Fix run-time partition pruning for appends with multiple source rels.

The previous coding here supposed that if run-time partitioning applied to
a particular Append/MergeAppend plan, then all child plans of that node
must be members of a single partitioning hierarchy.  This is totally wrong,
since an Append could be formed from a UNION ALL: we could have multiple
hierarchies sharing the same Append, or child plans that aren't part of any
hierarchy.

To fix, restructure the related plan-time and execution-time data
structures so that we can have a separate list or array for each
partitioning hierarchy.  Also track subplans that are not part of any
hierarchy, and make sure they don't get pruned.

Per reports from Phil Florent and others.  Back-patch to v11, since
the bug originated there.

David Rowley, with a lot of cosmetic adjustments by me; thanks also
to Amit Langote for review.

Discussion: https://postgr.es/m/HE1PR03MB17068BB27404C90B5B788BCABA7B0@HE1PR03MB1706.eurprd03.prod.outlook.com

Author: tglsfdc

src/backend/executor/execPartition.c

@@ -129,7 +129,7 @@ ExecInitAppend(Append *node, EState *estate, int eflags)
 	appendstate->as_whichplan = INVALID_SUBPLAN_INDEX;
 
 	/* If run-time partition pruning is enabled, then set that up now */
-	if (node->part_prune_infos != NIL)
+	if (node->part_prune_info != NULL)
 	{
 		PartitionPruneState *prunestate;
 
@@ -138,7 +138,7 @@ ExecInitAppend(Append *node, EState *estate, int eflags)
 
 		/* Create the working data structure for pruning. */
 		prunestate = ExecCreatePartitionPruneState(&appendstate->ps,
-												   node->part_prune_infos);
+												   node->part_prune_info);
 		appendstate->as_prune_state = prunestate;
 
 		/* Perform an initial partition prune, if required. */

src/backend/executor/nodeAppend.c

@@ -90,15 +90,15 @@ ExecInitMergeAppend(MergeAppend *node, EState *estate, int eflags)
 	mergestate->ms_noopscan = false;
 
 	/* If run-time partition pruning is enabled, then set that up now */
-	if (node->part_prune_infos != NIL)
+	if (node->part_prune_info != NULL)
 	{
 		PartitionPruneState *prunestate;
 
 		/* We may need an expression context to evaluate partition exprs */
 		ExecAssignExprContext(estate, &mergestate->ps);
 
 		prunestate = ExecCreatePartitionPruneState(&mergestate->ps,
-												   node->part_prune_infos);
+												   node->part_prune_info);
 		mergestate->ms_prune_state = prunestate;
 
 		/* Perform an initial partition prune, if required. */

src/backend/executor/nodeMergeAppend.c

@@ -245,7 +245,7 @@ _copyAppend(const Append *from)
 	COPY_NODE_FIELD(appendplans);
 	COPY_SCALAR_FIELD(first_partial_plan);
 	COPY_NODE_FIELD(partitioned_rels);
-	COPY_NODE_FIELD(part_prune_infos);
+	COPY_NODE_FIELD(part_prune_info);
 
 	return newnode;
 }
@@ -273,7 +273,7 @@ _copyMergeAppend(const MergeAppend *from)
 	COPY_POINTER_FIELD(sortOperators, from->numCols * sizeof(Oid));
 	COPY_POINTER_FIELD(collations, from->numCols * sizeof(Oid));
 	COPY_POINTER_FIELD(nullsFirst, from->numCols * sizeof(bool));
-	COPY_NODE_FIELD(part_prune_infos);
+	COPY_NODE_FIELD(part_prune_info);
 
 	return newnode;
 }
@@ -1182,6 +1182,17 @@ _copyPartitionPruneInfo(const PartitionPruneInfo *from)
 {
 	PartitionPruneInfo *newnode = makeNode(PartitionPruneInfo);
 
