es->buffers ? &bufusage : NULL)); + } else ExplainOneUtility(pstmt->utilityStmt, into, es, query_string, paramLI, queryEnv); diff --git a/src/backend/executor/README b/src/backend/executor/README index 67a5c1769b..f0312376c5 100644 --- a/src/backend/executor/README +++ b/src/backend/executor/README @@ -280,6 +280,39 @@ are typically reset to empty once per tuple. Per-tuple contexts are usually associated with ExprContexts, and commonly each PlanState node has its own ExprContext to evaluate its qual and targetlist expressions in. +Relation Locking +---------------- + +Normally, the executor does not lock non-index relations appearing in a given +plan tree when initializing it for execution if the plan tree is freshly +created, that is, not derived from a CachedPlan. The reason for that is that +the locks must already have been taken during parsing, rewriting, and planning +of the query in that case. If the plan tree is a cached one, there may still +be unlocked relations present in the plan tree, because GetCachedPlan() only +locks the relations that would be present in the query's range table before +planning occurs, but not relations that would have been added to the range +table during planning. This means that inheritance child tables present in +a cached plan, which are added to the query's range table during planning, +would not have been locked when the plan enters the executor. + +GetCachedPlan() punts on locking child tables because not all may actually be +scanned during a given execution of the plan if the child tables are partitions +which may get pruned away due to executor-initialization-time pruning. So the +locking of child tables is made to wait till execution-initialization-time, +which occurs during ExecInitNode() on the plan nodes containing the child +tables. + +So, there's a time window during which a cached plan tree could go stale +if it contains child tables, because they could get changed in other backends +before ExecInitNode() gets a lock on them. This means the executor now must +check the validity of the plan tree every time it takes a lock on a child +table contained in the tree (after executor-initialization-pruning, if any, +has been performed), which it does by looking at CachedPlan.is_valid of the +CachedPlan passed to it. If the plan tree is indeed stale (is_valid=false), +the executor must give up continuing to initialize it any further and return +to the caller letting it know that the execution must be retried with a new +plan tree. + Query Processing Control Flow ----------------------------- @@ -316,6 +349,12 @@ This is a sketch of control flow for full query processing: FreeQueryDesc +As mentioned in the "Relation Locking" section, if the plan tree is found to +be stale during one of the recursive calls of ExecInitNode() after taking a +lock on a child table, the control is immmediately returned to the caller of +ExecutorStart(), which must redo the steps from CreateQueryDesc with a new +plan tree. + Per above comments, it's not really critical for ExecEndPlan to free any memory; it'll all go away in FreeExecutorState anyway. However, we do need to be careful to close relations, drop buffer pins, etc, so we do need to scan diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c index 235bb52ccc..4a4b4b7690 100644 --- a/src/backend/executor/execMain.c +++ b/src/backend/executor/execMain.c @@ -79,7 +79,7 @@ ExecutorEnd_hook_type ExecutorEnd_hook = NULL; ExecutorCheckPerms_hook_type ExecutorCheckPerms_hook = NULL; /* decls for local routines only used within this module */ -static void InitPlan(QueryDesc *queryDesc, int eflags); +static bool InitPlan(QueryDesc *queryDesc, int eflags); static void CheckValidRowMarkRel(Relation rel, RowMarkType markType); static void ExecPostprocessPlan(EState *estate); static void ExecEndPlan(EState *estate); @@ -128,7 +128,7 @@ static void EvalPlanQualStart(EPQState *epqstate, Plan *planTree); * * ---------------------------------------------------------------- */ -void +bool ExecutorStart(QueryDesc *queryDesc, int eflags) { /* @@ -140,14 +140,15 @@ ExecutorStart(QueryDesc *queryDesc, int eflags) pgstat_report_query_id(queryDesc->plannedstmt->queryId, false); if (ExecutorStart_hook) - (*ExecutorStart_hook) (queryDesc, eflags); - else - standard_ExecutorStart(queryDesc, eflags); + return (*ExecutorStart_hook) (queryDesc, eflags); + + return standard_ExecutorStart(queryDesc, eflags); } -void +bool standard_ExecutorStart(QueryDesc *queryDesc, int eflags) { + bool plan_valid; EState *estate; MemoryContext oldcontext; @@ -263,9 +264,11 @@ standard_ExecutorStart(QueryDesc *queryDesc, int eflags) /* * Initialize the plan state tree */ - InitPlan(queryDesc, eflags); + plan_valid = InitPlan(queryDesc, eflags); MemoryContextSwitchTo(oldcontext); + + return plan_valid; } /* ---------------------------------------------------------------- @@ -620,6 +623,17 @@ ExecCheckPermissions(List *rangeTable, List *rteperminfos, RTEPermissionInfo *perminfo = lfirst_node(RTEPermissionInfo, l); Assert(OidIsValid(perminfo->relid)); + + /* + * Relations whose permissions need to be checked must already have + * been locked by the parser or by GetCachedPlan() if a cached plan is + * being executed. + * + * XXX shouldn't we skip calling ExecCheckPermissions from InitPlan + * in a parallel worker? + */ + Assert(CheckRelLockedByMe(perminfo->relid, AccessShareLock, true) || + IsParallelWorker()); result = ExecCheckOneRelPerms(perminfo); if (!result) { @@ -829,9 +843,26 @@ ExecCheckXactReadOnly(PlannedStmt *plannedstmt) * * Initializes the query plan: open files, allocate storage * and start up the rule manager + * + * + * Normally, the plan tree given in queryDesc->plannedstmt is known to be + * valid in a race-free manner, that is, all relations contained in + * plannedstmt->relationOids would have already been locked. That is not the + * case however if the plannedstmt comes from a CachedPlan, one given in + * queryDesc->cplan. That's because GetCachedPlan() only locks the tables + * that are mentioned in the original query but not the child tables, which + * would have been added to the plan by the planner. In that case, locks on + * child tables will be taken when initializing their Scan nodes in + * ExecInitNode() to be done here. If the CachedPlan gets invalidated as + * those locks are taken, plan tree initialization is suspended at the point + * where the invalidation is first detected, queryDesc->planstate will be set + * to NULL, and queryDesc->plan_valid to false. Callers must retry the + * execution after creating a new CachedPlan in that case, after properly + * releasing the resources of this QueryDesc, which includes calling + * ExecutorFinish() and ExecutorEnd() on the EState contained therein. * ---------------------------------------------------------------- */ -static void +static bool InitPlan(QueryDesc *queryDesc, int eflags) { CmdType operation = queryDesc->operation; @@ -839,7 +870,7 @@ InitPlan(QueryDesc *queryDesc, int eflags) Plan *plan = plannedstmt->planTree; List *rangeTable = plannedstmt->rtable; EState *estate = queryDesc->estate; - PlanState *planstate; + PlanState *planstate = NULL; TupleDesc tupType; ListCell *l; int i; @@ -850,10 +881,11 @@ InitPlan(QueryDesc *queryDesc, int eflags) ExecCheckPermissions(rangeTable, plannedstmt->permInfos, true); /* - * initialize the node's execution state + * Set up range table in EState. */ ExecInitRangeTable(estate, rangeTable, plannedstmt->permInfos); + estate->es_cachedplan = queryDesc->cplan; estate->es_plannedstmt = plannedstmt; /* @@ -886,6 +918,8 @@ InitPlan(QueryDesc *queryDesc, int eflags) case ROW_MARK_KEYSHARE: case ROW_MARK_REFERENCE: relation = ExecGetRangeTableRelation(estate, rc->rti); + if (!ExecPlanStillValid(estate)) + goto plan_init_suspended; break; case ROW_MARK_COPY: /* no physical table access is required */ @@ -953,6 +987,11 @@ InitPlan(QueryDesc *queryDesc, int eflags) sp_eflags |= EXEC_FLAG_REWIND; subplanstate = ExecInitNode(subplan, estate, sp_eflags); + if (!ExecPlanStillValid(estate)) + { + Assert(subplanstate == NULL); + goto plan_init_suspended; + } estate->es_subplanstates = lappend(estate->es_subplanstates, subplanstate); @@ -966,6 +1005,11 @@ InitPlan(QueryDesc *queryDesc, int eflags) * processing tuples. */ planstate = ExecInitNode(plan, estate, eflags); + if (!ExecPlanStillValid(estate)) + { + Assert(planstate == NULL); + goto plan_init_suspended; + } /* * Get the tuple descriptor describing the type of tuples to return. @@ -1008,7 +1052,18 @@ InitPlan(QueryDesc *queryDesc, int eflags) } queryDesc->tupDesc = tupType; + Assert(planstate != NULL); queryDesc->planstate = planstate; + return true; + +plan_init_suspended: + /* + * Plan initialization failed. Mark QueryDesc as such. ExecEndPlan() + * will clean up initialized plan nodes from estate->es_inited_plannodes. + */ + Assert(planstate == NULL); + queryDesc->planstate = NULL; + return false; } /* @@ -1426,7 +1481,7 @@ ExecGetAncestorResultRels(EState *estate, ResultRelInfo *resultRelInfo) /* * All ancestors up to the root target relation must have been - * locked by the planner or AcquireExecutorLocks(). + * locked by the planner or ExecLockAppendNonLeafRelations(). */ ancRel = table_open(ancOid, NoLock); rInfo = makeNode(ResultRelInfo); @@ -2856,7 +2911,8 @@ EvalPlanQualStart(EPQState *epqstate, Plan *planTree) * Child EPQ EStates share the parent's copy of unchanging state such as * the snapshot, rangetable, and external Param info. They need their own * copies of local state, including a tuple table, es_param_exec_vals, - * result-rel info, etc. + * result-rel info, etc. Also, we don't pass the parent't copy of the + * CachedPlan, because no new locks will be taken for EvalPlanQual(). */ rcestate->es_direction = ForwardScanDirection; rcestate->es_snapshot = parentestate->es_snapshot; @@ -2943,6 +2999,12 @@ EvalPlanQualStart(EPQState *epqstate, Plan *planTree) PlanState *subplanstate; subplanstate = ExecInitNode(subplan, rcestate, 0); + + /* + * At this point, we had better not received any new invalidation + * messages that would have caused the plan tree to go stale. + */ + Assert(ExecPlanStillValid(rcestate) && subplanstate); rcestate->es_subplanstates = lappend(rcestate->es_subplanstates, subplanstate); } @@ -2986,6 +3048,12 @@ EvalPlanQualStart(EPQState *epqstate, Plan *planTree) */ epqstate->recheckplanstate = ExecInitNode(planTree, rcestate, 0); + /* + * At this point, we had better not received any new invalidation messages + * that would have caused the plan tree to go stale. + */ + Assert(ExecPlanStillValid(rcestate) && epqstate->recheckplanstate); + MemoryContextSwitchTo(oldcontext); } @@ -3008,6 +3076,10 @@ EvalPlanQualEnd(EPQState *epqstate) MemoryContext oldcontext; ListCell *l; + /* Nothing to do if EvalPlanQualInit() wasn't done to begin with. */ + if (epqstate->parentestate == NULL) + return; + rtsize = epqstate->parentestate->es_range_table_size; /* diff --git a/src/backend/executor/execParallel.c b/src/backend/executor/execParallel.c index cc2b8ccab7..d32bc74609 100644 --- a/src/backend/executor/execParallel.c +++ b/src/backend/executor/execParallel.c @@ -1248,8 +1248,17 @@ ExecParallelGetQueryDesc(shm_toc *toc, DestReceiver *receiver, paramspace = shm_toc_lookup(toc, PARALLEL_KEY_PARAMLISTINFO, false); paramLI = RestoreParamList(¶mspace); - /* Create a QueryDesc for the query. */ + /* + * Create a QueryDesc for the query. Note that no CachedPlan is available + * here even if the leader may have gotten the plan tree from one. That's + * fine though, because the leader would have taken the locks necessary + * for the plan tree that