v49-0006-Add-field-to-store-parent-relids-to-Append-Merge.patch

From bbde32f56bfbaba07d699dec4838f21d43e40384 Mon Sep 17 00:00:00 2001
From: Amit Langote <amitlan@postgresql.org>
Date: Wed, 6 Sep 2023 17:54:02 +0900
Subject: [PATCH v49 6/8] Add field to store parent relids to
 Append/MergeAppend

There's no way currently in the executor to tell if the child
subplans of Append/MergeAppend are scanning partitions, and if
they indeed do, what the RT indexes of their parent/ancestor tables
are.  Executor doesn't need to see their RT indexes except for
run-time pruning, in which case they can can be found in the
PartitionPruneInfo.  A future commit will create a need for them to
be available at all times for the purpose of locking those
parent/ancestor tables when executing a cached plan, so add a
field called allpartrelids to Append/MergeAppend to store those
RT indexes.  This also adds a function called
ExecLockAppendNonLeafTables() to lock those tables.

The code to look up partitioned parent relids for a given list of
partition scan subpaths of an Append/MergeAppend is already present
in make_partition_pruneinfo() but it's local to partprune.c.  This
commit refactors that code into its own function called
add_append_subpath_partrelids() defined in appendinfo.c and
generalizes it to consider child join and aggregate paths.  To
facilitate looking up of parent rels of child grouping rels in
add_append_subpath_partrelids(), parent links are now also set in
the RelOptInfos of child grouping rels too, like they are in
those of child base and join rels.

Discussion: https://postgr.es/m/CA+HiwqFGkMSge6TgC9KQzde0ohpAycLQuV7ooitEEpbKB0O_mg@mail.gmail.com
---
 src/backend/executor/execMain.c         |   2 +-
 src/backend/executor/execUtils.c        |  33 ++++++
 src/backend/executor/nodeAppend.c       |  14 +++
 src/backend/executor/nodeMergeAppend.c  |  14 +++
 src/backend/optimizer/plan/createplan.c |  41 ++++++--
 src/backend/optimizer/plan/planner.c    |   3 +
 src/backend/optimizer/plan/setrefs.c    |   4 +
 src/backend/optimizer/util/appendinfo.c | 134 ++++++++++++++++++++++++
 src/backend/partitioning/partprune.c    | 124 +++-------------------
 src/include/executor/executor.h         |   1 +
 src/include/nodes/plannodes.h           |  14 +++
 src/include/optimizer/appendinfo.h      |   3 +
 src/include/partitioning/partprune.h    |   3 +-
 13 files changed, 266 insertions(+), 124 deletions(-)

diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c
index ffc62e379a..2804ec70f1 100644
--- a/src/backend/executor/execMain.c
+++ b/src/backend/executor/execMain.c
@@ -1475,7 +1475,7 @@ 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 ExecLockAppendNonLeafPartitions().
 			 */
 			ancRel = table_open(ancOid, NoLock);
 			rInfo = makeNode(ResultRelInfo);
diff --git a/src/backend/executor/execUtils.c b/src/backend/executor/execUtils.c
index 117773706a..2b7a08c9ba 100644
--- a/src/backend/executor/execUtils.c
+++ b/src/backend/executor/execUtils.c
@@ -827,6 +827,39 @@ ExecGetRangeTableRelation(EState *estate, Index rti)
 	return rel;
 }
 
+/*
+ * ExecLockAppendNonLeafPartitions
+ *		Lock non-leaf partitions whose child partitions are scanned by a given
+ *		Append/MergeAppend node
+ */
+void
+ExecLockAppendNonLeafPartitions(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 = -1;
+
+		while ((i = bms_next_member(partrelids, i)) > 0)
+		{
+			RangeTblEntry *rte = exec_rt_fetch(i, estate);
+
+			/*
+			 * Don't lock the root parent mentioned in the query, because it
+			 * should already have been locked before entering the executor.
+			 */
+			if (!rte->inFromCl)
+				LockRelationOid(rte->relid, rte->rellockmode);
+			else
+				Assert(CheckRelLockedByMe(rte->relid, rte->rellockmode, true));
+		}
+	}
+}
+
 /*
  * ExecInitResultRelation
  *		Open relation given by the passed-in RT index and fill its
diff --git a/src/backend/executor/nodeAppend.c b/src/backend/executor/nodeAppend.c
index 53ca9dc85d..4759511f87 100644
--- a/src/backend/executor/nodeAppend.c
+++ b/src/backend/executor/nodeAppend.c
@@ -133,6 +133,20 @@ ExecInitAppend(Append *node, EState *estate, int eflags)
 	appendstate->as_syncdone = false;
 	appendstate->as_begun = false;
 
