Disallow replacing joins with scans in problematic cases.

Etsuro Fujita · Etsuro Fujita · commit 9edf72aa7644 · 2023-07-28T15:45:08.000+09:00
Commit e7cb7ee, which introduced the infrastructure for FDWs and custom scan providers to replace joins with scans, failed to add support handling of pseudoconstant quals assigned to replaced joins in createplan.c, leading to an incorrect plan without a gating Result node when postgres_fdw replaced a join with such a qual. To fix, we could add the support by 1) modifying the ForeignPath and CustomPath structs to store the list of RestrictInfo nodes to apply to the join, as in JoinPaths, if they represent foreign and custom scans replacing a join with a scan, and by 2) modifying create_scan_plan() in createplan.c to use that list in that case, instead of the baserestrictinfo list, to get pseudoconstant quals assigned to the join; but #1 would cause an ABI break. So fix by modifying the infrastructure to just disallow replacing joins with such quals. Back-patch to all supported branches. Reported by Nishant Sharma. Patch by me, reviewed by Nishant Sharma and Richard Guo. Discussion: https://postgr.es/m/CADrsxdbcN1vejBaf8a%2BQhrZY5PXL-04mCd4GDu6qm6FigDZd6Q%40mail.gmail.com
diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out
@@ -2176,6 +2176,32 @@ SELECT t1."C 1" FROM "S 1"."T 1" t1, LATERAL (SELECT DISTINCT t2.c1, t3.c1 FROM
    1
 (10 rows)
 
+-- join with pseudoconstant quals, not pushed down.
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT t1.c1, t2.c1 FROM ft1 t1 JOIN ft2 t2 ON (t1.c1 = t2.c1 AND CURRENT_USER = SESSION_USER) ORDER BY t1.c3, t1.c1 OFFSET 100 LIMIT 10;
+                                  QUERY PLAN                                   
+-------------------------------------------------------------------------------
+ Limit
+   Output: t1.c1, t2.c1, t1.c3
+   ->  Sort
+         Output: t1.c1, t2.c1, t1.c3
+         Sort Key: t1.c3, t1.c1
+         ->  Result
+               Output: t1.c1, t2.c1, t1.c3
+               One-Time Filter: (CURRENT_USER = SESSION_USER)
+               ->  Hash Join
+                     Output: t1.c1, t1.c3, t2.c1
+                     Hash Cond: (t2.c1 = t1.c1)
+                     ->  Foreign Scan on public.ft2 t2
+                           Output: t2.c1
+                           Remote SQL: SELECT "C 1" FROM "S 1"."T 1"
+                     ->  Hash
+                           Output: t1.c1, t1.c3
+                           ->  Foreign Scan on public.ft1 t1
+                                 Output: t1.c1, t1.c3
+                                 Remote SQL: SELECT "C 1", c3 FROM "S 1"."T 1"
+(19 rows)
+
 -- non-Var items in targetlist of the nullable rel of a join preventing
 -- push-down in some cases
 -- unable to push {ft1, ft2}
diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql
@@ -570,6 +570,9 @@ SELECT t1c1, avg(t1c1 + t2c1) FROM (SELECT t1.c1, t2.c1 FROM ft1 t1 JOIN ft2 t2
 EXPLAIN (VERBOSE, COSTS OFF)
 SELECT t1."C 1" FROM "S 1"."T 1" t1, LATERAL (SELECT DISTINCT t2.c1, t3.c1 FROM ft1 t2, ft2 t3 WHERE t2.c1 = t3.c1 AND t2.c2 = t1.c2) q ORDER BY t1."C 1" OFFSET 10 LIMIT 10;
 SELECT t1."C 1" FROM "S 1"."T 1" t1, LATERAL (SELECT DISTINCT t2.c1, t3.c1 FROM ft1 t2, ft2 t3 WHERE t2.c1 = t3.c1 AND t2.c2 = t1.c2) q ORDER BY t1."C 1" OFFSET 10 LIMIT 10;
+-- join with pseudoconstant quals, not pushed down.
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT t1.c1, t2.c1 FROM ft1 t1 JOIN ft2 t2 ON (t1.c1 = t2.c1 AND CURRENT_USER = SESSION_USER) ORDER BY t1.c3, t1.c1 OFFSET 100 LIMIT 10;
 