we have here to be fully valid. That is true + * despite the fact that we will be taking our own copies of those locks + * in ExecGetRangeTableRelation(), because none of them would be the locks + * that are not already taken by the leader. + */ return CreateQueryDesc(pstmt, + NULL, queryString, GetActiveSnapshot(), InvalidSnapshot, receiver, paramLI, NULL, instrument_options); @@ -1430,7 +1439,12 @@ ParallelQueryMain(dsm_segment *seg, shm_toc *toc) /* Start up the executor */ queryDesc->plannedstmt->jitFlags = fpes->jit_flags; - ExecutorStart(queryDesc, fpes->eflags); + { + bool plan_valid PG_USED_FOR_ASSERTS_ONLY; + + plan_valid = ExecutorStart(queryDesc, fpes->eflags); + Assert(plan_valid); + } /* Special executor initialization steps for parallel workers */ queryDesc->planstate->state->es_query_dsa = area; diff --git a/src/backend/executor/execPartition.c b/src/backend/executor/execPartition.c index eb8a87fd63..cf73d28baa 100644 --- a/src/backend/executor/execPartition.c +++ b/src/backend/executor/execPartition.c @@ -513,6 +513,13 @@ ExecInitPartitionInfo(ModifyTableState *mtstate, EState *estate, oldcxt = MemoryContextSwitchTo(proute->memcxt); + /* + * Note that while we normally check ExecPlanStillValid(estate) after each + * lock taken during execution initialization, it is fine not do so for + * partitions opened here, for tuple routing. Locks taken here can't + * possibly invalidate the plan given that the plan doesn't contain any + * info about those partitions. + */ partrel = table_open(partOid, RowExclusiveLock); leaf_part_rri = makeNode(ResultRelInfo); @@ -1111,6 +1118,9 @@ ExecInitPartitionDispatchInfo(EState *estate, * Only sub-partitioned tables need to be locked here. The root * partitioned table will already have been locked as it's referenced in * the query's rtable. + * + * See the comment in ExecInitPartitionInfo() about taking locks and + * not checking ExecPlanStillValid(estate) here. */ if (partoid != RelationGetRelid(proute->partition_root)) rel = table_open(partoid, RowExclusiveLock); @@ -1801,6 +1811,8 @@ ExecInitPartitionPruning(PlanState *planstate, /* Create the working data structure for pruning */ prunestate = CreatePartitionPruneState(planstate, pruneinfo); + if (!ExecPlanStillValid(estate)) + return NULL; /* * Perform an initial partition prune pass, if required. @@ -1927,6 +1939,8 @@ CreatePartitionPruneState(PlanState *planstate, PartitionPruneInfo *pruneinfo) * duration of this executor run. */ partrel = ExecGetRangeTableRelation(estate, pinfo->rtindex); + if (!ExecPlanStillValid(estate)) + return NULL; partkey = RelationGetPartitionKey(partrel); partdesc = PartitionDirectoryLookup(estate->es_partition_directory, partrel); diff --git a/src/backend/executor/execProcnode.c b/src/backend/executor/execProcnode.c index 653f74cf58..2dcacafd03 100644 --- a/src/backend/executor/execProcnode.c +++ b/src/backend/executor/execProcnode.c @@ -135,10 +135,17 @@ static bool ExecShutdownNode_walker(PlanState *node, void *context); * 'estate' is the shared execution state for the plan tree * 'eflags' is a bitwise OR of flag bits described in executor.h * - * Returns a PlanState node corresponding to the given Plan node. + * Returns a PlanState node corresponding to the given Plan node or NULL. * - * As a side-effect, all PlanState nodes that are created are appended to - * estate->es_planstate_nodes for the cleanup processing in ExecEndPlan(). + * NULL may be returned either if the input node is NULL or if the plan + * tree that the node is a part of is found to have been invalidated when + * taking a lock on the relation mentioned in the node or in a child + * node. The latter case arises if the plan tree contains inheritance/ + * partition child tables and is from a CachedPlan. + * + * As a side-effect, all PlanState nodes that are successfully created are + * appended to estate->es_planstate_nodes for the cleanup processing in + * ExecEndPlan(). * ------------------------------------------------------------------------ */ PlanState * @@ -391,6 +398,13 @@ ExecInitNode(Plan *node, EState *estate, int eflags) break; } + if (!ExecPlanStillValid(estate)) + { + Assert(result == NULL); + return NULL; + } + + Assert(result != NULL); ExecSetExecProcNode(result, result->ExecProcNode); /* diff --git a/src/backend/executor/execUtils.c b/src/backend/executor/execUtils.c index b567165003..ee12235b2f 100644 --- a/src/backend/executor/execUtils.c +++ b/src/backend/executor/execUtils.c @@ -806,7 +806,25 @@ ExecGetRangeTableRelation(EState *estate, Index rti) Assert(rte->rtekind == RTE_RELATION); - if (!IsParallelWorker()) + if (IsParallelWorker() || + (estate->es_cachedplan != NULL && !rte->inFromCl)) + { + /* + * Take a lock if we are a parallel worker or if this is a child + * table referenced in a cached plan. + * + * Parallel workers need to have their own local lock on the + * relation. This ensures sane behavior in case the parent process + * exits before we do. + * + * When executing a cached plan, child tables must be locked + * here, because plancache.c (GetCachedPlan()) would only have + * locked tables mentioned in the query, that is, tables whose + * RTEs' inFromCl is true. + */ + rel = table_open(rte->relid, rte->rellockmode); + } + else { /* * In a normal query, we should already have the appropriate lock, @@ -819,15 +837,6 @@ ExecGetRangeTableRelation(EState *estate, Index rti) Assert(rte->rellockmode == AccessShareLock || CheckRelationLockedByMe(rel, rte->rellockmode, false)); } - else - { - /* - * If we are a parallel worker, we need to obtain our own local - * lock on the relation. This ensures sane behavior in case the - * parent process exits before we do. - */ - rel = table_open(rte->relid, rte->rellockmode); - } estate->es_relations[rti - 1] = rel; } @@ -835,6 +844,38 @@ ExecGetRangeTableRelation(EState *estate, Index rti) return rel; } +/* + * ExecLockAppendNonLeafRelations + * Lock non-leaf relations whose children are scanned by a given + * Append/MergeAppend node + */ +void +ExecLockAppendNonLeafRelations(EState *estate, List *allpartrelids) +{ + ListCell *l; + + /* This should get called only when executing cached plans. */ + Assert(estate->es_cachedplan != NULL); + foreach(l, allpartrelids) + { + Bitmapset *partrelids = lfirst_node(Bitmapset, l); + int i; + + /* + * Note that we don't lock the first member (i=0) of each bitmapset + * because it stands for the root parent mentioned in the query that + * should always have been locked before entering the executor. + */ + i = 0; + while ((i = bms_next_member(partrelids, i)) > 0) + { + RangeTblEntry *rte = exec_rt_fetch(i, estate); + + LockRelationOid(rte->relid, rte->rellockmode); + } + } +} + /* * ExecInitResultRelation * Open relation given by the passed-in RT index and fill its @@ -850,6 +891,8 @@ ExecInitResultRelation(EState *estate, ResultRelInfo *resultRelInfo, Relation resultRelationDesc; resultRelationDesc = ExecGetRangeTableRelation(estate, rti); + if (!ExecPlanStillValid(estate)) + return; InitResultRelInfo(resultRelInfo, resultRelationDesc, rti, diff --git a/src/backend/executor/functions.c b/src/backend/executor/functions.c index f55424eb5a..bc09ef992c 100644 --- a/src/backend/executor/functions.c +++ b/src/backend/executor/functions.c @@ -838,6 +838,7 @@ postquel_start(execution_state *es, SQLFunctionCachePtr fcache) dest = None_Receiver; es->qd = CreateQueryDesc(es->stmt, + NULL, /* fmgr_sql() doesn't use CachedPlans */ fcache->src, GetActiveSnapshot(), InvalidSnapshot, @@ -857,12 +858,14 @@ postquel_start(execution_state *es, SQLFunctionCachePtr fcache) * lazyEval mode for any statement that could possibly queue triggers. */ int eflags; + bool plan_valid PG_USED_FOR_ASSERTS_ONLY; if (es->lazyEval) eflags = EXEC_FLAG_SKIP_TRIGGERS; else eflags = 0; /* default run-to-completion flags */ - ExecutorStart(es->qd, eflags); + plan_valid = ExecutorStart(es->qd, eflags); + Assert(plan_valid); } es->status = F_EXEC_RUN; diff --git a/src/backend/executor/nodeAgg.c b/src/backend/executor/nodeAgg.c index e9d9ab6bdd..9553a85115 100644 --- a/src/backend/executor/nodeAgg.c +++ b/src/backend/executor/nodeAgg.c @@ -3304,6 +3304,8 @@ ExecInitAgg(Agg *node, EState *estate, int eflags) eflags &= ~EXEC_FLAG_REWIND; outerPlan = outerPlan(node); outerPlanState(aggstate) = ExecInitNode(outerPlan, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * initialize source tuple type. diff --git a/src/backend/executor/nodeAppend.c b/src/backend/executor/nodeAppend.c index 9148d7d3b1..b0cae25b33 100644 --- a/src/backend/executor/nodeAppend.c +++ b/src/backend/executor/nodeAppend.c @@ -133,6 +133,27 @@ ExecInitAppend(Append *node, EState *estate, int eflags) appendstate->as_syncdone = false; appendstate->as_begun = false; + /* + * Must take locks on child tables if running a cached plan, because + * GetCachedPlan() would've only locked the root parent named in the + * query. + * + * First lock non-leaf partitions before doing pruning if any. Even when + * no pruning is to be done, non-leaf partitions still must be locked + * explicitly like this, because they're not referenced elsewhere in + * the plan tree. XXX - OTOH, non-leaf partitions mentioned in + * part_prune_info, if any, would be opened by ExecInitPartitionPruning() + * using ExecGetRangeTableRelation() which locks child tables, redundantly + * in this case. + */ + if (estate->es_cachedplan) + { + ExecLockAppendNonLeafRelations(estate, node->allpartrelids); + if (!ExecPlanStillValid(estate)) + return NULL; + + } + /* If run-time partition pruning is enabled, then set that up now */ if (node->part_prune_info != NULL) { @@ -147,6 +168,8 @@ ExecInitAppend(Append *node, EState *estate, int eflags) list_length(node->appendplans), node->part_prune_info, &validsubplans); + if (!ExecPlanStillValid(estate)) + return NULL; appendstate->as_prune_state = prunestate; nplans = bms_num_members(validsubplans); @@ -221,6 +244,8 @@ ExecInitAppend(Append *node, EState *estate, int eflags) firstvalid = j; appendplanstates[j++] = ExecInitNode(initNode, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; } appendstate->as_first_partial_plan = firstvalid; diff --git a/src/backend/executor/nodeBitmapAnd.c b/src/backend/executor/nodeBitmapAnd.c index 147592f7e2..53afcef21c 100644 --- a/src/backend/executor/nodeBitmapAnd.c +++ b/src/backend/executor/nodeBitmapAnd.c @@ -88,8 +88,9 @@ ExecInitBitmapAnd(BitmapAnd *node, EState *estate, int eflags) foreach(l, node->bitmapplans) { initNode = (Plan *) lfirst(l); - bitmapplanstates[i] = ExecInitNode(initNode, estate, eflags); - i++; + bitmapplanstates[i++] = ExecInitNode(initNode, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; } /* diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c index d58ee4f4e1..388a02ec99 100644 --- a/src/backend/executor/nodeBitmapHeapscan.c +++ b/src/backend/executor/nodeBitmapHeapscan.c @@ -760,11 +760,15 @@ ExecInitBitmapHeapScan(BitmapHeapScan *node, EState *estate, int eflags) * open the scan relation */ currentRelation = ExecOpenScanRelation(estate, node->scan.scanrelid, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * initialize child nodes */ outerPlanState(scanstate) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * get the scan type from the relation descriptor. diff --git a/src/backend/executor/nodeBitmapIndexscan.c b/src/backend/executor/nodeBitmapIndexscan.c index 83ec9ede89..99015812a1 100644 --- a/src/backend/executor/nodeBitmapIndexscan.c +++ b/src/backend/executor/nodeBitmapIndexscan.c @@ -211,6 +211,7 @@ BitmapIndexScanState * ExecInitBitmapIndexScan(BitmapIndexScan *node, EState *estate, int eflags) { BitmapIndexScanState *indexstate; + Relation