+	/*
+	 * Lock non-leaf partitions whose leaf children are present in
+	 * node->appendplans.  Only need to do so if executing a cached
+	 * plan, because child tables present in cached plans are not
+	 * locked before execution.
+	 *
+	 * XXX - some of the non-leaf partitions may also be mentioned in
+	 * part_prune_info, which if they are would get locked again in
+	 * ExecInitPartitionPruning() because it calls
+	 * ExecGetRangeTableRelation() which locks child tables.
+	 */
+	if (estate->es_cachedplan)
+		ExecLockAppendNonLeafPartitions(estate, node->allpartrelids);
+
 	/* If run-time partition pruning is enabled, then set that up now */
 	if (node->part_prune_info != NULL)
 	{
diff --git a/src/backend/executor/nodeMergeAppend.c b/src/backend/executor/nodeMergeAppend.c
index 52c3edf278..158210aac1 100644
--- a/src/backend/executor/nodeMergeAppend.c
+++ b/src/backend/executor/nodeMergeAppend.c
@@ -81,6 +81,20 @@ ExecInitMergeAppend(MergeAppend *node, EState *estate, int eflags)
 	mergestate->ps.state = estate;
 	mergestate->ps.ExecProcNode = ExecMergeAppend;
 
+	/*
+	 * Lock non-leaf partitions whose leaf children are present in
+	 * node->mergeplans.  Only need to do so if executing a cached
+	 * plan, because child tables present in cached plans are not
+	 * locked before execution.
+	 *
+	 * XXX - some of the non-leaf partitions may also be mentioned in
+	 * part_prune_info, which if they are would get locked again in
+	 * ExecInitPartitionPruning() because it calls
+	 * ExecGetRangeTableRelation() which locks child tables.
+	 */
+	if (estate->es_cachedplan)
+		ExecLockAppendNonLeafPartitions(estate, node->allpartrelids);
+
 	/* If run-time partition pruning is enabled, then set that up now */
 	if (node->part_prune_info != NULL)
 	{
diff --git a/src/backend/optimizer/plan/createplan.c b/src/backend/optimizer/plan/createplan.c
index 34ca6d4ac2..d1f4f606bf 100644
--- a/src/backend/optimizer/plan/createplan.c
+++ b/src/backend/optimizer/plan/createplan.c
@@ -25,6 +25,7 @@
 #include "nodes/extensible.h"
 #include "nodes/makefuncs.h"
 #include "nodes/nodeFuncs.h"
+#include "optimizer/appendinfo.h"
 #include "optimizer/clauses.h"
 #include "optimizer/cost.h"
 #include "optimizer/optimizer.h"
@@ -1229,6 +1230,7 @@ create_append_plan(PlannerInfo *root, AppendPath *best_path, int flags)
 	Oid		   *nodeCollations = NULL;
 	bool	   *nodeNullsFirst = NULL;
 	bool		consider_async = false;
+	List	   *allpartrelids = NIL;
 
 	/*
 	 * The subpaths list could be empty, if every child was proven empty by
@@ -1370,15 +1372,23 @@ create_append_plan(PlannerInfo *root, AppendPath *best_path, int flags)
 			++nasyncplans;
 		}
 
+		/*
+		 * Find partitioned parent rel(s) of the subpath's rel(s).
+		 */
+		allpartrelids = add_append_subpath_partrelids(root, subpath, rel,
+													  allpartrelids);
+
 		subplans = lappend(subplans, subplan);
 	}
 
+	plan->allpartrelids = allpartrelids;
+
 	/*
-	 * If any quals exist, they may be useful to perform further partition
-	 * pruning during execution.  Gather information needed by the executor to
-	 * do partition pruning.
+	 * If scanning partitions, check if there are quals that may be useful to
+	 * perform further partition pruning during execution.  Gather information
+	 * needed by the executor to do partition pruning.
 	 */
-	if (enable_partition_pruning)
+	if (enable_partition_pruning && allpartrelids != NIL)
 	{
 		List	   *prunequal;
 