+	COPY_NODE_FIELD(prune_infos);
+	COPY_BITMAPSET_FIELD(other_subplans);
+
+	return newnode;
+}
+
+static PartitionedRelPruneInfo *
+_copyPartitionedRelPruneInfo(const PartitionedRelPruneInfo *from)
+{
+	PartitionedRelPruneInfo *newnode = makeNode(PartitionedRelPruneInfo);
+
 	COPY_SCALAR_FIELD(reloid);
 	COPY_NODE_FIELD(pruning_steps);
 	COPY_BITMAPSET_FIELD(present_parts);
@@ -4908,6 +4919,9 @@ copyObjectImpl(const void *from)
 		case T_PartitionPruneInfo:
 			retval = _copyPartitionPruneInfo(from);
 			break;
+		case T_PartitionedRelPruneInfo:
+			retval = _copyPartitionedRelPruneInfo(from);
+			break;
 		case T_PartitionPruneStepOp:
 			retval = _copyPartitionPruneStepOp(from);
 			break;

src/backend/nodes/copyfuncs.c

@@ -402,7 +402,7 @@ _outAppend(StringInfo str, const Append *node)
 	WRITE_NODE_FIELD(appendplans);
 	WRITE_INT_FIELD(first_partial_plan);
 	WRITE_NODE_FIELD(partitioned_rels);
-	WRITE_NODE_FIELD(part_prune_infos);
+	WRITE_NODE_FIELD(part_prune_info);
 }
 
 static void
@@ -435,7 +435,7 @@ _outMergeAppend(StringInfo str, const MergeAppend *node)
 	for (i = 0; i < node->numCols; i++)
 		appendStringInfo(str, " %s", booltostr(node->nullsFirst[i]));
 
-	WRITE_NODE_FIELD(part_prune_infos);
+	WRITE_NODE_FIELD(part_prune_info);
 }
 
 static void
@@ -1014,10 +1014,19 @@ _outPlanRowMark(StringInfo str, const PlanRowMark *node)
 
 static void
 _outPartitionPruneInfo(StringInfo str, const PartitionPruneInfo *node)
+{
+	WRITE_NODE_TYPE("PARTITIONPRUNEINFO");
+
+	WRITE_NODE_FIELD(prune_infos);
+	WRITE_BITMAPSET_FIELD(other_subplans);
+}
+
+static void
+_outPartitionedRelPruneInfo(StringInfo str, const PartitionedRelPruneInfo *node)
 {
 	int			i;
 
-	WRITE_NODE_TYPE("PARTITIONPRUNEINFO");
+	WRITE_NODE_TYPE("PARTITIONEDRELPRUNEINFO");
 
 	WRITE_OID_FIELD(reloid);
 	WRITE_NODE_FIELD(pruning_steps);
@@ -3831,6 +3840,9 @@ outNode(StringInfo str, const void *obj)
 			case T_PartitionPruneInfo:
 				_outPartitionPruneInfo(str, obj);
 				break;
+			case T_PartitionedRelPruneInfo:
+				_outPartitionedRelPruneInfo(str, obj);
+				break;
 			case T_PartitionPruneStepOp:
 				_outPartitionPruneStepOp(str, obj);
 				break;

src/backend/nodes/outfuncs.c

@@ -1612,7 +1612,7 @@ _readAppend(void)
 	READ_NODE_FIELD(appendplans);
 	READ_INT_FIELD(first_partial_plan);
 	READ_NODE_FIELD(partitioned_rels);
-	READ_NODE_FIELD(part_prune_infos);
+	READ_NODE_FIELD(part_prune_info);
 
 	READ_DONE();
 }
@@ -1634,7 +1634,7 @@ _readMergeAppend(void)
 	READ_OID_ARRAY(sortOperators, local_node->numCols);
 	READ_OID_ARRAY(collations, local_node->numCols);
 	READ_BOOL_ARRAY(nullsFirst, local_node->numCols);
-	READ_NODE_FIELD(part_prune_infos);
+	READ_NODE_FIELD(part_prune_info);
 
 	READ_DONE();
 }
@@ -2329,6 +2329,17 @@ _readPartitionPruneInfo(void)
 {
 	READ_LOCALS(PartitionPruneInfo);
 