indexRelation; LOCKMODE lockmode; /* check for unsupported flags */ @@ -262,7 +263,13 @@ ExecInitBitmapIndexScan(BitmapIndexScan *node, EState *estate, int eflags) /* Open the index relation. */ lockmode = exec_rt_fetch(node->scan.scanrelid, estate)->rellockmode; - indexstate->biss_RelationDesc = index_open(node->indexid, lockmode); + indexRelation = index_open(node->indexid, lockmode); + if (!ExecPlanStillValid(estate)) + { + index_close(indexRelation, lockmode); + return NULL; + } + indexstate->biss_RelationDesc = indexRelation; /* * Initialize index-specific scan state diff --git a/src/backend/executor/nodeBitmapOr.c b/src/backend/executor/nodeBitmapOr.c index 736852a0ae..425f22ee48 100644 --- a/src/backend/executor/nodeBitmapOr.c +++ b/src/backend/executor/nodeBitmapOr.c @@ -89,8 +89,9 @@ ExecInitBitmapOr(BitmapOr *node, EState *estate, int eflags) foreach(l, node->bitmapplans) { initNode = (Plan *) lfirst(l); - bitmapplanstates[i] = ExecInitNode(initNode, estate, eflags); - i++; + bitmapplanstates[i++] = ExecInitNode(initNode, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; } /* diff --git a/src/backend/executor/nodeCustom.c b/src/backend/executor/nodeCustom.c index bd42c65b29..91239cc500 100644 --- a/src/backend/executor/nodeCustom.c +++ b/src/backend/executor/nodeCustom.c @@ -61,6 +61,8 @@ ExecInitCustomScan(CustomScan *cscan, EState *estate, int eflags) if (scanrelid > 0) { scan_rel = ExecOpenScanRelation(estate, scanrelid, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; css->ss.ss_currentRelation = scan_rel; } diff --git a/src/backend/executor/nodeForeignscan.c b/src/backend/executor/nodeForeignscan.c index e6616dd718..71495313db 100644 --- a/src/backend/executor/nodeForeignscan.c +++ b/src/backend/executor/nodeForeignscan.c @@ -173,6 +173,8 @@ ExecInitForeignScan(ForeignScan *node, EState *estate, int eflags) if (scanrelid > 0) { currentRelation = ExecOpenScanRelation(estate, scanrelid, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; scanstate->ss.ss_currentRelation = currentRelation; fdwroutine = GetFdwRoutineForRelation(currentRelation, true); } @@ -264,6 +266,8 @@ ExecInitForeignScan(ForeignScan *node, EState *estate, int eflags) if (outerPlan(node)) outerPlanState(scanstate) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * Tell the FDW to initialize the scan. diff --git a/src/backend/executor/nodeGather.c b/src/backend/executor/nodeGather.c index f7a69f185b..c5652aeb2d 100644 --- a/src/backend/executor/nodeGather.c +++ b/src/backend/executor/nodeGather.c @@ -89,6 +89,9 @@ ExecInitGather(Gather *node, EState *estate, int eflags) */ outerNode = outerPlan(node); outerPlanState(gatherstate) = ExecInitNode(outerNode, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; + tupDesc = ExecGetResultType(outerPlanState(gatherstate)); /* diff --git a/src/backend/executor/nodeGatherMerge.c b/src/backend/executor/nodeGatherMerge.c index d357ff0c47..1191b9e420 100644 --- a/src/backend/executor/nodeGatherMerge.c +++ b/src/backend/executor/nodeGatherMerge.c @@ -108,6 +108,8 @@ ExecInitGatherMerge(GatherMerge *node, EState *estate, int eflags) */ outerNode = outerPlan(node); outerPlanState(gm_state) = ExecInitNode(outerNode, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * Leader may access ExecProcNode result directly (if diff --git a/src/backend/executor/nodeGroup.c b/src/backend/executor/nodeGroup.c index 2badcc7e60..b4c3044c1f 100644 --- a/src/backend/executor/nodeGroup.c +++ b/src/backend/executor/nodeGroup.c @@ -185,6 +185,8 @@ ExecInitGroup(Group *node, EState *estate, int eflags) * initialize child nodes */ outerPlanState(grpstate) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * Initialize scan slot and type. diff --git a/src/backend/executor/nodeHash.c b/src/backend/executor/nodeHash.c index edd2324384..b2119febb6 100644 --- a/src/backend/executor/nodeHash.c +++ b/src/backend/executor/nodeHash.c @@ -386,6 +386,8 @@ ExecInitHash(Hash *node, EState *estate, int eflags) * initialize child nodes */ outerPlanState(hashstate) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * initialize our result slot and type. No need to build projection diff --git a/src/backend/executor/nodeHashjoin.c b/src/backend/executor/nodeHashjoin.c index 8078d7f229..d5ff80660e 100644 --- a/src/backend/executor/nodeHashjoin.c +++ b/src/backend/executor/nodeHashjoin.c @@ -752,8 +752,12 @@ ExecInitHashJoin(HashJoin *node, EState *estate, int eflags) hashNode = (Hash *) innerPlan(node); outerPlanState(hjstate) = ExecInitNode(outerNode, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; outerDesc = ExecGetResultType(outerPlanState(hjstate)); innerPlanState(hjstate) = ExecInitNode((Plan *) hashNode, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; innerDesc = ExecGetResultType(innerPlanState(hjstate)); /* diff --git a/src/backend/executor/nodeIncrementalSort.c b/src/backend/executor/nodeIncrementalSort.c index 52b146cfb8..785896e5ea 100644 --- a/src/backend/executor/nodeIncrementalSort.c +++ b/src/backend/executor/nodeIncrementalSort.c @@ -1041,6 +1041,8 @@ ExecInitIncrementalSort(IncrementalSort *node, EState *estate, int eflags) * nodes may be able to do something more useful. */ outerPlanState(incrsortstate) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * Initialize scan slot and type. diff --git a/src/backend/executor/nodeIndexonlyscan.c b/src/backend/executor/nodeIndexonlyscan.c index 0b43a9b969..ea8bef4b97 100644 --- a/src/backend/executor/nodeIndexonlyscan.c +++ b/src/backend/executor/nodeIndexonlyscan.c @@ -490,6 +490,7 @@ ExecInitIndexOnlyScan(IndexOnlyScan *node, EState *estate, int eflags) { IndexOnlyScanState *indexstate; Relation currentRelation; + Relation indexRelation; LOCKMODE lockmode; TupleDesc tupDesc; @@ -512,6 +513,8 @@ ExecInitIndexOnlyScan(IndexOnlyScan *node, EState *estate, int eflags) * open the scan relation */ currentRelation = ExecOpenScanRelation(estate, node->scan.scanrelid, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; indexstate->ss.ss_currentRelation = currentRelation; indexstate->ss.ss_currentScanDesc = NULL; /* no heap scan here */ @@ -564,7 +567,13 @@ ExecInitIndexOnlyScan(IndexOnlyScan *node, EState *estate, int eflags) /* Open the index relation. */ lockmode = exec_rt_fetch(node->scan.scanrelid, estate)->rellockmode; - indexstate->ioss_RelationDesc = index_open(node->indexid, lockmode); + indexRelation = index_open(node->indexid, lockmode); + if (!ExecPlanStillValid(estate)) + { + index_close(indexRelation, lockmode); + return NULL; + } + indexstate->ioss_RelationDesc = indexRelation; /* * Initialize index-specific scan state diff --git a/src/backend/executor/nodeIndexscan.c b/src/backend/executor/nodeIndexscan.c index 4540c7781d..956e9e5543 100644 --- a/src/backend/executor/nodeIndexscan.c +++ b/src/backend/executor/nodeIndexscan.c @@ -904,6 +904,7 @@ ExecInitIndexScan(IndexScan *node, EState *estate, int eflags) { IndexScanState *indexstate; Relation currentRelation; + Relation indexRelation; LOCKMODE lockmode; /* @@ -925,6 +926,8 @@ ExecInitIndexScan(IndexScan *node, EState *estate, int eflags) * open the scan relation */ currentRelation = ExecOpenScanRelation(estate, node->scan.scanrelid, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; indexstate->ss.ss_currentRelation = currentRelation; indexstate->ss.ss_currentScanDesc = NULL; /* no heap scan here */ @@ -969,7 +972,13 @@ ExecInitIndexScan(IndexScan *node, EState *estate, int eflags) /* Open the index relation. */ lockmode = exec_rt_fetch(node->scan.scanrelid, estate)->rellockmode; - indexstate->iss_RelationDesc = index_open(node->indexid, lockmode); + indexRelation = index_open(node->indexid, lockmode); + if (!ExecPlanStillValid(estate)) + { + index_close(indexRelation, lockmode); + return NULL; + } + indexstate->iss_RelationDesc = indexRelation; /* * Initialize index-specific scan state diff --git a/src/backend/executor/nodeLimit.c b/src/backend/executor/nodeLimit.c index a75099dd73..a1fc36a3f0 100644 --- a/src/backend/executor/nodeLimit.c +++ b/src/backend/executor/nodeLimit.c @@ -476,6 +476,8 @@ ExecInitLimit(Limit *node, EState *estate, int eflags) */ outerPlan = outerPlan(node); outerPlanState(limitstate) = ExecInitNode(outerPlan, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * initialize child expressions diff --git a/src/backend/executor/nodeLockRows.c b/src/backend/executor/nodeLockRows.c index 55de8d3d65..ff86a82b92 100644 --- a/src/backend/executor/nodeLockRows.c +++ b/src/backend/executor/nodeLockRows.c @@ -322,6 +322,8 @@ ExecInitLockRows(LockRows *node, EState *estate, int eflags) * then initialize outer plan */ outerPlanState(lrstate) = ExecInitNode(outerPlan, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* node returns unmodified slots from the outer plan */ lrstate->ps.resultopsset = true; diff --git a/src/backend/executor/nodeMaterial.c b/src/backend/executor/nodeMaterial.c index ef04e9a8e7..8d02ac0ccb 100644 --- a/src/backend/executor/nodeMaterial.c +++ b/src/backend/executor/nodeMaterial.c @@ -214,6 +214,8 @@ ExecInitMaterial(Material *node, EState *estate, int eflags) outerPlan = outerPlan(node); outerPlanState(matstate) = ExecInitNode(outerPlan, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * Initialize result type and slot. No need to initialize projection info diff --git a/src/backend/executor/nodeMemoize.c b/src/backend/executor/nodeMemoize.c index 61578d4b5c..a994d48fb2 100644 --- a/src/backend/executor/nodeMemoize.c +++ b/src/backend/executor/nodeMemoize.c @@ -938,6 +938,8 @@ ExecInitMemoize(Memoize *node, EState *estate, int eflags) outerNode = outerPlan(node); outerPlanState(mstate) = ExecInitNode(outerNode, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * Initialize return slot and type. No need to initialize projection info diff --git a/src/backend/executor/nodeMergeAppend.c b/src/backend/executor/nodeMergeAppend.c index 8aa64944c9..18808c19ae 100644 --- a/src/backend/executor/nodeMergeAppend.c +++ b/src/backend/executor/nodeMergeAppend.c @@ -81,6 +81,27 @@ ExecInitMergeAppend(MergeAppend *node, EState *estate, int eflags) mergestate->ps.state = estate; mergestate->ps.ExecProcNode = ExecMergeAppend; + /* + * Must take locks on child tables if running a cached plan, because + * GetCachedPlan() would've only locked the root parent named in the + * query. + * + * First lock non-leaf partitions before doing pruning if any. Even when + * no pruning is to be done, non-leaf partitions still must be locked + * explicitly like this, because they're not referenced elsewhere in + * the plan tree. XXX - OTOH, non-leaf partitions mentioned in + * part_prune_info, if any, would be opened by ExecInitPartitionPruning() + * using ExecGetRangeTableRelation() which locks child tables, redundantly + * in this case. + */ + if (estate->es_cachedplan) + { + ExecLockAppendNonLeafRelations(estate, node->allpartrelids); + if (!ExecPlanStillValid(estate)) + return NULL; + + } + /* If run-time partition pruning is enabled, then set that up now */ if (node->part_prune_info != NULL) { @@ -95,6 +116,8 @@ ExecInitMergeAppend(MergeAppend *node, EState *estate, int eflags) list_length(node->mergeplans), node->part_prune_info, &validsubplans); + if (!ExecPlanStillValid(estate)) + return NULL; mergestate->ms_prune_state = prunestate; nplans = bms_num_members(validsubplans); @@ -151,6 +174,8 @@ ExecInitMergeAppend(MergeAppend *node, EState *estate, int eflags) Plan *initNode = (Plan *) list_nth(node->mergeplans, i); mergeplanstates[j++] = ExecInitNode(initNode, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; } mergestate->ps.ps_ProjInfo = NULL; diff --git a/src/backend/executor/nodeMergejoin.c