 -- non-Var items in targetlist of the nullable rel of a join preventing
 -- push-down in some cases
diff --git a/src/backend/optimizer/path/joinpath.c b/src/backend/optimizer/path/joinpath.c
@@ -22,6 +22,7 @@
 #include "optimizer/pathnode.h"
 #include "optimizer/paths.h"
 #include "optimizer/planmain.h"
+#include "optimizer/restrictinfo.h"
 
 /* Hook for plugins to get control in add_paths_to_joinrel() */
 set_join_pathlist_hook_type set_join_pathlist_hook = NULL;
@@ -124,6 +125,7 @@ add_paths_to_joinrel(PlannerInfo *root,
 {
 	JoinPathExtraData extra;
 	bool		mergejoin_allowed = true;
+	bool		consider_join_pushdown = false;
 	ListCell   *lc;
 	Relids		joinrelids;
 
@@ -307,21 +309,34 @@ add_paths_to_joinrel(PlannerInfo *root,
 		hash_inner_and_outer(root, joinrel, outerrel, innerrel,
 							 jointype, &extra);
 
+	/*
+	 * createplan.c does not currently support handling of pseudoconstant
+	 * clauses assigned to joins pushed down by extensions; check if the
+	 * restrictlist has such clauses, and if so, disallow pushing down joins.
+	 */
+	if ((joinrel->fdwroutine &&
+		 joinrel->fdwroutine->GetForeignJoinPaths) ||
+		set_join_pathlist_hook)
+		consider_join_pushdown = !has_pseudoconstant_clauses(root,
+															 restrictlist);
+
 	/*
 	 * 5. If inner and outer relations are foreign tables (or joins) belonging
 	 * to the same server and assigned to the same user to check access
 	 * permissions as, give the FDW a chance to push down joins.
 	 */
 	if (joinrel->fdwroutine &&
-		joinrel->fdwroutine->GetForeignJoinPaths)
+		joinrel->fdwroutine->GetForeignJoinPaths &&
+		consider_join_pushdown)
 		joinrel->fdwroutine->GetForeignJoinPaths(root, joinrel,
 												 outerrel, innerrel,
 												 jointype, &extra);
 
 	/*
 	 * 6. Finally, give extensions a chance to manipulate the path list.
 	 */
-	if (set_join_pathlist_hook)
+	if (set_join_pathlist_hook &&
+		consider_join_pushdown)
 		set_join_pathlist_hook(root, joinrel, outerrel, innerrel,
 							   jointype, &extra);
 }
diff --git a/src/backend/optimizer/util/restrictinfo.c b/src/backend/optimizer/util/restrictinfo.c
@@ -509,6 +509,35 @@ extract_actual_join_clauses(List *restrictinfo_list,
 	}
 }
 
+/*
+ * has_pseudoconstant_clauses
+ *
+ * Returns true if 'restrictinfo_list' includes pseudoconstant clauses.
+ *
+ * This is used when we determine whether to allow extensions to consider
+ * pushing down joins in add_paths_to_joinrel().
+ */
+bool
+has_pseudoconstant_clauses(PlannerInfo *root,
+						   List *restrictinfo_list)
+{
+	ListCell   *l;
+
+	/* No need to look if we know there are no pseudoconstants */
+	if (!root->hasPseudoConstantQuals)
+		return false;
+
+	/* See if there are pseudoconstants in the RestrictInfo list */
+	foreach(l, restrictinfo_list)
+	{
+		RestrictInfo *rinfo = lfirst_node(RestrictInfo, l);
+
+		if (rinfo->pseudoconstant)
+			return true;
+	}
+	return false;
+}
+
 
 /*
  * join_clause_is_movable_to
diff --git a/src/include/optimizer/restrictinfo.h b/src/include/optimizer/restrictinfo.h
@@ -49,6 +49,8 @@ extern void extract_actual_join_clauses(List *restrictinfo_list,
 										Relids joinrelids,
 										List **joinquals,
 										List **otherquals);
+extern bool has_pseudoconstant_clauses(PlannerInfo *root,
+									   List *restrictinfo_list);
 extern bool join_clause_is_movable_to(RestrictInfo *rinfo, RelOptInfo *baserel);
 extern bool join_clause_is_movable_into(RestrictInfo *rinfo,
 										Relids currentrelids,
