Ignore extended statistics for inheritance trees

Since commit 859b3003de we only build extended statistics for individual
relations, ignoring the child relations. This resolved the issue with
updating catalog tuple twice, but we still tried to use the statistics
when calculating estimates for the whole inheritance tree. When the
relations contain very distinct data, it may produce bogus estimates.

This is roughly the same issue 427c6b5b9 addressed ~15 years ago, and we
fix it the same way - by ignoring extended statistics when calculating
estimates for the inheritance tree as a whole. We still consider
extended statistics when calculating estimates for individual child
relations, of course.

This may result in plan changes due to different estimates, but if the
old statistics were not describing the inheritance tree particularly
well it's quite likely the new plans is actually better.

Report and patch by Justin Pryzby, minor fixes and cleanup by me.
Backpatch all the way back to PostgreSQL 10, where extended statistics
were introduced (same as 859b3003de).

Author: Justin Pryzby
Reported-by: Justin Pryzby
Backpatch-through: 10
Discussion: https://postgr.es/m/20210923212624.GI831%40telsasoft.com

2 files changed, 18 insertions, 0 deletions

diff --git a/src/backend/statistics/dependencies.c b/src/backend/statistics/dependencies.c
index 82b549fdc2..f1602cd3a2 100644
--- a/src/backend/statistics/dependencies.c
+++ b/src/backend/statistics/dependencies.c
@@ -24,6 +24,7 @@
 #include "nodes/pathnodes.h"
 #include "optimizer/clauses.h"
 #include "optimizer/optimizer.h"
+#include "parser/parsetree.h"
 #include "statistics/extended_stats_internal.h"
 #include "statistics/statistics.h"
 #include "utils/bytea.h"
@@ -1410,11 +1411,19 @@ dependencies_clauselist_selectivity(PlannerInfo *root,
 	int			ndependencies;
 	int			i;
 	AttrNumber	attnum_offset;
+	RangeTblEntry *rte = planner_rt_fetch(rel->relid, root);
 
 	/* unique expressions */
 	Node	  **unique_exprs;
 	int			unique_exprs_cnt;
 
+	/*
+	 * When dealing with inheritance trees, ignore extended stats (which were
+	 * built without data from child rels, and thus do not represent them).
+	 */
+	if (rte->inh)
+		return 1.0;
+
 	/* check if there's any stats that might be useful for us. */
 	if (!has_stats_of_kind(rel->statlist, STATS_EXT_DEPENDENCIES))
 		return 1.0;
diff --git a/src/backend/statistics/extended_stats.c b/src/backend/statistics/extended_stats.c
index 4ab9aaa591..b23c15e9db 100644
--- a/src/backend/statistics/extended_stats.c
+++ b/src/backend/statistics/extended_stats.c
@@ -30,6 +30,7 @@
 #include "nodes/nodeFuncs.h"
 #include "optimizer/clauses.h"
 #include "optimizer/optimizer.h"
+#include "parser/parsetree.h"
 #include "pgstat.h"
 #include "postmaster/autovacuum.h"
 #include "statistics/extended_stats_internal.h"
@@ -1694,6 +1695,14 @@ statext_mcv_clauselist_selectivity(PlannerInfo *root, List *clauses, int varReli
 	List	  **list_exprs;		/* expressions matched to any statistic */
 	int			listidx;
 	Selectivity sel = (is_or) ? 0.0 : 1.0;
+	RangeTblEntry *rte = planner_rt_fetch(rel->relid, root);
+
+	/*
+	 * When dealing with inheritance trees, ignore extended stats (which were
+	 * built without data from child rels, and thus do not represent them).
+	 */
+	if (rte->inh)
+		return sel;
 
 	/* check if there's any stats that might be useful for us. */
 	if (!has_stats_of_kind(rel->statlist, STATS_EXT_MCV))