b/src/backend/executor/nodeMergejoin.c index 7b530d9088..0d92ec278a 100644 --- a/src/backend/executor/nodeMergejoin.c +++ b/src/backend/executor/nodeMergejoin.c @@ -1490,11 +1490,15 @@ ExecInitMergeJoin(MergeJoin *node, EState *estate, int eflags) mergestate->mj_SkipMarkRestore = node->skip_mark_restore; outerPlanState(mergestate) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; outerDesc = ExecGetResultType(outerPlanState(mergestate)); innerPlanState(mergestate) = ExecInitNode(innerPlan(node), estate, mergestate->mj_SkipMarkRestore ? eflags : (eflags | EXEC_FLAG_MARK)); + if (!ExecPlanStillValid(estate)) + return NULL; innerDesc = ExecGetResultType(innerPlanState(mergestate)); /* diff --git a/src/backend/executor/nodeModifyTable.c b/src/backend/executor/nodeModifyTable.c index bdbaa4753b..2245a67397 100644 --- a/src/backend/executor/nodeModifyTable.c +++ b/src/backend/executor/nodeModifyTable.c @@ -3984,6 +3984,9 @@ ExecInitModifyTable(ModifyTable *node, EState *estate, int eflags) linitial_int(node->resultRelations)); } + if (!ExecPlanStillValid(estate)) + return NULL; + /* set up epqstate with dummy subplan data for the moment */ EvalPlanQualInit(&mtstate->mt_epqstate, estate, NULL, NIL, node->epqParam, node->resultRelations); @@ -4011,6 +4014,8 @@ ExecInitModifyTable(ModifyTable *node, EState *estate, int eflags) if (resultRelInfo != mtstate->rootResultRelInfo) { ExecInitResultRelation(estate, resultRelInfo, resultRelation); + if (!ExecPlanStillValid(estate)) + return NULL; /* * For child result relations, store the root result relation @@ -4038,6 +4043,8 @@ ExecInitModifyTable(ModifyTable *node, EState *estate, int eflags) * Now we may initialize the subplan. */ outerPlanState(mtstate) = ExecInitNode(subplan, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * Do additional per-result-relation initialization. diff --git a/src/backend/executor/nodeNestloop.c b/src/backend/executor/nodeNestloop.c index 5cfb50a366..e24554f4f8 100644 --- a/src/backend/executor/nodeNestloop.c +++ b/src/backend/executor/nodeNestloop.c @@ -295,11 +295,15 @@ ExecInitNestLoop(NestLoop *node, EState *estate, int eflags) * values. */ outerPlanState(nlstate) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; if (node->nestParams == NIL) eflags |= EXEC_FLAG_REWIND; else eflags &= ~EXEC_FLAG_REWIND; innerPlanState(nlstate) = ExecInitNode(innerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * Initialize result slot, type and projection. diff --git a/src/backend/executor/nodeProjectSet.c b/src/backend/executor/nodeProjectSet.c index 4a388220ee..863bf2cc65 100644 --- a/src/backend/executor/nodeProjectSet.c +++ b/src/backend/executor/nodeProjectSet.c @@ -247,6 +247,8 @@ ExecInitProjectSet(ProjectSet *node, EState *estate, int eflags) * initialize child nodes */ outerPlanState(state) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * we don't use inner plan diff --git a/src/backend/executor/nodeRecursiveunion.c b/src/backend/executor/nodeRecursiveunion.c index aee31c7139..3f3de771d0 100644 --- a/src/backend/executor/nodeRecursiveunion.c +++ b/src/backend/executor/nodeRecursiveunion.c @@ -244,7 +244,11 @@ ExecInitRecursiveUnion(RecursiveUnion *node, EState *estate, int eflags) * initialize child nodes */ outerPlanState(rustate) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; innerPlanState(rustate) = ExecInitNode(innerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * If hashing, precompute fmgr lookup data for inner loop, and create the diff --git a/src/backend/executor/nodeResult.c b/src/backend/executor/nodeResult.c index a100b144be..f2206af451 100644 --- a/src/backend/executor/nodeResult.c +++ b/src/backend/executor/nodeResult.c @@ -208,6 +208,8 @@ ExecInitResult(Result *node, EState *estate, int eflags) * initialize child nodes */ outerPlanState(resstate) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * we don't use inner plan diff --git a/src/backend/executor/nodeSamplescan.c b/src/backend/executor/nodeSamplescan.c index d7e22b1dbb..22357e7a0e 100644 --- a/src/backend/executor/nodeSamplescan.c +++ b/src/backend/executor/nodeSamplescan.c @@ -125,6 +125,8 @@ ExecInitSampleScan(SampleScan *node, EState *estate, int eflags) ExecOpenScanRelation(estate, node->scan.scanrelid, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* we won't set up the HeapScanDesc till later */ scanstate->ss.ss_currentScanDesc = NULL; diff --git a/src/backend/executor/nodeSeqscan.c b/src/backend/executor/nodeSeqscan.c index 4da0f28f7b..b0b34cd14e 100644 --- a/src/backend/executor/nodeSeqscan.c +++ b/src/backend/executor/nodeSeqscan.c @@ -153,6 +153,8 @@ ExecInitSeqScan(SeqScan *node, EState *estate, int eflags) ExecOpenScanRelation(estate, node->scan.scanrelid, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* and create slot with the appropriate rowtype */ ExecInitScanTupleSlot(estate, &scanstate->ss, diff --git a/src/backend/executor/nodeSetOp.c b/src/backend/executor/nodeSetOp.c index f7db9a3415..3535aa298c 100644 --- a/src/backend/executor/nodeSetOp.c +++ b/src/backend/executor/nodeSetOp.c @@ -528,6 +528,8 @@ ExecInitSetOp(SetOp *node, EState *estate, int eflags) if (node->strategy == SETOP_HASHED) eflags &= ~EXEC_FLAG_REWIND; outerPlanState(setopstate) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; outerDesc = ExecGetResultType(outerPlanState(setopstate)); /* diff --git a/src/backend/executor/nodeSort.c b/src/backend/executor/nodeSort.c index 078d041c40..547203ebfd 100644 --- a/src/backend/executor/nodeSort.c +++ b/src/backend/executor/nodeSort.c @@ -263,6 +263,8 @@ ExecInitSort(Sort *node, EState *estate, int eflags) eflags &= ~(EXEC_FLAG_REWIND | EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK); outerPlanState(sortstate) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * Initialize scan slot and type. diff --git a/src/backend/executor/nodeSubqueryscan.c b/src/backend/executor/nodeSubqueryscan.c index bc55a82fc3..8b6629c939 100644 --- a/src/backend/executor/nodeSubqueryscan.c +++ b/src/backend/executor/nodeSubqueryscan.c @@ -124,6 +124,8 @@ ExecInitSubqueryScan(SubqueryScan *node, EState *estate, int eflags) * initialize subquery */ subquerystate->subplan = ExecInitNode(node->subplan, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * Initialize scan slot and type (needed by ExecAssignScanProjectionInfo) diff --git a/src/backend/executor/nodeTidrangescan.c b/src/backend/executor/nodeTidrangescan.c index 2124c55ef5..613b377c7c 100644 --- a/src/backend/executor/nodeTidrangescan.c +++ b/src/backend/executor/nodeTidrangescan.c @@ -386,6 +386,8 @@ ExecInitTidRangeScan(TidRangeScan *node, EState *estate, int eflags) * open the scan relation */ currentRelation = ExecOpenScanRelation(estate, node->scan.scanrelid, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; tidrangestate->ss.ss_currentRelation = currentRelation; tidrangestate->ss.ss_currentScanDesc = NULL; /* no table scan here */ diff --git a/src/backend/executor/nodeTidscan.c b/src/backend/executor/nodeTidscan.c index 862bd0330b..1b0a2d8083 100644 --- a/src/backend/executor/nodeTidscan.c +++ b/src/backend/executor/nodeTidscan.c @@ -529,6 +529,8 @@ ExecInitTidScan(TidScan *node, EState *estate, int eflags) * open the scan relation */ currentRelation = ExecOpenScanRelation(estate, node->scan.scanrelid, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; tidstate->ss.ss_currentRelation = currentRelation; tidstate->ss.ss_currentScanDesc = NULL; /* no heap scan here */ diff --git a/src/backend/executor/nodeUnique.c b/src/backend/executor/nodeUnique.c index 50babacdc8..ae9af8f21e 100644 --- a/src/backend/executor/nodeUnique.c +++ b/src/backend/executor/nodeUnique.c @@ -136,6 +136,8 @@ ExecInitUnique(Unique *node, EState *estate, int eflags) * then initialize outer plan */ outerPlanState(uniquestate) = ExecInitNode(outerPlan(node), estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * Initialize result slot and type. Unique nodes do no projections, so diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c index 648cdadc32..77de2d0c22 100644 --- a/src/backend/executor/nodeWindowAgg.c +++ b/src/backend/executor/nodeWindowAgg.c @@ -2458,6 +2458,8 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) */ outerPlan = outerPlan(node); outerPlanState(winstate) = ExecInitNode(outerPlan, estate, eflags); + if (!ExecPlanStillValid(estate)) + return NULL; /* * initialize source tuple type (which is also the tuple type that we'll diff --git a/src/backend/executor/spi.c b/src/backend/executor/spi.c index 33975687b3..cfee208719 100644 --- a/src/backend/executor/spi.c +++ b/src/backend/executor/spi.c @@ -71,7 +71,7 @@ static int _SPI_execute_plan(SPIPlanPtr plan, const SPIExecuteOptions *options, static ParamListInfo _SPI_convert_params(int nargs, Oid *argtypes, Datum *Values, const char *Nulls); -static int _SPI_pquery(QueryDesc *queryDesc, bool fire_triggers, uint64 tcount); +static int _SPI_pquery(QueryDesc *queryDesc, uint64 tcount); static void _SPI_error_callback(void *arg); @@ -1582,6 +1582,7 @@ SPI_cursor_open_internal(const char *name, SPIPlanPtr plan, Snapshot snapshot; MemoryContext oldcontext; Portal portal; + bool plan_valid; SPICallbackArg spicallbackarg; ErrorContextCallback spierrcontext; @@ -1623,6 +1624,7 @@ SPI_cursor_open_internal(const char *name, SPIPlanPtr plan, _SPI_current->processed = 0; _SPI_current->tuptable = NULL; +replan: /* Create the portal */ if (name == NULL || name[0] == '\0') { @@ -1766,15 +1768,24 @@ SPI_cursor_open_internal(const char *name, SPIPlanPtr plan, } /* - * Start portal execution. + * Start portal execution. If the portal contains a cached plan, it must + * be recreated if portal->plan_valid is false which tells that the cached + * plan was found to have been invalidated when initializing one of the + * plan trees contained in it. */ - PortalStart(portal, paramLI, 0, snapshot); + plan_valid = PortalStart(portal, paramLI, 0, snapshot); Assert(portal->strategy != PORTAL_MULTI_QUERY); /* Pop the error context stack */ error_context_stack = spierrcontext.previous; + if (!plan_valid) + { + PortalDrop(portal, false); + goto replan; + } + /* Pop the SPI stack */ _SPI_end_call(true); @@ -2552,6 +2563,7 @@ _SPI_execute_plan(SPIPlanPtr plan, const SPIExecuteOptions *options, * Replan if needed, and increment plan refcount. If it's a saved * plan, the refcount must be backed by the plan_owner. */ +replan: cplan = GetCachedPlan(plansource, options->params, plan_owner, _SPI_current->queryEnv); @@ -2661,6 +2673,7 @@ _SPI_execute_plan(SPIPlanPtr plan, const SPIExecuteOptions *options, { QueryDesc *qdesc; Snapshot snap; + int eflags; if (ActiveSnapshotSet()) snap = GetActiveSnapshot(); @@ -2668,14 +2681,31 @@ _SPI_execute_plan(SPIPlanPtr plan, const SPIExecuteOptions *options, snap = InvalidSnapshot; qdesc = CreateQueryDesc(stmt, + cplan, plansource->query_string, snap, crosscheck_snapshot, dest, options->params, _SPI_current->queryEnv, 0); - res = _SPI_pquery(qdesc, fire_triggers, - canSetTag ? options->tcount : 0); + + /* Select execution options */ + if (fire_triggers) + eflags = 0; /* default run-to-completion flags */ + else + eflags = EXEC_FLAG_SKIP_TRIGGERS; + + if (!ExecutorStart(qdesc, eflags)) + { + ExecutorFinish(qdesc); + ExecutorEnd(qdesc); + FreeQueryDesc(qdesc); + Assert(cplan); + ReleaseCachedPlan(cplan, plan_owner); + goto replan; + } + + res = _SPI_pquery(qdesc, canSetTag ? options->tcount : 0); FreeQueryDesc(qdesc); } else @@ -2850,10 +2880,9 @@ _SPI_convert_params(int nargs, Oid *argtypes, } static int -_SPI_pquery(QueryDesc *queryDesc, bool fire_triggers, uint64 tcount) +_SPI_pquery(QueryDesc *queryDesc, uint64 tcount) { int operation = queryDesc->operation; - int