From 0c8671803853427dc43c1e2f58240a6a925fac4b Mon Sep 17 00:00:00 2001 From: Amit Langote Date: Wed, 4 Dec 2024 16:16:29 +0900 Subject: [PATCH v58 1/4] Move PartitionPruneInfo out of plan nodes into PlannedStmt This change moves PartitionPruneInfo from individual plan nodes to PlannedStmt, enabling runtime initial pruning to be performed across the entire plan tree without traversing it to find nodes containing PartitionPruneInfos. The PartitionPruneInfo pointer fields in Append and MergeAppend nodes have been replaced with an integer index that points to a list of PartitionPruneInfos within PlannedStmt, which now holds the PartitionPruneInfos for all subqueries. A bitmapset field has been added to PartitionPruneInfo to store the RT indexes that correspond to the apprelids field in Append or MergeAppend. This ensures that the execution pruning logic cross-checks that it operates on the correct plan node. Duplicated code in set_append_references() and set_mergeappend_references() has been moved to a new function, register_pruneinfo(), which both updates the RT indexes by adding rtoffset and adds the PartitionPruneInfo to the global list in PlannerGlobal. Reviewed-by: Alvaro Herrera Reviewed-by: Robert Haas Reviewed-by: Tomas Vondra Discussion: https://postgr.es/m/CA+HiwqFGkMSge6TgC9KQzde0ohpAycLQuV7ooitEEpbKB0O_mg@mail.gmail.com --- src/backend/executor/execMain.c | 1 + src/backend/executor/execParallel.c | 1 + src/backend/executor/execPartition.c | 17 ++++- src/backend/executor/execUtils.c | 1 + src/backend/executor/nodeAppend.c | 5 +- src/backend/executor/nodeMergeAppend.c | 5 +- src/backend/optimizer/plan/createplan.c | 23 +++---- src/backend/optimizer/plan/planner.c | 1 + src/backend/optimizer/plan/setrefs.c | 85 ++++++++++++++++--------- src/backend/partitioning/partprune.c | 19 ++++-- src/include/executor/execPartition.h | 3 +- src/include/nodes/execnodes.h | 1 + src/include/nodes/pathnodes.h | 6 ++ src/include/nodes/plannodes.h | 16 +++-- src/include/partitioning/partprune.h | 8 +-- 15 files changed, 131 insertions(+), 61 deletions(-) diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c index 5ca856fd27..b40fe38178 100644 --- a/src/backend/executor/execMain.c +++ b/src/backend/executor/execMain.c @@ -856,6 +856,7 @@ InitPlan(QueryDesc *queryDesc, int eflags) ExecInitRangeTable(estate, rangeTable, plannedstmt->permInfos); estate->es_plannedstmt = plannedstmt; + estate->es_part_prune_infos = plannedstmt->partPruneInfos; /* * Next, build the ExecRowMark array from the PlanRowMark(s), if any. diff --git a/src/backend/executor/execParallel.c b/src/backend/executor/execParallel.c index bfb3419efb..b01a2fdfdd 100644 --- a/src/backend/executor/execParallel.c +++ b/src/backend/executor/execParallel.c @@ -181,6 +181,7 @@ ExecSerializePlan(Plan *plan, EState *estate) pstmt->dependsOnRole = false; pstmt->parallelModeNeeded = false; pstmt->planTree = plan; + pstmt->partPruneInfos = estate->es_part_prune_infos; pstmt->rtable = estate->es_range_table; pstmt->permInfos = estate->es_rteperminfos; pstmt->resultRelations = NIL; diff --git a/src/backend/executor/execPartition.c b/src/backend/executor/execPartition.c index 7651886229..950fa3289c 100644 --- a/src/backend/executor/execPartition.c +++ b/src/backend/executor/execPartition.c @@ -1786,6 +1786,9 @@ adjust_partition_colnos_using_map(List *colnos, AttrMap *attrMap) * Initialize data structure needed for run-time partition pruning and * do initial pruning if needed * + * 'relids' identifies the relation to which both the parent plan and the + * PartitionPruneInfo given by 'part_prune_index' belong. + * * On return, *initially_valid_subplans is assigned the set of indexes of * child subplans that must be initialized along with the parent plan node. * Initial pruning is performed here if needed and in that case only the @@ -1798,11 +1801,23 @@ adjust_partition_colnos_using_map(List *colnos, AttrMap *attrMap) PartitionPruneState * ExecInitPartitionPruning(PlanState *planstate, int n_total_subplans, - PartitionPruneInfo *pruneinfo, + int part_prune_index, + Bitmapset *relids, Bitmapset **initially_valid_subplans) { PartitionPruneState *prunestate; EState *estate = planstate->state; + PartitionPruneInfo *pruneinfo; + + /* Obtain the pruneinfo we need. */ + pruneinfo = list_nth_node(PartitionPruneInfo, estate->es_part_prune_infos, + part_prune_index); + + /* Its relids better match the plan node's or the planner messed up. */ + if (!bms_equal(relids, pruneinfo->relids)) + elog(ERROR, "wrong pruneinfo with relids=%s found at part_prune_index=%d contained in plan node with relids=%s", + bmsToString(pruneinfo->relids), part_prune_index, + bmsToString(relids)); /* We may need an expression context to evaluate partition exprs */ ExecAssignExprContext(estate, planstate); diff --git a/src/backend/executor/execUtils.c b/src/backend/executor/execUtils.c index 740e8fb148..bc905a0cdc 100644 --- a/src/backend/executor/execUtils.c +++ b/src/backend/executor/execUtils.c @@ -118,6 +118,7 @@ CreateExecutorState(void) estate->es_rowmarks = NULL; estate->es_rteperminfos = NIL; estate->es_plannedstmt = NULL; + estate->es_part_prune_infos = NIL; estate->es_junkFilter = NULL; diff --git a/src/backend/executor/nodeAppend.c b/src/backend/executor/nodeAppend.c index ca0f54d676..de7ebab5c2 100644 --- a/src/backend/executor/nodeAppend.c +++ b/src/backend/executor/nodeAppend.c @@ -134,7 +134,7 @@ ExecInitAppend(Append *node, EState *estate, int eflags) appendstate->as_begun = false; /* If run-time partition pruning is enabled, then set that up now */ - if (node->part_prune_info != NULL) + if (node->part_prune_index >= 0) { PartitionPruneState *prunestate; @@ -145,7 +145,8 @@ ExecInitAppend(Append *node, EState *estate, int eflags) */ prunestate = ExecInitPartitionPruning(&appendstate->ps, list_length(node->appendplans), - node->part_prune_info, + node->part_prune_index, + node->apprelids, &validsubplans); appendstate->as_prune_state = prunestate; nplans = bms_num_members(validsubplans); diff --git a/src/backend/executor/nodeMergeAppend.c b/src/backend/executor/nodeMergeAppend.c index e1b9b984a7..3ed91808dd 100644 --- a/src/backend/executor/nodeMergeAppend.c +++ b/src/backend/executor/nodeMergeAppend.c @@ -82,7 +82,7 @@ ExecInitMergeAppend(MergeAppend *node, EState *estate, int eflags) mergestate->ps.ExecProcNode = ExecMergeAppend; /* If run-time partition pruning is enabled, then set that up now */ - if (node->part_prune_info != NULL) + if (node->part_prune_index >= 0) { PartitionPruneState *prunestate; @@ -93,7 +93,8 @@ ExecInitMergeAppend(MergeAppend *node, EState *estate, int eflags) */ prunestate = ExecInitPartitionPruning(&mergestate->ps, list_length(node->mergeplans), - node->part_prune_info, + node->part_prune_index, + node->apprelids, &validsubplans); mergestate->ms_prune_state = prunestate; nplans = bms_num_members(validsubplans); diff --git a/src/backend/optimizer/plan/createplan.c b/src/backend/optimizer/plan/createplan.c index 178c572b02..8f209c2d2f 100644 --- a/src/backend/optimizer/plan/createplan.c +++ b/src/backend/optimizer/plan/createplan.c @@ -1227,7 +1227,6 @@ create_append_plan(PlannerInfo *root, AppendPath *best_path, int flags) ListCell *subpaths; int nasyncplans = 0; RelOptInfo *rel = best_path->path.parent; - PartitionPruneInfo *partpruneinfo = NULL; int nodenumsortkeys = 0; AttrNumber *nodeSortColIdx = NULL; Oid *nodeSortOperators = NULL; @@ -1378,6 +1377,9 @@ create_append_plan(PlannerInfo *root, AppendPath *best_path, int flags) subplans = lappend(subplans, subplan); } + /* Set below if we find quals that we can use to run-time prune */ + plan->part_prune_index = -1; + /* * If any quals exist, they may be useful to perform further partition * pruning during execution. Gather information needed by the executor to @@ -1401,16 +1403,14 @@ create_append_plan(PlannerInfo *root, AppendPath *best_path, int flags) } if (prunequal != NIL) - partpruneinfo = - make_partition_pruneinfo(root, rel, - best_path->subpaths, - prunequal); + plan->part_prune_index = make_partition_pruneinfo(root, rel, + best_path->subpaths, + prunequal); } plan->appendplans = subplans; plan->nasyncplans = nasyncplans; plan->first_partial_plan = best_path->first_partial_path; - plan->part_prune_info = partpruneinfo; copy_generic_path_info(&plan->plan, (Path *) best_path); @@ -1449,7 +1449,6 @@ create_merge_append_plan(PlannerInfo *root, MergeAppendPath *best_path, List *subplans = NIL; ListCell *subpaths; RelOptInfo *rel = best_path->path.parent; - PartitionPruneInfo *partpruneinfo = NULL; /* * We don't have the actual creation of the MergeAppend node split out @@ -1542,6 +1541,9 @@ create_merge_append_plan(PlannerInfo *root, MergeAppendPath *best_path, subplans = lappend(subplans, subplan); } + /* Set below if we find quals that we can use to run-time prune */ + node->part_prune_index = -1; + /* * If any quals exist, they may be useful to perform further partition * pruning during execution. Gather information needed by the executor to @@ -1557,13 +1559,12 @@ create_merge_append_plan(PlannerInfo *root, MergeAppendPath *best_path, Assert(best_path->path.param_info == NULL); if (prunequal != NIL) - partpruneinfo = make_partition_pruneinfo(root, rel, - best_path->subpaths, - prunequal); + node->part_prune_index = make_partition_pruneinfo(root, rel, + best_path->subpaths, + prunequal); } node->mergeplans = subplans; - node->part_prune_info = partpruneinfo; /* * If prepare_sort_from_pathkeys added sort columns, but we were told to diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c index b665a7762e..9c253e864a 100644 --- a/src/backend/optimizer/plan/planner.c +++ b/src/backend/optimizer/plan/planner.c @@ -557,6 +557,7 @@ standard_planner(Query *parse, const char *query_string, int cursorOptions, result->dependsOnRole = glob->dependsOnRole; result->parallelModeNeeded = glob->parallelModeNeeded; result->planTree = top_plan; + result->partPruneInfos = glob->partPruneInfos; result->rtable = glob->finalrtable; result->permInfos = glob->finalrteperminfos; result->resultRelations = glob->resultRelations; diff --git a/src/backend/optimizer/plan/setrefs.c b/src/backend/optimizer/plan/setrefs.c index 6d23df108d..9f13243d54 100644 --- a/src/backend/optimizer/plan/setrefs.c +++ b/src/backend/optimizer/plan/setrefs.c @@ -1731,6 +1731,47 @@ set_customscan_references(PlannerInfo *root, cscan->custom_relids = offset_relid_set(cscan->custom_relids, rtoffset); } +/* + * register_partpruneinfo + * Subroutine for set_append_references and set_mergeappend_references + * + * Add the PartitionPruneInfo from root->partPruneInfos at the given index + * into PlannerGlobal->partPruneInfos and return its index there. + * + * Also update the RT indexes present in PartitionedRelPruneInfos to add the + * offset. + */ +static int +register_partpruneinfo(PlannerInfo *root, int part_prune_index, int rtoffset) +{ + PlannerGlobal *glob = root->glob; + PartitionPruneInfo *pinfo; + ListCell *l; + + Assert(part_prune_index >= 0 && + part_prune_index < list_length(root->partPruneInfos)); + pinfo = list_nth_node(PartitionPruneInfo, root->partPruneInfos, + part_prune_index); + + pinfo->relids = offset_relid_set(pinfo->relids, rtoffset); + foreach(l, pinfo->prune_infos) + { + List *prune_infos = lfirst(l); + ListCell *l2; + + foreach(l2, prune_infos) + { + PartitionedRelPruneInfo *prelinfo = lfirst(l2); + + prelinfo->rtindex += rtoffset; + } + } + + glob->partPruneInfos = lappend(glob->partPruneInfos, pinfo); + + return list_length(glob->partPruneInfos) - 1; +} + /* * set_append_references * Do set_plan_references processing on an Append @@ -1783,21 +1824,13 @@ set_append_references(PlannerInfo *root, aplan->apprelids = offset_relid_set(aplan->apprelids, rtoffset); - if (aplan->part_prune_info) - { - foreach(l, aplan->part_prune_info->prune_infos) - { - List *prune_infos = lfirst(l); - ListCell *l2; - - foreach(l2, prune_infos) - { - PartitionedRelPruneInfo *pinfo = lfirst(l2); - - pinfo->rtindex += rtoffset; - } - } - } + /* + * Add PartitionPruneInfo, if any, to PlannerGlobal and update the index. + * Also update the RT indexes present in it to add the offset. + */ + if (aplan->part_prune_index >= 0) + aplan->part_prune_index = + register_partpruneinfo(root, aplan->part_prune_index, rtoffset); /* We don't need to recurse to lefttree or righttree ... */ Assert(aplan->plan.lefttree == NULL); @@ -1859,21 +1892,13 @@ set_mergeappend_references(PlannerInfo *root, mplan->apprelids = offset_relid_set(mplan->apprelids, rtoffset); - if (mplan->part_prune_info) - { - foreach(l, mplan->part_prune_info->prune_infos) - { - List *prune_infos = lfirst(l); - ListCell *l2; - - foreach(l2, prune_infos) - { - PartitionedRelPruneInfo *pinfo = lfirst(l2); - - pinfo->rtindex += rtoffset; - } - } - } + /* + * Add PartitionPruneInfo, if any, to PlannerGlobal and update the index. + * Also update the RT indexes present in it to add the offset. + */ + if (mplan->part_prune_index >= 0) + mplan->part_prune_index = + register_partpruneinfo(root, mplan->part_prune_index, rtoffset); /* We don't need to recurse to lefttree or righttree ... */ Assert(mplan->plan.lefttree == NULL); diff --git a/src/backend/partitioning/partprune.c b/src/backend/partitioning/partprune.c index 4e12ae5d1e..ca5467104d 100644 --- a/src/backend/partitioning/partprune.c +++ b/src/backend/partitioning/partprune.c @@ -207,16 +207,20 @@ static void partkey_datum_from_expr(PartitionPruneContext *context, /* * make_partition_pruneinfo - * Builds a PartitionPruneInfo which can be used in the executor to allow - * additional partition pruning to take place. Returns NULL when - * partition pruning would be useless. + * Checks if the given set of quals can be used to build pruning steps + * that the executor can use to prune away unneeded partitions. If + * suitable quals are found then a PartitionPruneInfo is built and tagged + * onto the PlannerInfo's partPruneInfos list. + * + * The return value is the 0-based index of the item added to the + * partPruneInfos list or -1 if nothing was added. * * 'parentrel' is the RelOptInfo for an appendrel, and 'subpaths' is the list * of scan paths for its child rels. * 'prunequal' is a list of potential pruning quals (i.e., restriction * clauses that are applicable to the appendrel). */ -PartitionPruneInfo * +int make_partition_pruneinfo(PlannerInfo *root, RelOptInfo *parentrel, List *subpaths, List *prunequal) @@ -330,10 +334,11 @@ make_partition_pruneinfo(PlannerInfo *root, RelOptInfo *parentrel, * quals, then we can just not bother with run-time pruning. */ if (prunerelinfos == NIL) - return NULL; + return -1; /* Else build the result data structure */ pruneinfo = makeNode(PartitionPruneInfo); + pruneinfo->relids = bms_copy(parentrel->relids); pruneinfo->prune_infos = prunerelinfos; /* @@ -356,7 +361,9 @@ make_partition_pruneinfo(PlannerInfo *root, RelOptInfo *parentrel, else pruneinfo->other_subplans = NULL; - return pruneinfo; + root->partPruneInfos = lappend(root->partPruneInfos, pruneinfo); + + return list_length(root->partPruneInfos) - 1; } /* diff --git a/src/include/executor/execPartition.h b/src/include/executor/execPartition.h index c09bc83b2a..33d922fe8d 100644 --- a/src/include/executor/execPartition.h +++ b/src/include/executor/execPartition.h @@ -123,7 +123,8 @@ typedef struct PartitionPruneState extern PartitionPruneState *ExecInitPartitionPruning(PlanState *planstate, int n_total_subplans, - PartitionPruneInfo *pruneinfo, + int part_prune_index, + Bitmapset *relids, Bitmapset **initially_valid_subplans); extern Bitmapset *ExecFindMatchingSubPlans(PartitionPruneState *prunestate, bool