@@ -1399,7 +1409,8 @@ create_append_plan(PlannerInfo *root, AppendPath *best_path, int flags)
 			partpruneinfo =
 				make_partition_pruneinfo(root, rel,
 										 best_path->subpaths,
-										 prunequal);
+										 prunequal,
+										 allpartrelids);
 	}
 
 	plan->appendplans = subplans;
@@ -1445,6 +1456,7 @@ create_merge_append_plan(PlannerInfo *root, MergeAppendPath *best_path,
 	ListCell   *subpaths;
 	RelOptInfo *rel = best_path->path.parent;
 	PartitionPruneInfo *partpruneinfo = NULL;
+	List	   *allpartrelids = NIL;
 
 	/*
 	 * We don't have the actual creation of the MergeAppend node split out
@@ -1534,15 +1546,23 @@ create_merge_append_plan(PlannerInfo *root, MergeAppendPath *best_path,
 			subplan = (Plan *) sort;
 		}
 
+		/*
+		 * Find partitioned parent rel(s) of the subpath's rel(s).
+		 */
+		allpartrelids = add_append_subpath_partrelids(root, subpath, rel,
+													  allpartrelids);
+
 		subplans = lappend(subplans, subplan);
 	}
 
+	node->allpartrelids = allpartrelids;
+
 	/*
-	 * If any quals exist, they may be useful to perform further partition
-	 * pruning during execution.  Gather information needed by the executor to
-	 * do partition pruning.
+	 * If scanning partitions, check if there are quals that may be useful to
+	 * perform further partition pruning during execution.  Gather information
+	 * needed by the executor to do partition pruning.
 	 */
-	if (enable_partition_pruning)
+	if (enable_partition_pruning && allpartrelids != NIL)
 	{
 		List	   *prunequal;
 
@@ -1554,7 +1574,8 @@ create_merge_append_plan(PlannerInfo *root, MergeAppendPath *best_path,
 		if (prunequal != NIL)
 			partpruneinfo = make_partition_pruneinfo(root, rel,
 													 best_path->subpaths,
-													 prunequal);
+													 prunequal,
+													 allpartrelids);
 	}
 
 	node->mergeplans = subplans;
diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c
index a8cea5efe1..63a11e511e 100644
--- a/src/backend/optimizer/plan/planner.c
+++ b/src/backend/optimizer/plan/planner.c
@@ -7850,8 +7850,11 @@ create_partitionwise_grouping_paths(PlannerInfo *root,
 									   agg_costs, gd, &child_extra,
 									   &child_partially_grouped_rel);
 
+		/* Mark as child of grouped_rel. */
+		child_grouped_rel->parent = grouped_rel;
 		if (child_partially_grouped_rel)
 		{
+			child_partially_grouped_rel->parent = grouped_rel;
 			partially_grouped_live_children =
 				lappend(partially_grouped_live_children,
 						child_partially_grouped_rel);
diff --git a/src/backend/optimizer/plan/setrefs.c b/src/backend/optimizer/plan/setrefs.c
index fc3709510d..04910c301f 100644
--- a/src/backend/optimizer/plan/setrefs.c
+++ b/src/backend/optimizer/plan/setrefs.c
@@ -1766,6 +1766,8 @@ set_append_references(PlannerInfo *root,
 	set_dummy_tlist_references((Plan *) aplan, rtoffset);
 
 	aplan->apprelids = offset_relid_set(aplan->apprelids, rtoffset);
+	foreach(l, aplan->allpartrelids)
+		lfirst(l) = offset_relid_set((Relids) lfirst(l), rtoffset);
 
 	if (aplan->part_prune_info)
 	{
@@ -1842,6 +1844,8 @@ set_mergeappend_references(PlannerInfo *root,
 	set_dummy_tlist_references((Plan *) mplan, rtoffset);
 
 	mplan->apprelids = offset_relid_set(mplan->apprelids, rtoffset);
+	foreach(l, mplan->allpartrelids)
+		lfirst(l) = offset_relid_set((Relids) lfirst(l), rtoffset);
 