eflags; int res; switch (operation) @@ -2897,14 +2926,6 @@ _SPI_pquery(QueryDesc *queryDesc, bool fire_triggers, uint64 tcount) ResetUsage(); #endif - /* Select execution options */ - if (fire_triggers) - eflags = 0; /* default run-to-completion flags */ - else - eflags = EXEC_FLAG_SKIP_TRIGGERS; - - ExecutorStart(queryDesc, eflags); - ExecutorRun(queryDesc, ForwardScanDirection, tcount, true); _SPI_current->processed = queryDesc->estate->es_processed; diff --git a/src/backend/storage/lmgr/lmgr.c b/src/backend/storage/lmgr/lmgr.c index ee9b89a672..c807e9cdcc 100644 --- a/src/backend/storage/lmgr/lmgr.c +++ b/src/backend/storage/lmgr/lmgr.c @@ -27,6 +27,7 @@ #include "storage/procarray.h" #include "storage/sinvaladt.h" #include "utils/inval.h" +#include "utils/lsyscache.h" /* @@ -364,6 +365,50 @@ CheckRelationLockedByMe(Relation relation, LOCKMODE lockmode, bool orstronger) return false; } +/* + * CheckRelLockedByMe + * + * Returns true if current transaction holds a lock on the given relation of + * mode 'lockmode'. If 'orstronger' is true, a stronger lockmode is also OK. + * ("Stronger" is defined as "numerically higher", which is a bit + * semantically dubious but is OK for the purposes we use this for.) + */ +bool +CheckRelLockedByMe(Oid relid, LOCKMODE lockmode, bool orstronger) +{ + Oid dbId = get_rel_relisshared(relid) ? InvalidOid : MyDatabaseId; + LOCKTAG tag; + + SET_LOCKTAG_RELATION(tag, dbId, relid); + + if (LockHeldByMe(&tag, lockmode)) + return true; + + if (orstronger) + { + LOCKMODE slockmode; + + for (slockmode = lockmode + 1; + slockmode <= MaxLockMode; + slockmode++) + { + if (LockHeldByMe(&tag, slockmode)) + { +#ifdef NOT_USED + /* Sometimes this might be useful for debugging purposes */ + elog(WARNING, "lock mode %s substituted for %s on relation %s", + GetLockmodeName(tag.locktag_lockmethodid, slockmode), + GetLockmodeName(tag.locktag_lockmethodid, lockmode), + RelationGetRelationName(relation)); +#endif + return true; + } + } + } + + return false; +} + /* * LockHasWaitersRelation * diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c index 36cc99ec9c..cf27fa3968 100644 --- a/src/backend/tcop/postgres.c +++ b/src/backend/tcop/postgres.c @@ -1232,7 +1232,12 @@ exec_simple_query(const char *query_string) /* * Start the portal. No parameters here. */ - PortalStart(portal, NULL, 0, InvalidSnapshot); + { + bool plan_valid PG_USED_FOR_ASSERTS_ONLY; + + plan_valid = PortalStart(portal, NULL, 0, InvalidSnapshot); + Assert(plan_valid); + } /* * Select the appropriate output format: text unless we are doing a @@ -1737,6 +1742,7 @@ exec_bind_message(StringInfo input_message) "commands ignored until end of transaction block"), errdetail_abort())); +replan: /* * Create the portal. Allow silent replacement of an existing portal only * if the unnamed portal is specified. @@ -2028,9 +2034,16 @@ exec_bind_message(StringInfo input_message) PopActiveSnapshot(); /* - * And we're ready to start portal execution. + * Start portal execution. If the portal contains a cached plan, it must + * be recreated if portal->plan_valid is false which tells that the cached + * plan was found to have been invalidated when initializing one of the + * plan trees contained in it. */ - PortalStart(portal, params, 0, InvalidSnapshot); + if (!PortalStart(portal, params, 0, InvalidSnapshot)) + { + PortalDrop(portal, false); + goto replan; + } /* * Apply the result format requests to the portal. diff --git a/src/backend/tcop/pquery.c b/src/backend/tcop/pquery.c index 5565f200c3..528f795d4f 100644 --- a/src/backend/tcop/pquery.c +++ b/src/backend/tcop/pquery.c @@ -19,6 +19,7 @@ #include "access/xact.h" #include "commands/prepare.h" +#include "executor/execdesc.h" #include "executor/tstoreReceiver.h" #include "miscadmin.h" #include "pg_trace.h" @@ -35,12 +36,6 @@ Portal ActivePortal = NULL; -static void ProcessQuery(PlannedStmt *plan, - const char *sourceText, - ParamListInfo params, - QueryEnvironment *queryEnv, - DestReceiver *dest, - QueryCompletion *qc); static void FillPortalStore(Portal portal, bool isTopLevel); static uint64 RunFromStore(Portal portal, ScanDirection direction, uint64 count, DestReceiver *dest); @@ -65,6 +60,7 @@ static void DoPortalRewind(Portal portal); */ QueryDesc * CreateQueryDesc(PlannedStmt *plannedstmt, + CachedPlan *cplan, const char *sourceText, Snapshot snapshot, Snapshot crosscheck_snapshot, @@ -77,6 +73,7 @@ CreateQueryDesc(PlannedStmt *plannedstmt, qd->operation = plannedstmt->commandType; /* operation */ qd->plannedstmt = plannedstmt; /* plan */ + qd->cplan = cplan; /* CachedPlan, if plan is from one */ qd->sourceText = sourceText; /* query text */ qd->snapshot = RegisterSnapshot(snapshot); /* snapshot */ /* RI check snapshot */ @@ -116,86 +113,6 @@ FreeQueryDesc(QueryDesc *qdesc) } -/* - * ProcessQuery - * Execute a single plannable query within a PORTAL_MULTI_QUERY, - * PORTAL_ONE_RETURNING, or PORTAL_ONE_MOD_WITH portal - * - * plan: the plan tree for the query - * sourceText: the source text of the query - * params: any parameters needed - * dest: where to send results - * qc: where to store the command completion status data. - * - * qc may be NULL if caller doesn't want a status string. - * - * Must be called in a memory context that will be reset or deleted on - * error; otherwise the executor's memory usage will be leaked. - */ -static void -ProcessQuery(PlannedStmt *plan, - const char *sourceText, - ParamListInfo params, - QueryEnvironment *queryEnv, - DestReceiver *dest, - QueryCompletion *qc) -{ - QueryDesc *queryDesc; - - /* - * Create the QueryDesc object - */ - queryDesc = CreateQueryDesc(plan, sourceText, - GetActiveSnapshot(), InvalidSnapshot, - dest, params, queryEnv, 0); - - /* - * Call ExecutorStart to prepare the plan for execution - */ - ExecutorStart(queryDesc, 0); - - /* - * Run the plan to completion. - */ - ExecutorRun(queryDesc, ForwardScanDirection, 0, true); - - /* - * Build command completion status data, if caller wants one. - */ - if (qc) - { - switch (queryDesc->operation) - { - case CMD_SELECT: - SetQueryCompletion(qc, CMDTAG_SELECT, queryDesc->estate->es_processed); - break; - case CMD_INSERT: - SetQueryCompletion(qc, CMDTAG_INSERT, queryDesc->estate->es_processed); - break; - case CMD_UPDATE: - SetQueryCompletion(qc, CMDTAG_UPDATE, queryDesc->estate->es_processed); - break; - case CMD_DELETE: - SetQueryCompletion(qc, CMDTAG_DELETE, queryDesc->estate->es_processed); - break; - case CMD_MERGE: - SetQueryCompletion(qc, CMDTAG_MERGE, queryDesc->estate->es_processed); - break; - default: - SetQueryCompletion(qc, CMDTAG_UNKNOWN, queryDesc->estate->es_processed); - break; - } - } - - /* - * Now, we close down all the scans and free allocated resources. - */ - ExecutorFinish(queryDesc); - ExecutorEnd(queryDesc); - - FreeQueryDesc(queryDesc); -} - /* * ChoosePortalStrategy * Select portal execution strategy given the intended statement list. @@ -426,19 +343,21 @@ FetchStatementTargetList(Node *stmt) * presently ignored for non-PORTAL_ONE_SELECT portals (it's only intended * to be used for cursors). * - * On return, portal is ready to accept PortalRun() calls, and the result - * tupdesc (if any) is known. + * True is returned if portal is ready to accept PortalRun() calls, and the + * result tupdesc (if any) is known. False if the plan tree is no longer + * valid, in which case, the caller must retry after generating a new + * CachedPlan. */ -void +bool PortalStart(Portal portal, ParamListInfo params, int eflags, Snapshot snapshot) { Portal saveActivePortal; ResourceOwner saveResourceOwner; - MemoryContext savePortalContext; MemoryContext oldContext; QueryDesc *queryDesc; - int myeflags; + int myeflags = 0; + bool plan_valid = true; Assert(PortalIsValid(portal)); Assert(portal->status == PORTAL_DEFINED); @@ -448,15 +367,13 @@ PortalStart(Portal portal, ParamListInfo params, */ saveActivePortal = ActivePortal; saveResourceOwner = CurrentResourceOwner; - savePortalContext = PortalContext; PG_TRY(); { ActivePortal = portal; if (portal->resowner) CurrentResourceOwner = portal->resowner; - PortalContext = portal->portalContext; - oldContext = MemoryContextSwitchTo(PortalContext); + oldContext = MemoryContextSwitchTo(portal->queryContext); /* Must remember portal param list, if any */ portal->portalParams = params; @@ -472,6 +389,8 @@ PortalStart(Portal portal, ParamListInfo params, switch (portal->strategy) { case PORTAL_ONE_SELECT: + case PORTAL_ONE_RETURNING: + case PORTAL_ONE_MOD_WITH: /* Must set snapshot before starting executor. */ if (snapshot) @@ -493,6 +412,7 @@ PortalStart(Portal portal, ParamListInfo params, * the destination to DestNone. */ queryDesc = CreateQueryDesc(linitial_node(PlannedStmt, portal->stmts), + portal->cplan, portal->sourceText, GetActiveSnapshot(), InvalidSnapshot, @@ -501,30 +421,51 @@ PortalStart(Portal portal, ParamListInfo params, portal->queryEnv, 0); + /* Remember for PortalRunMulti(). */ + if (portal->strategy == PORTAL_ONE_RETURNING || + portal->strategy == PORTAL_ONE_MOD_WITH) + portal->qdescs = list_make1(queryDesc); + /* * If it's a scrollable cursor, executor needs to support * REWIND and backwards scan, as well as whatever the caller * might've asked for. */ - if (portal->cursorOptions & CURSOR_OPT_SCROLL) + if (portal->strategy == PORTAL_ONE_SELECT && + (portal->cursorOptions & CURSOR_OPT_SCROLL)) myeflags = eflags | EXEC_FLAG_REWIND | EXEC_FLAG_BACKWARD; else myeflags = eflags; /* - * Call ExecutorStart to prepare the plan for execution + * Call ExecutorStart to prepare the plan for execution. A + * cached plan may get invalidated as we're doing that. */ - ExecutorStart(queryDesc, myeflags); + if (!ExecutorStart(queryDesc, myeflags)) + { + Assert(queryDesc->cplan); + PortalQueryFinish(queryDesc); + PopActiveSnapshot(); + plan_valid = false; + goto plan_init_failed; + } /* - * This tells PortalCleanup to shut down the executor + * This tells PortalCleanup to shut down the executor, though + * not needed for queries handled by PortalRunMulti(). */ - portal->queryDesc = queryDesc; + if (portal->strategy == PORTAL_ONE_SELECT) + portal->queryDesc = queryDesc; /* - * Remember tuple descriptor (computed by ExecutorStart) + * Remember tuple descriptor (computed by ExecutorStart), + * though make it independent of QueryDesc for queries handled + * by PortalRunMulti(). */ - portal->tupDesc = queryDesc->tupDesc; + if (portal->strategy != PORTAL_ONE_SELECT) + portal->tupDesc = CreateTupleDescCopy(queryDesc->tupDesc); + else + portal->tupDesc = queryDesc->tupDesc; /* * Reset cursor position data to "start of query" @@ -536,29 +477,6 @@ PortalStart(Portal portal, ParamListInfo params, PopActiveSnapshot(); break; - case PORTAL_ONE_RETURNING: - case PORTAL_ONE_MOD_WITH: - - /* - * We don't start the executor until we are told to run the - * portal. We do need to set up the result tupdesc. - */ - { - PlannedStmt *pstmt; - - pstmt = PortalGetPrimaryStmt(portal); - portal->tupDesc = - ExecCleanTypeFromTL(pstmt->planTree->targetlist); - } - - /* - * Reset cursor position data to "start of query" - */ - portal->atStart = true; - portal->atEnd = false; /* allow fetches */ - portal->portalPos = 0; - break; - case PORTAL_UTIL_SELECT: /* @@ -581,7 +499,81 @@ PortalStart(Portal portal, ParamListInfo params, break; case PORTAL_MULTI_QUERY: - /* Need do nothing now */ + { + ListCell *lc; + bool first = true; + + myeflags = eflags; + foreach(lc, portal->stmts) + { + PlannedStmt *plan = lfirst_node(PlannedStmt, lc); + bool is_utility = (plan->utilityStmt != NULL); + + /* + * Push the snapshot to be used by the executor. + */ + if (!is_utility) + { + /* + * Must copy the snapshot for all