initial_prune); diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h index 182a6956bb..b1471e68fe 100644 --- a/src/include/nodes/execnodes.h +++ b/src/include/nodes/execnodes.h @@ -639,6 +639,7 @@ typedef struct EState * ExecRowMarks, or NULL if none */ List *es_rteperminfos; /* List of RTEPermissionInfo */ PlannedStmt *es_plannedstmt; /* link to top of plan tree */ + List *es_part_prune_infos; /* List of PartitionPruneInfo */ const char *es_sourceText; /* Source text from QueryDesc */ JunkFilter *es_junkFilter; /* top-level junk filter, if any */ diff --git a/src/include/nodes/pathnodes.h b/src/include/nodes/pathnodes.h index add0f9e45f..f8a4cd42c6 100644 --- a/src/include/nodes/pathnodes.h +++ b/src/include/nodes/pathnodes.h @@ -128,6 +128,9 @@ typedef struct PlannerGlobal /* "flat" list of AppendRelInfos */ List *appendRelations; + /* "flat" list of PartitionPruneInfos */ + List *partPruneInfos; + /* OIDs of relations the plan depends on */ List *relationOids; @@ -559,6 +562,9 @@ struct PlannerInfo /* Does this query modify any partition key columns? */ bool partColsUpdated; + + /* PartitionPruneInfos added in this query's plan. */ + List *partPruneInfos; }; diff --git a/src/include/nodes/plannodes.h b/src/include/nodes/plannodes.h index 52f29bcdb6..ef89927471 100644 --- a/src/include/nodes/plannodes.h +++ b/src/include/nodes/plannodes.h @@ -69,6 +69,9 @@ typedef struct PlannedStmt struct Plan *planTree; /* tree of Plan nodes */ + List *partPruneInfos; /* List of PartitionPruneInfo contained in the + * plan */ + List *rtable; /* list of RangeTblEntry nodes */ List *permInfos; /* list of RTEPermissionInfo nodes for rtable @@ -276,8 +279,8 @@ typedef struct Append */ int first_partial_plan; - /* Info for run-time subplan pruning; NULL if we're not doing that */ - struct PartitionPruneInfo *part_prune_info; + /* Index to PlannerInfo.partPruneInfos or -1 if no run-time pruning */ + int part_prune_index; } Append; /* ---------------- @@ -311,8 +314,8 @@ typedef struct MergeAppend /* NULLS FIRST/LAST directions */ bool *nullsFirst pg_node_attr(array_size(numCols)); - /* Info for run-time subplan pruning; NULL if we're not doing that */ - struct PartitionPruneInfo *part_prune_info; + /* Index to PlannerInfo.partPruneInfos or -1 if no run-time pruning */ + int part_prune_index; } MergeAppend; /* ---------------- @@ -1414,6 +1417,10 @@ typedef struct PlanRowMark * Then, since an Append-type node could have multiple partitioning * hierarchies among its children, we have an unordered List of those Lists. * + * relids RelOptInfo.relids of the parent plan node (e.g. Append + * or MergeAppend) to which this PartitionPruneInfo node + * belongs. The pruning logic ensures that this matches + * the parent plan node's apprelids. * prune_infos List of Lists containing PartitionedRelPruneInfo nodes, * one sublist per run-time-prunable partition hierarchy * appearing in the parent plan node's subplans. @@ -1426,6 +1433,7 @@ typedef struct PartitionPruneInfo pg_node_attr(no_equal, no_query_jumble) NodeTag type; + Bitmapset *relids; List *prune_infos; Bitmapset *other_subplans; } PartitionPruneInfo; diff --git a/src/include/partitioning/partprune.h b/src/include/partitioning/partprune.h index bd490d154f..6922e04430 100644 --- a/src/include/partitioning/partprune.h +++ b/src/include/partitioning/partprune.h @@ -70,10 +70,10 @@ typedef struct PartitionPruneContext #define PruneCxtStateIdx(partnatts, step_id, keyno) \ ((partnatts) * (step_id) + (keyno)) -extern PartitionPruneInfo *make_partition_pruneinfo(struct PlannerInfo *root, - struct RelOptInfo *parentrel, - List *subpaths, - List *prunequal); +extern int make_partition_pruneinfo(struct PlannerInfo *root, + struct RelOptInfo *parentrel, + List *subpaths, + List *prunequal); extern Bitmapset *prune_append_rel_partitions(struct RelOptInfo *rel); extern Bitmapset *get_matching_partitions(PartitionPruneContext *context, List *pruning_steps); -- 2.43.0