 	if (mplan->part_prune_info)
 	{
diff --git a/src/backend/optimizer/util/appendinfo.c b/src/backend/optimizer/util/appendinfo.c
index f456b3b0a4..5bd8e82b9b 100644
--- a/src/backend/optimizer/util/appendinfo.c
+++ b/src/backend/optimizer/util/appendinfo.c
@@ -41,6 +41,7 @@ static void make_inh_translation_list(Relation oldrelation,
 									  AppendRelInfo *appinfo);
 static Node *adjust_appendrel_attrs_mutator(Node *node,
 											adjust_appendrel_attrs_context *context);
+static List *add_part_relids(List *allpartrelids, Bitmapset *partrelids);
 
 
 /*
@@ -1035,3 +1036,136 @@ distribute_row_identity_vars(PlannerInfo *root)
 		}
 	}
 }
+
+/*
+ * add_append_subpath_partrelids
+ *		Look up a child subpath's rel's partitioned parent relids up to
+ *		parentrel and add the bitmapset containing those into
+ *		'allpartrelids'
+ */
+List *
+add_append_subpath_partrelids(PlannerInfo *root, Path *subpath,
+							  RelOptInfo *parentrel,
+							  List *allpartrelids)
+{
+	RelOptInfo *prel = subpath->parent;
+	Relids		partrelids = NULL;
+
+	/* Nothing to do if there's no parent to begin with. */
+	if (!IS_OTHER_REL(prel))
+		return allpartrelids;
+
+	/*
+	 * Traverse up to the pathrel's topmost partitioned parent, collecting
+	 * parent relids as we go; but stop if we reach parentrel.  (Normally, a
+	 * pathrel's topmost partitioned parent is either parentrel or a UNION ALL
+	 * appendrel child of parentrel.  But when handling partitionwise joins of
+	 * multi-level partitioning trees, we can see an append path whose
+	 * parentrel is an intermediate partitioned table.)
+	 */
+	do
+	{
+		Relids	parent_relids = NULL;
+
+		/*
+		 * For simple child rels, we can simply set the parent_relids to
+		 * prel->parent->relids.  But for partitionwise join and aggregate
+		 * child rels, while we can use prel->parent to move up the tree,
+		 * parent_relids must be found the hard way through AppendInfoInfos,
+		 * because 1) a joinrel's relids may point to RTE_JOIN entries,
+		 * 2) topmost parent grouping rel's relids field is NULL.
+		 */
+		if (IS_SIMPLE_REL(prel))
+		{
+			prel = prel->parent;
+			/* Stop once we reach the root partitioned rel. */
+			if (!IS_PARTITIONED_REL(prel))
+				break;
+			parent_relids = bms_add_members(parent_relids, prel->relids);
+		}
+		else
+		{
+			AppendRelInfo **appinfos;
+			int		nappinfos,
+					i;
+
+			appinfos = find_appinfos_by_relids(root, prel->relids,
+											   &nappinfos);
+			for (i = 0; i < nappinfos; i++)
+			{
+				AppendRelInfo *appinfo = appinfos[i];
+
+				parent_relids = bms_add_member(parent_relids,
+											   appinfo->parent_relid);
+			}
+			pfree(appinfos);
+			prel = prel->parent;
+		}
+		/* accept this level as an interesting parent */
+		partrelids = bms_add_members(partrelids, parent_relids);
+		if (prel == parentrel)
+			break;		/* don't traverse above parentrel */
+	} while (IS_OTHER_REL(prel));
+
+	if (partrelids == NULL)
+		return allpartrelids;
+
+	return add_part_relids(allpartrelids, partrelids);
+}
+
+/*
+ * add_part_relids
+ *		Add new info to a list of Bitmapsets of partitioned relids.
+ *
+ * Within 'allpartrelids', there is one Bitmapset for each topmost parent
+ * partitioned rel.  Each Bitmapset contains the RT indexes of the topmost
+ * parent as well as its relevant non-leaf child partitions.  Since (by
+ * construction of the rangetable list) parent partitions must have lower
+ * RT indexes than their children, we can distinguish the topmost parent
+ * as being the lowest set bit in the Bitmapset.
+ *
+ * 'partrelids' contains the RT indexes of a parent partitioned rel, and
+ * possibly some non-leaf children, that are newly identified as parents of
+ * some subpath rel passed to make_partition_pruneinfo().  These are added
+ * to an appropriate member of 'allpartrelids'.
+ *
+ * Note that the list contains only RT indexes of partitioned tables that
+ * are parents of some scan-level relation appearing in the 'subpaths' that
+ * make_partition_pruneinfo() is dealing with.  Also, "topmost" parents are
+ * not allowed to be higher than the 'parentrel' associated with the append
+ * path.  In this way, we avoid expending cycles on partitioned rels that
+ * can't contribute useful pruning information for the problem at hand.
+ * (It is possible for 'parentrel' to be a child partitioned table, and it
+ * is also possible for scan-level relations to be child partitioned tables
+ * rather than leaf partitions.  Hence we must construct this relation set
+ * with reference to the particular append path we're dealing with, rather
+ * than looking at the full partitioning structure represented in the
+ * RelOptInfos.)
+ */
+static List *
+add_part_relids(List *allpartrelids, Bitmapset *partrelids)
+{
+	Index		targetpart;
+	ListCell   *lc;
+
+	/* We can easily get the lowest set bit this way: */
+	targetpart = bms_next_member(partrelids, -1);
+	Assert(targetpart > 0);
+
+	/* Look for a matching topmost parent */
+	foreach(lc, allpartrelids)
+	{
+		Bitmapset  *currpartrelids = (Bitmapset *) lfirst(lc);
+		Index		currtarget = bms_next_member(currpartrelids, -1);
+
+		if (targetpart == currtarget)
+		{
+			/* Found a match, so add any new RT indexes to this hierarchy */
+			currpartrelids = bms_add_members(currpartrelids, partrelids);
+			lfirst(lc) = currpartrelids;
+			return allpartrelids;
+		}
+	}
+	/* No match, so add the new partition hierarchy to the list */
+	return lappend(allpartrelids, partrelids);
+}
diff --git a/src/backend/partitioning/partprune.c b/src/backend/partitioning/partprune.c
index 3f31ecc956..42461a5b2c 100644
--- a/src/backend/partitioning/partprune.c
+++ b/src/backend/partitioning/partprune.c
@@ -138,7 +138,6 @@ typedef struct PruneStepResult
 } PruneStepResult;
 