statements + * except thec first as we'll need to update its + * command ID. + */ + if (!first) + PushCopiedSnapshot(GetTransactionSnapshot()); + else + PushActiveSnapshot(GetTransactionSnapshot()); + } + + /* + * From the 2nd statement onwards, update the command + * ID and the snapshot to match. + */ + if (!first) + { + CommandCounterIncrement(); + UpdateActiveSnapshotCommandId(); + } + + first = false; + + /* + * Create the QueryDesc object. DestReceiver will + * be set in PortalRunMulti(). + */ + queryDesc = CreateQueryDesc(plan, portal->cplan, + portal->sourceText, + !is_utility ? + GetActiveSnapshot() : + InvalidSnapshot, + InvalidSnapshot, + NULL, + params, + portal->queryEnv, 0); + + /* Remember for PortalRunMulti() */ + portal->qdescs = lappend(portal->qdescs, queryDesc); + + if (is_utility) + continue; + + /* + * Call ExecutorStart to prepare the plan for + * execution. A cached plan may get invalidated as + * we're doing that. + */ + if (!ExecutorStart(queryDesc, myeflags)) + { + PopActiveSnapshot(); + Assert(queryDesc->cplan); + PortalQueryFinish(queryDesc); + plan_valid = false; + goto plan_init_failed; + } + PopActiveSnapshot(); + } + } + portal->tupDesc = NULL; break; } @@ -594,19 +586,20 @@ PortalStart(Portal portal, ParamListInfo params, /* Restore global vars and propagate error */ ActivePortal = saveActivePortal; CurrentResourceOwner = saveResourceOwner; - PortalContext = savePortalContext; PG_RE_THROW(); } PG_END_TRY(); + portal->status = PORTAL_READY; + +plan_init_failed: MemoryContextSwitchTo(oldContext); ActivePortal = saveActivePortal; CurrentResourceOwner = saveResourceOwner; - PortalContext = savePortalContext; - portal->status = PORTAL_READY; + return plan_valid; } /* @@ -1193,7 +1186,7 @@ PortalRunMulti(Portal portal, QueryCompletion *qc) { bool active_snapshot_set = false; - ListCell *stmtlist_item; + ListCell *qdesc_item; /* * If the destination is DestRemoteExecute, change to DestNone. The @@ -1214,9 +1207,10 @@ PortalRunMulti(Portal portal, * Loop to handle the individual queries generated from a single parsetree * by analysis and rewrite. */ - foreach(stmtlist_item, portal->stmts) + foreach(qdesc_item, portal->qdescs) { - PlannedStmt *pstmt = lfirst_node(PlannedStmt, stmtlist_item); + QueryDesc *qdesc = (QueryDesc *) lfirst(qdesc_item); + PlannedStmt *pstmt = qdesc->plannedstmt; /* * If we got a cancel signal in prior command, quit @@ -1233,33 +1227,26 @@ PortalRunMulti(Portal portal, if (log_executor_stats) ResetUsage(); - /* - * Must always have a snapshot for plannable queries. First time - * through, take a new snapshot; for subsequent queries in the - * same portal, just update the snapshot's copy of the command - * counter. - */ + /* Push the snapshot for plannable queries. */ if (!active_snapshot_set) { - Snapshot snapshot = GetTransactionSnapshot(); + Snapshot snapshot = qdesc->snapshot; - /* If told to, register the snapshot and save in portal */ + /* + * If told to, register the snapshot and save in portal + * + * Note that the command ID of qdesc->snapshot for 2nd query + * onwards would have been updated in PortalStart() to account + * for CCI() done between queries, but it's OK that here we + * don't likewise update holdSnapshot's command ID. + */ if (setHoldSnapshot) { snapshot = RegisterSnapshot(snapshot); portal->holdSnapshot = snapshot; } - /* - * We can't have the holdSnapshot also be the active one, - * because UpdateActiveSnapshotCommandId would complain. So - * force an extra snapshot copy. Plain PushActiveSnapshot - * would have copied the transaction snapshot anyway, so this - * only adds a copy step when setHoldSnapshot is true. (It's - * okay for the command ID of the active snapshot to diverge - * from what holdSnapshot has.) - */ - PushCopiedSnapshot(snapshot); + PushActiveSnapshot(snapshot); /* * As for PORTAL_ONE_SELECT portals, it does not seem @@ -1268,26 +1255,39 @@ PortalRunMulti(Portal portal, active_snapshot_set = true; } - else - UpdateActiveSnapshotCommandId(); + /* + * Run the plan to completion. + */ + qdesc->dest = dest; + ExecutorRun(qdesc, ForwardScanDirection, 0, true); + + /* + * Build command completion status data if needed. + */ if (pstmt->canSetTag) { - /* statement can set tag string */ - ProcessQuery(pstmt, - portal->sourceText, - portal->portalParams, - portal->queryEnv, - dest, qc); - } - else - { - /* stmt added by rewrite cannot set tag */ - ProcessQuery(pstmt, - portal->sourceText, - portal->portalParams, - portal->queryEnv, - altdest, NULL); + switch (qdesc->operation) + { + case CMD_SELECT: + SetQueryCompletion(qc, CMDTAG_SELECT, qdesc->estate->es_processed); + break; + case CMD_INSERT: + SetQueryCompletion(qc, CMDTAG_INSERT, qdesc->estate->es_processed); + break; + case CMD_UPDATE: + SetQueryCompletion(qc, CMDTAG_UPDATE, qdesc->estate->es_processed); + break; + case CMD_DELETE: + SetQueryCompletion(qc, CMDTAG_DELETE, qdesc->estate->es_processed); + break; + case CMD_MERGE: + SetQueryCompletion(qc, CMDTAG_MERGE, qdesc->estate->es_processed); + break; + default: + SetQueryCompletion(qc, CMDTAG_UNKNOWN, qdesc->estate->es_processed); + break; + } } if (log_executor_stats) @@ -1342,12 +1342,12 @@ PortalRunMulti(Portal portal, if (portal->stmts == NIL) break; - /* - * Increment command counter between queries, but not after the last - * one. - */ - if (lnext(portal->stmts, stmtlist_item) != NULL) - CommandCounterIncrement(); + if (qdesc->estate) + { + ExecutorFinish(qdesc); + ExecutorEnd(qdesc); + } + FreeQueryDesc(qdesc); } /* Pop the snapshot if we pushed one. */ diff --git a/src/backend/utils/cache/lsyscache.c b/src/backend/utils/cache/lsyscache.c index fc6d267e44..2725d02312 100644 --- a/src/backend/utils/cache/lsyscache.c +++ b/src/backend/utils/cache/lsyscache.c @@ -2095,6 +2095,27 @@ get_rel_persistence(Oid relid) return result; } +/* + * get_rel_relisshared + * + * Returns if the given relation is shared or not + */ +bool +get_rel_relisshared(Oid relid) +{ + HeapTuple tp; + Form_pg_class reltup; + bool result; + + tp = SearchSysCache1(RELOID, ObjectIdGetDatum(relid)); + if (!HeapTupleIsValid(tp)) + elog(ERROR, "cache lookup failed for relation %u", relid); + reltup = (Form_pg_class) GETSTRUCT(tp); + result = reltup->relisshared; + ReleaseSysCache(tp); + + return result; +} /* ---------- TRANSFORM CACHE ---------- */ diff --git a/src/backend/utils/cache/plancache.c b/src/backend/utils/cache/plancache.c index d67cd9a405..84a354a701 100644 --- a/src/backend/utils/cache/plancache.c +++ b/src/backend/utils/cache/plancache.c @@ -102,13 +102,13 @@ static void ReleaseGenericPlan(CachedPlanSource *plansource); static List *RevalidateCachedQuery(CachedPlanSource *plansource, QueryEnvironment *queryEnv); static bool CheckCachedPlan(CachedPlanSource *plansource); +static bool GenericPlanIsValid(CachedPlan *cplan); static CachedPlan *BuildCachedPlan(CachedPlanSource *plansource, List *qlist, ParamListInfo boundParams, QueryEnvironment *queryEnv); static bool choose_custom_plan(CachedPlanSource *plansource, ParamListInfo boundParams); static double cached_plan_cost(CachedPlan *plan, bool include_planner); static Query *QueryListGetPrimaryStmt(List *stmts); -static void AcquireExecutorLocks(List *stmt_list, bool acquire); static void AcquirePlannerLocks(List *stmt_list, bool acquire); static void ScanQueryForLocks(Query *parsetree, bool acquire); static bool ScanQueryWalker(Node *node, bool *acquire); @@ -790,8 +790,14 @@ RevalidateCachedQuery(CachedPlanSource *plansource, * Caller must have already called RevalidateCachedQuery to verify that the * querytree is up to date. * - * On a "true" return, we have acquired the locks needed to run the plan. - * (We must do this for the "true" result to be race-condition-free.) + * Note though that if the plan contains any child relations that would have + * been added by the planner, which would not have been locked yet (because + * AcquirePlannerLocks() only locks relations that would be present in the + * range table before entering the planner), the plan could go stale before + * it reaches execution if any of those child relations get modified + * concurrently. The executor must check that the plan (CachedPlan) is still + * valid after taking a lock on each of the child tables, and if it is not, + * ask the caller to recreate the plan. */ static bool CheckCachedPlan(CachedPlanSource *plansource) @@ -805,60 +811,56 @@ CheckCachedPlan(CachedPlanSource *plansource) if (!plan) return false; - Assert(plan->magic == CACHEDPLAN_MAGIC); - /* Generic plans are never one-shot */ - Assert(!plan->is_oneshot); + if (GenericPlanIsValid(plan)) + return true; /* - * If plan isn't valid for current role, we can't use it. + * Plan has been invalidated, so unlink it from the parent and release it. */ - if (plan->is_valid && plan->dependsOnRole && - plan->planRoleId != GetUserId()) - plan->is_valid = false; + ReleaseGenericPlan(plansource); - /* - * If it appears valid, acquire locks and recheck; this is much the same - * logic as in RevalidateCachedQuery, but for a plan. - */ - if (plan->is_valid) + return false; +} + +/* + * GenericPlanIsValid + * Is a generic plan still valid? + * + * It may have gone stale due to concurrent schema modifications of relations + * mentioned in the plan or a couple of other things mentioned below. + */ +static bool +GenericPlanIsValid(CachedPlan *cplan) +{ + Assert(cplan != NULL); + Assert(cplan->magic == CACHEDPLAN_MAGIC); + /* Generic plans are never one-shot */ + Assert(!cplan->is_oneshot); + + if (cplan->is_valid) { /* * Plan must have positive refcount because it is referenced by * plansource; so no need to fear it disappears under us here. */ - Assert(plan->refcount > 0); - - AcquireExecutorLocks(plan->stmt_list, true); + Assert(cplan->refcount > 0); /* - * If plan was transient, check to see if TransactionXmin has - * advanced, and if so invalidate it. + * If plan isn't valid for current role, we can't use it. */ - if (plan->is_valid && - TransactionIdIsValid(plan->saved_xmin) && - !TransactionIdEquals(plan->saved_xmin, TransactionXmin)) - plan->is_valid = false; + if (cplan->dependsOnRole && cplan->planRoleId != GetUserId()) + cplan->is_valid = false; /* - * By now, if any invalidation has happened, the inval callback - * functions will have marked the plan invalid. + * If plan was transient, check to see if TransactionXmin has + * advanced, and if so invalidate it. */ - if (plan->is_valid) - { - /* Successfully revalidated and locked the query. */ - return true; - } - - /* Oops, the race case happened. Release useless locks. */ - AcquireExecutorLocks(plan->stmt_list, false); + if (TransactionIdIsValid(cplan->saved_xmin) && + !TransactionIdEquals(cplan->saved_xmin, TransactionXmin)) + cplan->is_valid = false; } - /* - * Plan has been invalidated, so unlink it from the parent and release it. - */ - ReleaseGenericPlan(plansource); - - return false; + return cplan->is_valid; } /* @@ -1128,8 +1130,15 @@ cached_plan_cost(CachedPlan *plan, bool include_planner) * plan or a custom plan for the given parameters: the caller does not know * which it will get. * - * On return, the plan is valid and we have sufficient locks to begin - * execution. + * On return, the plan is valid unless it contains inheritance/partition child + * tables, that is, only the locks on the tables mentioned in the query have + * been taken. If any of those tables have inheritance/partition tables, the + * executor must also lock them before executing the plan and if the plan gets + * invalidated as a result of taking those locks, must ask the caller to get + * a new plan by calling here again. Locking of the child tables must be + * deferred to the executor like this, because not all child tables may need + * to be locked; some may get pruned during the executor plan initialization + * phase (InitPlan()). * * On return, the refcount of the plan has been incremented; a later * ReleaseCachedPlan() call is expected. If "owner" is not NULL then @@ -1362,8 +1371,8 @@ CachedPlanAllowsSimpleValidityCheck(CachedPlanSource *plansource, } /* - * Reject if AcquireExecutorLocks would have anything to do. This is - * probably unnecessary given the previous check, but let's be safe. + * Reject if the executor would need to take additional locks, that is, in + * addition to those taken by AcquirePlannerLocks() on a given query. */ foreach(lc, plan->stmt_list) { @@ -1739,58 +1748,6 @@ QueryListGetPrimaryStmt(List *stmts) return NULL; } -/* - * AcquireExecutorLocks: acquire locks needed for execution of a cached plan; - * or release them if acquire is false. - */ -static void -AcquireExecutorLocks(List *stmt_list, bool acquire) -{ - ListCell *lc1; - - foreach(lc1, stmt_list) - { - PlannedStmt *plannedstmt = lfirst_node(PlannedStmt, lc1); - ListCell *lc2; - - if (plannedstmt->commandType == CMD_UTILITY) - { - /* - * Ignore utility statements, except those (such as EXPLAIN) that - * contain a parsed-but-not-planned query. Note: it's okay to use - * ScanQueryForLocks, even though the query hasn't been through - * rule rewriting, because rewriting doesn't change the query - * representation. - */ - Query *query = UtilityContainsQuery(plannedstmt->utilityStmt); - - if (query) - ScanQueryForLocks(query, acquire); - continue; - } - - foreach(lc2, plannedstmt->rtable) - { - RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc2); - - if (!