+	READ_NODE_FIELD(prune_infos);
+	READ_BITMAPSET_FIELD(other_subplans);
+
+	READ_DONE();
+}
+
+static PartitionedRelPruneInfo *
+_readPartitionedRelPruneInfo(void)
+{
+	READ_LOCALS(PartitionedRelPruneInfo);
+
 	READ_OID_FIELD(reloid);
 	READ_NODE_FIELD(pruning_steps);
 	READ_BITMAPSET_FIELD(present_parts);
@@ -2726,6 +2737,8 @@ parseNodeString(void)
 		return_value = _readPlanRowMark();
 	else if (MATCH("PARTITIONPRUNEINFO", 18))
 		return_value = _readPartitionPruneInfo();
+	else if (MATCH("PARTITIONEDRELPRUNEINFO", 23))
+		return_value = _readPartitionedRelPruneInfo();
 	else if (MATCH("PARTITIONPRUNESTEPOP", 20))
 		return_value = _readPartitionPruneStepOp();
 	else if (MATCH("PARTITIONPRUNESTEPCOMBINE", 25))

src/backend/nodes/readfuncs.c

@@ -1388,7 +1388,6 @@ add_paths_to_append_rel(PlannerInfo *root, RelOptInfo *rel,
 	List	   *all_child_outers = NIL;
 	ListCell   *l;
 	List	   *partitioned_rels = NIL;
-	bool		build_partitioned_rels = false;
 	double		partial_rows = -1;
 
 	/* If appropriate, consider parallel append */
@@ -1413,10 +1412,11 @@ add_paths_to_append_rel(PlannerInfo *root, RelOptInfo *rel,
 	if (rel->part_scheme != NULL)
 	{
 		if (IS_SIMPLE_REL(rel))
-			partitioned_rels = rel->partitioned_child_rels;
+			partitioned_rels = list_make1(rel->partitioned_child_rels);
 		else if (IS_JOIN_REL(rel))
 		{
 			int			relid = -1;
+			List	   *partrels = NIL;
 
 			/*
 			 * For a partitioned joinrel, concatenate the component rels'
@@ -1430,16 +1430,16 @@ add_paths_to_append_rel(PlannerInfo *root, RelOptInfo *rel,
 				component = root->simple_rel_array[relid];
 				Assert(component->part_scheme != NULL);
 				Assert(list_length(component->partitioned_child_rels) >= 1);
-				partitioned_rels =
-					list_concat(partitioned_rels,
+				partrels =
+					list_concat(partrels,
 								list_copy(component->partitioned_child_rels));
 			}
+
+			partitioned_rels = list_make1(partrels);
 		}
 
 		Assert(list_length(partitioned_rels) >= 1);
 	}
-	else if (rel->rtekind == RTE_SUBQUERY)
-		build_partitioned_rels = true;
 
 	/*
 	 * For every non-dummy child, remember the cheapest path.  Also, identify
@@ -1453,17 +1453,12 @@ add_paths_to_append_rel(PlannerInfo *root, RelOptInfo *rel,
 		Path	   *cheapest_partial_path = NULL;
 
 		/*
-		 * If we need to build partitioned_rels, accumulate the partitioned
-		 * rels for this child.  We must ensure that parents are always listed
-		 * before their child partitioned tables.
+		 * For UNION ALLs with non-empty partitioned_child_rels, accumulate
+		 * the Lists of child relations.
 		 */
-		if (build_partitioned_rels)
-		{
-			List	   *cprels = childrel->partitioned_child_rels;
-
-			partitioned_rels = list_concat(partitioned_rels,
-										   list_copy(cprels));
-		}
+		if (rel->rtekind == RTE_SUBQUERY && childrel->partitioned_child_rels != NIL)
+			partitioned_rels = lappend(partitioned_rels,
+									   childrel->partitioned_child_rels);
 
 		/*
 		 * If child has an unparameterized cheapest-total path, add that to