 
-static List *add_part_relids(List *allpartrelids, Bitmapset *partrelids);
 static List *make_partitionedrel_pruneinfo(PlannerInfo *root,
 										   RelOptInfo *parentrel,
 										   List *prunequal,
@@ -216,33 +215,32 @@ static void partkey_datum_from_expr(PartitionPruneContext *context,
  * 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).
+ * 'allpartrelids' contains Bitmapsets of RT indexes of partitioned parents
+ * whose partitions' Paths are in 'subpaths'; there's one Bitmapset for every
+ * partition tree involved.
  */
 PartitionPruneInfo *
 make_partition_pruneinfo(PlannerInfo *root, RelOptInfo *parentrel,
 						 List *subpaths,
-						 List *prunequal)
+						 List *prunequal,
+						 List *allpartrelids)
 {
 	PartitionPruneInfo *pruneinfo;
 	Bitmapset  *allmatchedsubplans = NULL;
-	List	   *allpartrelids;
 	List	   *prunerelinfos;
 	int		   *relid_subplan_map;
 	ListCell   *lc;
 	int			i;
 
+	Assert(list_length(allpartrelids) > 0);
+
 	/*
-	 * Scan the subpaths to see which ones are scans of partition child
-	 * relations, and identify their parent partitioned rels.  (Note: we must
-	 * restrict the parent partitioned rels to be parentrel or children of
-	 * parentrel, otherwise we couldn't translate prunequal to match.)
-	 *
-	 * Also construct a temporary array to map from partition-child-relation
-	 * relid to the index in 'subpaths' of the scan plan for that partition.
+	 * Construct a temporary array to map from partition-child-relation relid
+	 * to the index in 'subpaths' of the scan plan for that partition.
 	 * (Use of "subplan" rather than "subpath" is a bit of a misnomer, but
 	 * we'll let it stand.)  For convenience, we use 1-based indexes here, so
 	 * that zero can represent an un-filled array entry.
 	 */
-	allpartrelids = NIL;
 	relid_subplan_map = palloc0(sizeof(int) * root->simple_rel_array_size);
 
 	i = 1;
@@ -251,50 +249,9 @@ make_partition_pruneinfo(PlannerInfo *root, RelOptInfo *parentrel,
 		Path	   *path = (Path *) lfirst(lc);
 		RelOptInfo *pathrel = path->parent;
 