(rte->rtekind == RTE_RELATION || - (rte->rtekind == RTE_SUBQUERY && OidIsValid(rte->relid)))) - continue; - - /* - * Acquire the appropriate type of lock on each relation OID. Note - * that we don't actually try to open the rel, and hence will not - * fail if it's been dropped entirely --- we'll just transiently - * acquire a non-conflicting lock. - */ - if (acquire) - LockRelationOid(rte->relid, rte->rellockmode); - else - UnlockRelationOid(rte->relid, rte->rellockmode); - } - } -} - /* * AcquirePlannerLocks: acquire locks needed for planning of a querytree list; * or release them if acquire is false. diff --git a/src/backend/utils/mmgr/portalmem.c b/src/backend/utils/mmgr/portalmem.c index 06dfa85f04..0cad450dcd 100644 --- a/src/backend/utils/mmgr/portalmem.c +++ b/src/backend/utils/mmgr/portalmem.c @@ -201,6 +201,13 @@ CreatePortal(const char *name, bool allowDup, bool dupSilent) portal->portalContext = AllocSetContextCreate(TopPortalContext, "PortalContext", ALLOCSET_SMALL_SIZES); + /* + * initialize portal's query context to store QueryDescs created during + * PortalStart() and then used in PortalRun(). + */ + portal->queryContext = AllocSetContextCreate(TopPortalContext, + "PortalQueryContext", + ALLOCSET_SMALL_SIZES); /* create a resource owner for the portal */ portal->resowner = ResourceOwnerCreate(CurTransactionResourceOwner, @@ -224,6 +231,7 @@ CreatePortal(const char *name, bool allowDup, bool dupSilent) /* for named portals reuse portal->name copy */ MemoryContextSetIdentifier(portal->portalContext, portal->name[0] ? portal->name : ""); + MemoryContextSetIdentifier(portal->queryContext, portal->name[0] ? portal->name : ""); return portal; } @@ -594,6 +602,7 @@ PortalDrop(Portal portal, bool isTopCommit) /* release subsidiary storage */ MemoryContextDelete(portal->portalContext); + MemoryContextDelete(portal->queryContext); /* release portal struct (it's in TopPortalContext) */ pfree(portal); diff --git a/src/include/commands/explain.h b/src/include/commands/explain.h index 3d3e632a0c..392abb5150 100644 --- a/src/include/commands/explain.h +++ b/src/include/commands/explain.h @@ -88,7 +88,11 @@ extern void ExplainOneUtility(Node *utilityStmt, IntoClause *into, ExplainState *es, const char *queryString, ParamListInfo params, QueryEnvironment *queryEnv); -extern void ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, +extern QueryDesc *ExplainQueryDesc(PlannedStmt *stmt, struct CachedPlan *cplan, + const char *queryString, IntoClause *into, ExplainState *es, + ParamListInfo params, QueryEnvironment *queryEnv); +extern void ExplainOnePlan(QueryDesc *queryDesc, + IntoClause *into, ExplainState *es, const char *queryString, ParamListInfo params, QueryEnvironment *queryEnv, const instr_time *planduration, @@ -104,6 +108,7 @@ extern void ExplainQueryParameters(ExplainState *es, ParamListInfo params, int m extern void ExplainBeginOutput(ExplainState *es); extern void ExplainEndOutput(ExplainState *es); +extern void ExplainResetOutput(ExplainState *es); extern void ExplainSeparatePlans(ExplainState *es); extern void ExplainPropertyList(const char *qlabel, List *data, diff --git a/src/include/executor/execdesc.h b/src/include/executor/execdesc.h index af2bf36dfb..4b7368a0dc 100644 --- a/src/include/executor/execdesc.h +++ b/src/include/executor/execdesc.h @@ -32,9 +32,12 @@ */ typedef struct QueryDesc { + NodeTag type; + /* These fields are provided by CreateQueryDesc */ CmdType operation; /* CMD_SELECT, CMD_UPDATE, etc. */ PlannedStmt *plannedstmt; /* planner's output (could be utility, too) */ + struct CachedPlan *cplan; /* CachedPlan, if plannedstmt is from one */ const char *sourceText; /* source text of the query */ Snapshot snapshot; /* snapshot to use for query */ Snapshot crosscheck_snapshot; /* crosscheck for RI update/delete */ @@ -57,6 +60,7 @@ typedef struct QueryDesc /* in pquery.c */ extern QueryDesc *CreateQueryDesc(PlannedStmt *plannedstmt, + struct CachedPlan *cplan, const char *sourceText, Snapshot snapshot, Snapshot crosscheck_snapshot, diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h index c677e490d7..edf2f13d04 100644 --- a/src/include/executor/executor.h +++ b/src/include/executor/executor.h @@ -19,6 +19,7 @@ #include "nodes/lockoptions.h" #include "nodes/parsenodes.h" #include "utils/memutils.h" +#include "utils/plancache.h" /* @@ -72,7 +73,7 @@ /* Hook for plugins to get control in ExecutorStart() */ -typedef void (*ExecutorStart_hook_type) (QueryDesc *queryDesc, int eflags); +typedef bool (*ExecutorStart_hook_type) (QueryDesc *queryDesc, int eflags); extern PGDLLIMPORT ExecutorStart_hook_type ExecutorStart_hook; /* Hook for plugins to get control in ExecutorRun() */ @@ -197,8 +198,8 @@ ExecGetJunkAttribute(TupleTableSlot *slot, AttrNumber attno, bool *isNull) /* * prototypes from functions in execMain.c */ -extern void ExecutorStart(QueryDesc *queryDesc, int eflags); -extern void standard_ExecutorStart(QueryDesc *queryDesc, int eflags); +extern bool ExecutorStart(QueryDesc *queryDesc, int eflags); +extern bool standard_ExecutorStart(QueryDesc *queryDesc, int eflags); extern void ExecutorRun(QueryDesc *queryDesc, ScanDirection direction, uint64 count, bool execute_once); extern void standard_ExecutorRun(QueryDesc *queryDesc, @@ -256,6 +257,17 @@ extern void ExecEndNode(PlanState *node); extern void ExecShutdownNode(PlanState *node); extern void ExecSetTupleBound(int64 tuples_needed, PlanState *child_node); +/* + * Is the cached plan, if any, still valid at this point? That is, not + * invalidated by the incoming invalidation messages that have been processed + * recently. + */ +static inline bool +ExecPlanStillValid(EState *estate) +{ + return estate->es_cachedplan == NULL ? true : + CachedPlanStillValid(estate->es_cachedplan); +} /* ---------------------------------------------------------------- * ExecProcNode @@ -590,6 +602,7 @@ exec_rt_fetch(Index rti, EState *estate) } extern Relation ExecGetRangeTableRelation(EState *estate, Index rti); +extern void ExecLockAppendNonLeafRelations(EState *estate, List *allpartrelids); extern void ExecInitResultRelation(EState *estate, ResultRelInfo *resultRelInfo, Index rti); diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h index 233fb6b4f9..20c1bacae1 100644 --- a/src/include/nodes/execnodes.h +++ b/src/include/nodes/execnodes.h @@ -623,6 +623,8 @@ typedef struct EState * ExecRowMarks, or NULL if none */ List *es_rteperminfos; /* List of RTEPermissionInfo */ PlannedStmt *es_plannedstmt; /* link to top of plan tree */ + struct CachedPlan *es_cachedplan; /* CachedPlan if plannedstmt is from + * one */ const char *es_sourceText; /* Source text from QueryDesc */ JunkFilter *es_junkFilter; /* top-level junk filter, if any */ diff --git a/src/include/storage/lmgr.h b/src/include/storage/lmgr.h index 4ee91e3cf9..598bf2688a 100644 --- a/src/include/storage/lmgr.h +++ b/src/include/storage/lmgr.h @@ -48,6 +48,7 @@ extern bool ConditionalLockRelation(Relation relation, LOCKMODE lockmode); extern void UnlockRelation(Relation relation, LOCKMODE lockmode); extern bool CheckRelationLockedByMe(Relation relation, LOCKMODE lockmode, bool orstronger); +extern bool CheckRelLockedByMe(Oid relid, LOCKMODE lockmode, bool orstronger); extern bool LockHasWaitersRelation(Relation relation, LOCKMODE lockmode); extern void LockRelationIdForSession(LockRelId *relid, LOCKMODE lockmode); diff --git a/src/include/tcop/pquery.h b/src/include/tcop/pquery.h index a5e65b98aa..577b81a9ee 100644 --- a/src/include/tcop/pquery.h +++ b/src/include/tcop/pquery.h @@ -29,7 +29,7 @@ extern List *FetchPortalTargetList(Portal portal); extern List *FetchStatementTargetList(Node *stmt); -extern void PortalStart(Portal portal, ParamListInfo params, +extern bool PortalStart(Portal portal, ParamListInfo params, int eflags, Snapshot snapshot); extern void PortalSetResultFormat(Portal portal, int nFormats, diff --git a/src/include/utils/lsyscache.h b/src/include/utils/lsyscache.h index f5fdbfe116..a024e5dcd0 100644 --- a/src/include/utils/lsyscache.h +++ b/src/include/utils/lsyscache.h @@ -140,6 +140,7 @@ extern char get_rel_relkind(Oid relid); extern bool get_rel_relispartition(Oid relid); extern Oid get_rel_tablespace(Oid relid); extern char get_rel_persistence(Oid relid); +extern bool get_rel_relisshared(Oid relid); extern Oid get_transform_fromsql(Oid typid, Oid langid, List *trftypes); extern Oid get_transform_tosql(Oid typid, Oid langid, List *trftypes); extern bool get_typisdefined(Oid typid); diff --git a/src/include/utils/plancache.h b/src/include/utils/plancache.h index 916e59d9fe..c83a67fea3 100644 --- a/src/include/utils/plancache.h +++ b/src/include/utils/plancache.h @@ -221,6 +221,20 @@ extern CachedPlan *GetCachedPlan(CachedPlanSource *plansource, ParamListInfo boundParams, ResourceOwner owner, QueryEnvironment *queryEnv); + +/* + * CachedPlanStillValid + * Returns if a cached generic plan is still valid + * + * Called by the executor on every relation lock taken when initializing the + * plan tree in the CachedPlan. + */ +static inline bool +CachedPlanStillValid(CachedPlan *cplan) +{ + return cplan->is_valid; +} + extern void ReleaseCachedPlan(CachedPlan *plan, ResourceOwner owner); extern bool CachedPlanAllowsSimpleValidityCheck(CachedPlanSource *plansource, diff --git a/src/include/utils/portal.h b/src/include/utils/portal.h index aa08b1e0fc..e7e2fb0c3f 100644 --- a/src/include/utils/portal.h +++ b/src/include/utils/portal.h @@ -138,6 +138,8 @@ typedef struct PortalData QueryCompletion qc; /* command completion data for executed query */ List *stmts; /* list of PlannedStmts */ CachedPlan *cplan; /* CachedPlan, if stmts are from one */ + List *qdescs; /* list of QueryDescs */ + MemoryContext queryContext; /* memory for QueryDescs and children */ ParamListInfo portalParams; /* params to pass to query */ QueryEnvironment *queryEnv; /* environment for query */ @@ -242,6 +244,7 @@ extern void PortalDefineQuery(Portal portal, CommandTag