Investigating #7782 - catch when Postgres planning removes all Citus

tables
citusdata · Feb 20, 2025 · 1c472be · 1c472be
1 parent 459c283
commit 1c472be
Show file tree

Hide file tree

Showing 3 changed files with 102 additions and 0 deletions.
diff --git a/src/backend/distributed/planner/distributed_planner.c b/src/backend/distributed/planner/distributed_planner.c
@@ -272,6 +272,28 @@ distributed_planner(Query *parse,
 			planContext.plan = standard_planner(planContext.query, NULL,
 												planContext.cursorOptions,
 												planContext.boundParams);
+
+			if (needsDistributedPlanning)
+			{
+				Node *origQuals = planContext.originalQuery->jointree->quals;
+				Node *plannedQuals = planContext.query->jointree->quals;
+
+				/*
+				 * The WHERE quals have been eliminated by the Postgres planner, possibly by
+				 * an OR clause that was simplified to TRUE. In such cases, we need to check
+				 * if planned query still requires distributed planning.
+				 */
+				if (origQuals != NULL && plannedQuals == NULL)
+				{
+					List *rtesPostPlan = ExtractRangeTableEntryList(planContext.query);
+					if (list_length(rtesPostPlan) < list_length(rangeTableList))
+					{
+						needsDistributedPlanning = ListContainsDistributedTableRTE(
+							rtesPostPlan, NULL);
+					}
+				}
+			}
+
 			if (needsDistributedPlanning)
 			{
 				result = PlanDistributedStmt(&planContext, rteIdCounter);

diff --git a/src/test/regress/expected/subquery_in_where.out b/src/test/regress/expected/subquery_in_where.out
@@ -1146,7 +1146,53 @@ WHERE (SELECT COUNT(DISTINCT e1.value_2)
 
 (1 row)
 
+-- Test redundant WHERE clause (fix #7782, #7783)
+create table t0 (vkey int4, pkey int4, c0 timestamp);
+create table t1 (vkey int4, pkey int4, c4 timestamp, c5 text, c6 text);
+create table t3 (vkey int4, pkey int4, c9 timestamp);
+create table t7 (vkey int4, pkey int4);
+insert into t0 (vkey, pkey, c0) values
+(3, 13000, make_timestamp(2032, 9, 4, 13, 38, 0));
+SELECT create_reference_table('t1');
+ create_reference_table
+---------------------------------------------------------------------
+
+(1 row)
+
+SELECT create_distributed_table('t3', 'c9');
+ create_distributed_table
+---------------------------------------------------------------------
+
+(1 row)
+
+update t0 set vkey = 117
+where (((t0.pkey) in (select t7.vkey from t7 where false
+        union all
+        select t3.pkey from t3 where false
+        )))
+  or TRUE;
+-- Local table t0 is updated
+SELECT vkey, pkey, c0 FROM t0;
+ vkey | pkey  |            c0
+---------------------------------------------------------------------
+  117 | 13000 | Sat Sep 04 13:38:00 2032
+(1 row)
+
+delete from t0
+where TRUE or (((t0.vkey) >= (select
+          pg_catalog.regexp_count(ref_0.c5, ref_0.c6)
+        from t1 as ref_0 where true)));
+-- Local table t0 is now empty (0 rows)
+SELECT vkey, pkey, c0 FROM t0;
+ vkey | pkey | c0
+---------------------------------------------------------------------
+(0 rows)
+
 SET client_min_messages TO DEFAULT;
 DROP TABLE local_table;
+DROP TABLE t0;
+DROP TABLE t1;
+DROP TABLE t3;
+DROP TABLE t7;
 DROP SCHEMA subquery_in_where CASCADE;
 SET search_path TO public;
diff --git a/src/test/regress/sql/subquery_in_where.sql b/src/test/regress/sql/subquery_in_where.sql
@@ -847,8 +847,42 @@ WHERE (SELECT COUNT(DISTINCT e1.value_2)
      WHERE e1.user_id = u1.user_id
           ) > 115 AND false;
 
+-- Test redundant WHERE clause (fix #7782, #7783)
+create table t0 (vkey int4, pkey int4, c0 timestamp);
+create table t1 (vkey int4, pkey int4, c4 timestamp, c5 text, c6 text);
+create table t3 (vkey int4, pkey int4, c9 timestamp);
+create table t7 (vkey int4, pkey int4);
+
+insert into t0 (vkey, pkey, c0) values
+(3, 13000, make_timestamp(2032, 9, 4, 13, 38, 0));
+
+SELECT create_reference_table('t1');
+SELECT create_distributed_table('t3', 'c9');
+
+update t0 set vkey = 117
+where (((t0.pkey) in (select t7.vkey from t7 where false
+        union all
+        select t3.pkey from t3 where false
+        )))
+  or TRUE;
+
+-- Local table t0 is updated
+SELECT vkey, pkey, c0 FROM t0;
+
+delete from t0
+where TRUE or (((t0.vkey) >= (select  
+          pg_catalog.regexp_count(ref_0.c5, ref_0.c6)
+        from t1 as ref_0 where true)));
+
+-- Local table t0 is now empty (0 rows)
+SELECT vkey, pkey, c0 FROM t0;
+
 SET client_min_messages TO DEFAULT;
 
 DROP TABLE local_table;
+DROP TABLE t0;
+DROP TABLE t1;
+DROP TABLE t3;
+DROP TABLE t7;
 DROP SCHEMA subquery_in_where CASCADE;
 SET search_path TO public;