-		/* We don't consider partitioned joins here */
-		if (pathrel->reloptkind == RELOPT_OTHER_MEMBER_REL)
-		{
-			RelOptInfo *prel = pathrel;
-			Bitmapset  *partrelids = NULL;
-
-			/*
-			 * Traverse up to the pathrel's topmost partitioned parent,
-			 * collecting parent relids as we go; but stop if we reach
-			 * parentrel.  (Normally, a pathrel's topmost partitioned parent
-			 * is either parentrel or a UNION ALL appendrel child of
-			 * parentrel.  But when handling partitionwise joins of
-			 * multi-level partitioning trees, we can see an append path whose
-			 * parentrel is an intermediate partitioned table.)
-			 */
-			do
-			{
-				AppendRelInfo *appinfo;
-
-				Assert(prel->relid < root->simple_rel_array_size);
-				appinfo = root->append_rel_array[prel->relid];
-				prel = find_base_rel(root, appinfo->parent_relid);
-				if (!IS_PARTITIONED_REL(prel))
-					break;		/* reached a non-partitioned parent */
-				/* accept this level as an interesting parent */
-				partrelids = bms_add_member(partrelids, prel->relid);
-				if (prel == parentrel)
-					break;		/* don't traverse above parentrel */
-			} while (prel->reloptkind == RELOPT_OTHER_MEMBER_REL);
-
-			if (partrelids)
-			{
-				/*
-				 * Found some relevant parent partitions, which may or may not
-				 * overlap with partition trees we already found.  Add new
-				 * information to the allpartrelids list.
-				 */
-				allpartrelids = add_part_relids(allpartrelids, partrelids);
-				/* Also record the subplan in relid_subplan_map[] */
-				/* No duplicates please */
-				Assert(relid_subplan_map[pathrel->relid] == 0);
-				relid_subplan_map[pathrel->relid] = i;
-			}
-		}
+		/* No duplicates please */
+		Assert(relid_subplan_map[pathrel->relid] == 0);
+		relid_subplan_map[pathrel->relid] = i;
 		i++;
 	}
 
@@ -360,63 +317,6 @@ make_partition_pruneinfo(PlannerInfo *root, RelOptInfo *parentrel,
 	return pruneinfo;
 }
 
-/*
- * add_part_relids
- *		Add new info to a list of Bitmapsets of partitioned relids.
- *
- * Within 'allpartrelids', there is one Bitmapset for each topmost parent
- * partitioned rel.  Each Bitmapset contains the RT indexes of the topmost
- * parent as well as its relevant non-leaf child partitions.  Since (by
- * construction of the rangetable list) parent partitions must have lower
- * RT indexes than their children, we can distinguish the topmost parent
- * as being the lowest set bit in the Bitmapset.
- *
- * 'partrelids' contains the RT indexes of a parent partitioned rel, and
- * possibly some non-leaf children, that are newly identified as parents of
- * some subpath rel passed to make_partition_pruneinfo().  These are added
- * to an appropriate member of 'allpartrelids'.
- *
- * Note that the list contains only RT indexes of partitioned tables that
- * are parents of some scan-level relation appearing in the 'subpaths' that
- * make_partition_pruneinfo() is dealing with.  Also, "topmost" parents are
- * not allowed to be higher than the 'parentrel' associated with the append
- * path.  In this way, we avoid expending cycles on partitioned rels that
- * can't contribute useful pruning information for the problem at hand.
- * (It is possible for 'parentrel' to be a child partitioned table, and it
- * is also possible for scan-level relations to be child partitioned tables
- * rather than leaf partitions.  Hence we must construct this relation set
- * with reference to the particular append path we're dealing with, rather
- * than looking at the full partitioning structure represented in the
- * RelOptInfos.)
- */
-static List *
-add_part_relids(List *allpartrelids, Bitmapset *partrelids)
-{
-	Index		targetpart;
-	ListCell   *lc;
-
-	/* We can easily get the lowest set bit this way: */
-	targetpart = bms_next_member(partrelids, -1);
-	Assert(targetpart > 0);
-
-	/* Look for a matching topmost parent */
-	foreach(lc, allpartrelids)
-	{
-		Bitmapset  *currpartrelids = (Bitmapset *) lfirst(lc);
-		Index		currtarget = bms_next_member(currpartrelids, -1);
-
-		if (targetpart == currtarget)
-		{
-			/* Found a match, so add any new RT indexes to this hierarchy */
-			currpartrelids = bms_add_members(currpartrelids, partrelids);
-			lfirst(lc) = currpartrelids;
-			return allpartrelids;
-		}
-	}
-	/* No match, so add the new partition hierarchy to the list */
-	return lappend(allpartrelids, partrelids);
-}
-
 /*
  * make_partitionedrel_pruneinfo
  *		Build a List of PartitionedRelPruneInfos, one for each interesting
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 4f183ec6cd..350a625107 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -601,6 +601,7 @@ exec_rt_fetch(Index rti, EState *estate)
 extern Relation ExecGetRangeTableRelation(EState *estate, Index rti);
 extern void ExecInitResultRelation(EState *estate, ResultRelInfo *resultRelInfo,
 								   Index rti);
+extern void ExecLockAppendNonLeafPartitions(EState *estate, List *allpartrelids);
 