commandTag, List *stmts, CachedPlan *cplan); +extern void PortalQueryFinish(QueryDesc *queryDesc); extern PlannedStmt *PortalGetPrimaryStmt(Portal portal); extern void PortalCreateHoldStore(Portal portal); extern void PortalHashTableDeleteAll(void); diff --git a/src/test/modules/delay_execution/Makefile b/src/test/modules/delay_execution/Makefile index 70f24e846d..2fca84d027 100644 --- a/src/test/modules/delay_execution/Makefile +++ b/src/test/modules/delay_execution/Makefile @@ -8,7 +8,8 @@ OBJS = \ delay_execution.o ISOLATION = partition-addition \ - partition-removal-1 + partition-removal-1 \ + cached-plan-replan ifdef USE_PGXS PG_CONFIG = pg_config diff --git a/src/test/modules/delay_execution/delay_execution.c b/src/test/modules/delay_execution/delay_execution.c index 7cd76eb34b..ce189156ad 100644 --- a/src/test/modules/delay_execution/delay_execution.c +++ b/src/test/modules/delay_execution/delay_execution.c @@ -1,14 +1,18 @@ /*------------------------------------------------------------------------- * * delay_execution.c - * Test module to allow delay between parsing and execution of a query. + * Test module to introduce delay at various points during execution of a + * query to test that execution proceeds safely in light of concurrent + * changes. * * The delay is implemented by taking and immediately releasing a specified * advisory lock. If another process has previously taken that lock, the * current process will be blocked until the lock is released; otherwise, * there's no effect. This allows an isolationtester script to reliably - * test behaviors where some specified action happens in another backend - * between parsing and execution of any desired query. + * test behaviors where some specified action happens in another backend in + * a couple of cases: 1) between parsing and execution of any desired query + * when using the planner_hook, 2) between RevalidateCachedQuery() and + * ExecutorStart() when using the ExecutorStart_hook. * * Copyright (c) 2020-2023, PostgreSQL Global Development Group * @@ -22,6 +26,7 @@ #include +#include "executor/executor.h" #include "optimizer/planner.h" #include "utils/builtins.h" #include "utils/guc.h" @@ -32,9 +37,11 @@ PG_MODULE_MAGIC; /* GUC: advisory lock ID to use. Zero disables the feature. */ static int post_planning_lock_id = 0; +static int executor_start_lock_id = 0; -/* Save previous planner hook user to be a good citizen */ +/* Save previous hook users to be a good citizen */ static planner_hook_type prev_planner_hook = NULL; +static ExecutorStart_hook_type prev_ExecutorStart_hook = NULL; /* planner_hook function to provide the desired delay */ @@ -70,11 +77,45 @@ delay_execution_planner(Query *parse, const char *query_string, return result; } +/* ExecutorStart_hook function to provide the desired delay */ +static bool +delay_execution_ExecutorStart(QueryDesc *queryDesc, int eflags) +{ + bool plan_valid; + + /* If enabled, delay by taking and releasing the specified lock */ + if (executor_start_lock_id != 0) + { + DirectFunctionCall1(pg_advisory_lock_int8, + Int64GetDatum((int64) executor_start_lock_id)); + DirectFunctionCall1(pg_advisory_unlock_int8, + Int64GetDatum((int64) executor_start_lock_id)); + + /* + * Ensure that we notice any pending invalidations, since the advisory + * lock functions don't do this. + */ + AcceptInvalidationMessages(); + } + + /* Now start the executor, possibly via a previous hook user */ + if (prev_ExecutorStart_hook) + plan_valid = prev_ExecutorStart_hook(queryDesc, eflags); + else + plan_valid = standard_ExecutorStart(queryDesc, eflags); + + if (executor_start_lock_id != 0) + elog(NOTICE, "Finished ExecutorStart(): CachedPlan is %s", + plan_valid ? "valid" : "not valid"); + + return plan_valid; +} + /* Module load function */ void _PG_init(void) { - /* Set up the GUC to control which lock is used */ + /* Set up GUCs to control which lock is used */ DefineCustomIntVariable("delay_execution.post_planning_lock_id", "Sets the advisory lock ID to be locked/unlocked after planning.", "Zero disables the delay.", @@ -86,10 +127,22 @@ _PG_init(void) NULL, NULL, NULL); - + DefineCustomIntVariable("delay_execution.executor_start_lock_id", + "Sets the advisory lock ID to be locked/unlocked before starting execution.", + "Zero disables the delay.", + &executor_start_lock_id, + 0, + 0, INT_MAX, + PGC_USERSET, + 0, + NULL, + NULL, + NULL); MarkGUCPrefixReserved("delay_execution"); - /* Install our hook */ + /* Install our hooks. */ prev_planner_hook = planner_hook; planner_hook = delay_execution_planner; + prev_ExecutorStart_hook = ExecutorStart_hook; + ExecutorStart_hook = delay_execution_ExecutorStart; } diff --git a/src/test/modules/delay_execution/expected/cached-plan-replan.out b/src/test/modules/delay_execution/expected/cached-plan-replan.out new file mode 100644 index 0000000000..0ac6a17c2b --- /dev/null +++ b/src/test/modules/delay_execution/expected/cached-plan-replan.out @@ -0,0 +1,156 @@ +Parsed test spec with 2 sessions + +starting permutation: s1prep s2lock s1exec s2dropi s2unlock +step s1prep: SET plan_cache_mode = force_generic_plan; + PREPARE q AS SELECT * FROM foov WHERE a = $1; + EXPLAIN (COSTS OFF) EXECUTE q (1); +QUERY PLAN +-------------------------------------------- +Append + Subplans Removed: 1 + -> Bitmap Heap Scan on foo11 foo_1 + Recheck Cond: (a = $1) + -> Bitmap Index Scan on foo11_a_idx + Index Cond: (a = $1) +(6 rows) + +step s2lock: SELECT pg_advisory_lock(12345); +pg_advisory_lock +---------------- + +(1 row) + +step s1exec: LOAD 'delay_execution'; + SET delay_execution.executor_start_lock_id = 12345; + EXPLAIN (COSTS OFF) EXECUTE q (1); +step s2dropi: DROP INDEX foo11_a; +step s2unlock: SELECT pg_advisory_unlock(12345); +pg_advisory_unlock +------------------ +t +(1 row) + +step s1exec: <... completed> +s1: NOTICE: Finished ExecutorStart(): CachedPlan is not valid +s1: NOTICE: Finished ExecutorStart(): CachedPlan is valid +QUERY PLAN +----------------------------- +Append + Subplans Removed: 1 + -> Seq Scan on foo11 foo_1 + Filter: (a = $1) +(4 rows) + + +starting permutation: s1prep2 s2lock s1exec2 s2dropi s2unlock +step s1prep2: SET plan_cache_mode = force_generic_plan; + PREPARE q2 AS SELECT * FROM foov WHERE a = 1; + EXPLAIN (COSTS OFF) EXECUTE q2; +s1: NOTICE: Finished ExecutorStart(): CachedPlan is valid +QUERY PLAN +-------------------------------------- +Bitmap Heap Scan on foo11 foo + Recheck Cond: (a = 1) + -> Bitmap Index Scan on foo11_a_idx + Index Cond: (a = 1) +(4 rows) + +step s2lock: SELECT pg_advisory_lock(12345); +pg_advisory_lock +---------------- + +(1 row) + +step s1exec2: LOAD 'delay_execution'; + SET delay_execution.executor_start_lock_id = 12345; + EXPLAIN (COSTS OFF) EXECUTE q2; +step s2dropi: DROP INDEX foo11_a; +step s2unlock: SELECT pg_advisory_unlock(12345); +pg_advisory_unlock +------------------ +t +(1 row) + +step s1exec2: <... completed> +s1: NOTICE: Finished ExecutorStart(): CachedPlan is not valid +s1: NOTICE: Finished ExecutorStart(): CachedPlan is valid +QUERY PLAN +--------------------- +Seq Scan on foo11 foo + Filter: (a = 1) +(2 rows) + + +starting permutation: s1prep3 s2lock s1exec3 s2dropi s2unlock +step s1prep3: SET plan_cache_mode = force_generic_plan; + SET enable_partitionwise_aggregate = on; + SET enable_partitionwise_join = on; + PREPARE q3 AS SELECT t1.a, count(t2.b) FROM foo t1, foo t2 WHERE t1.a = t2.a GROUP BY 1; + EXPLAIN (COSTS OFF) EXECUTE q3; +s1: NOTICE: Finished ExecutorStart(): CachedPlan is valid +QUERY PLAN +---------------------------------------------------------------- +Append + -> GroupAggregate + Group Key: t1.a + -> Merge Join + Merge Cond: (t1.a = t2.a) + -> Index Only Scan using foo11_a_idx on foo11 t1 + -> Materialize + -> Index Scan using foo11_a_idx on foo11 t2 + -> GroupAggregate + Group Key: t1_1.a + -> Merge Join + Merge Cond: (t1_1.a = t2_1.a) + -> Sort + Sort Key: t1_1.a + -> Seq Scan on foo2 t1_1 + -> Sort + Sort Key: t2_1.a + -> Seq Scan on foo2 t2_1 +(18 rows) + +step s2lock: SELECT pg_advisory_lock(12345); +pg_advisory_lock +---------------- + +(1 row) + +step s1exec3: LOAD 'delay_execution'; + SET delay_execution.executor_start_lock_id = 12345; + EXPLAIN (COSTS OFF) EXECUTE q3; +step s2dropi: DROP INDEX foo11_a; +step s2unlock: SELECT pg_advisory_unlock(12345); +pg_advisory_unlock +------------------ +t +(1 row) + +step s1exec3: <... completed> +s1: NOTICE: Finished ExecutorStart(): CachedPlan is not valid +s1: NOTICE: Finished ExecutorStart(): CachedPlan is valid +QUERY PLAN +--------------------------------------------- +Append + -> GroupAggregate + Group Key: t1.a + -> Merge Join + Merge Cond: (t1.a = t2.a) + -> Sort + Sort Key: t1.a + -> Seq Scan on foo11 t1 + -> Sort + Sort Key: t2.a + -> Seq Scan on foo11 t2 + -> GroupAggregate + Group Key: t1_1.a + -> Merge Join + Merge Cond: (t1_1.a = t2_1.a) + -> Sort + Sort Key: t1_1.a + -> Seq Scan on foo2 t1_1 + -> Sort + Sort Key: t2_1.a + -> Seq Scan on foo2 t2_1 +(21 rows) + diff --git a/src/test/modules/delay_execution/specs/cached-plan-replan.spec b/src/test/modules/delay_execution/specs/cached-plan-replan.spec new file mode 100644 index 0000000000..3c92cbd5c6 --- /dev/null +++ b/src/test/modules/delay_execution/specs/cached-plan-replan.spec @@ -0,0 +1,61 @@ +# Test to check that invalidation of cached generic plans during ExecutorStart +# correctly triggers replanning and re-execution. + +setup +{ + CREATE TABLE foo (a int, b text) PARTITION BY LIST(a); + CREATE TABLE foo1 PARTITION OF foo FOR VALUES IN (1) PARTITION BY LIST (a); + CREATE TABLE foo11 PARTITION OF foo1 FOR VALUES IN (1); + CREATE INDEX foo11_a ON foo1 (a); + CREATE TABLE foo2 PARTITION OF foo FOR VALUES IN (2); + CREATE VIEW foov AS SELECT * FROM foo; +} + +teardown +{ + DROP VIEW foov; + DROP TABLE foo; +} + +session "s1" +# Append with run-time pruning +step "s1prep" { SET plan_cache_mode = force_generic_plan; + PREPARE q AS SELECT * FROM foov WHERE a = $1; + EXPLAIN (COSTS OFF) EXECUTE q (1); } + +# no Append case (only one partition selected by the planner) +step "s1prep2" { SET plan_cache_mode = force_generic_plan; + PREPARE q2 AS SELECT * FROM foov WHERE a = 1; + EXPLAIN (COSTS OFF) EXECUTE q2; } + +# Append with partition-wise join aggregate and join plans as child subplans +step "s1prep3" { SET plan_cache_mode = force_generic_plan; + SET enable_partitionwise_aggregate = on; + SET enable_partitionwise_join = on; + PREPARE q3 AS SELECT t1.a, count(t2.b) FROM foo t1, foo t2 WHERE t1.a = t2.a GROUP BY 1; + EXPLAIN (COSTS OFF) EXECUTE q3; } + +# Executes a generic plan +step "s1exec" { LOAD 'delay_execution'; + SET delay_execution.executor_start_lock_id = 12345; + EXPLAIN (COSTS OFF) EXECUTE q (1); } +step "s1exec2" { LOAD 'delay_execution'; + SET delay_execution.executor_start_lock_id = 12345; + EXPLAIN (COSTS OFF) EXECUTE q2; } +step "s1exec3" { LOAD 'delay_execution'; + SET delay_execution.executor_start_lock_id = 12345; + EXPLAIN (COSTS OFF) EXECUTE q3; } + +session "s2" +step "s2lock" { SELECT pg_advisory_lock(12345); } +step "s2unlock" { SELECT pg_advisory_unlock(12345); } +step "s2dropi" { DROP INDEX foo11_a; } + +# While "s1exec", etc. wait to acquire the advisory lock, "s2drop" is able to +# drop the index being used in the cached plan. When "s1exec" is then +# unblocked and initializes the cached plan for execution, it detects the +# concurrent index drop and causes the cached plan to be discarded and +# recreated without the index. +permutation "s1prep" "s2lock" "s1exec" "s2dropi" "s2unlock" +permutation "s1prep2" "s2lock" "s1exec2" "s2dropi" "s2unlock" +permutation "s1prep3" "s2lock" "s1exec3" "s2dropi" "s2unlock" -- 2.35.3