 extern int	executor_errposition(EState *estate, int location);
 
diff --git a/src/include/nodes/plannodes.h b/src/include/nodes/plannodes.h
index d40af8e59f..ffcc8490d7 100644
--- a/src/include/nodes/plannodes.h
+++ b/src/include/nodes/plannodes.h
@@ -267,6 +267,13 @@ typedef struct Append
 	List	   *appendplans;
 	int			nasyncplans;	/* # of asynchronous plans */
 
+	/*
+	 * RTIs of all partitioned tables whose children are scanned by
+	 * appendplans. The list contains a bitmapset for every partition tree
+	 * covered by this Append.
+	 */
+	List	   *allpartrelids;
+
 	/*
 	 * All 'appendplans' preceding this index are non-partial plans. All
 	 * 'appendplans' from this index onwards are partial plans.
@@ -291,6 +298,13 @@ typedef struct MergeAppend
 
 	List	   *mergeplans;
 
+	/*
+	 * RTIs of all partitioned tables whose children are scanned by
+	 * mergeplans. The list contains a bitmapset for every partition tree
+	 * covered by this MergeAppend.
+	 */
+	List	   *allpartrelids;
+
 	/* these fields are just like the sort-key info in struct Sort: */
 
 	/* number of sort-key columns */
diff --git a/src/include/optimizer/appendinfo.h b/src/include/optimizer/appendinfo.h
index a05f91f77d..1621a7319a 100644
--- a/src/include/optimizer/appendinfo.h
+++ b/src/include/optimizer/appendinfo.h
@@ -46,5 +46,8 @@ extern void add_row_identity_columns(PlannerInfo *root, Index rtindex,
 									 RangeTblEntry *target_rte,
 									 Relation target_relation);
 extern void distribute_row_identity_vars(PlannerInfo *root);
+extern List *add_append_subpath_partrelids(PlannerInfo *root, Path *subpath,
+							  RelOptInfo *parentrel,
+							  List *allpartrelids);
 
 #endif							/* APPENDINFO_H */
diff --git a/src/include/partitioning/partprune.h b/src/include/partitioning/partprune.h
index 8636e04e37..caa774a111 100644
--- a/src/include/partitioning/partprune.h
+++ b/src/include/partitioning/partprune.h
@@ -73,7 +73,8 @@ typedef struct PartitionPruneContext
 extern PartitionPruneInfo *make_partition_pruneinfo(struct PlannerInfo *root,
 													struct RelOptInfo *parentrel,
 													List *subpaths,
-													List *prunequal);
+													List *prunequal,
+													List *allpartrelids);
 extern Bitmapset *prune_append_rel_partitions(struct RelOptInfo *rel);
 extern Bitmapset *get_matching_partitions(PartitionPruneContext *context,
 										  List *pruning_steps);
-- 
2.35.3