Disallow partitionwise join when collations don't match

If the collation of any join key column doesn’t match the collation of
the corresponding partition key, partitionwise joins can yield incorrect
results. For example, rows that would match under the join key collation
might be located in different partitions due to the partitioning
collation. In such cases, a partitionwise join would yield different
results from a non-partitionwise join, so disallow it in such cases.

Reported-by: Tender Wang <tndrwang@gmail.com>
Author: Jian He <jian.universality@gmail.com>
Reviewed-by: Tender Wang <tndrwang@gmail.com>
Reviewed-by: Junwang Zhao <zhjwpku@gmail.com>
Discussion: https://postgr.es/m/CAHewXNno_HKiQ6PqyLYfuqDtwp7KKHZiH1J7Pqyz0nr+PS2Dwg@mail.gmail.com
Backpatch-through: 12

diff --git a/src/backend/optimizer/util/relnode.c b/src/backend/optimizer/util/relnode.c
index e05b21c884e57d8bee0629a24a4a0a2bff9021f4..610093fe915edeb7867febb252885045ecf5b645 100644 (file)
--- a/src/backend/optimizer/util/relnode.c
+++ b/src/backend/optimizer/util/relnode.c
@@ -2188,6 +2188,10 @@ have_partkey_equi_join(PlannerInfo *root, RelOptInfo *joinrel,
                if (ipk1 != ipk2)
                        continue;
 
+               /* Reject if the partition key collation differs from the clause's. */
+               if (rel1->part_scheme->partcollation[ipk1] != opexpr->inputcollid)
+                       return false;
+
                /*
                 * The clause allows partitionwise join only if it uses the same
                 * operator family as that specified by the partition key.

diff --git a/src/test/regress/expected/collate.icu.utf8.out b/src/test/regress/expected/collate.icu.utf8.out
index c7807a14ca6d6368a57bb0f88c0370cbe70e7dbe..7a425afe1f5c752f65580e94ce18ee3f445c0819 100644 (file)
--- a/src/test/regress/expected/collate.icu.utf8.out
+++ b/src/test/regress/expected/collate.icu.utf8.out
@@ -2138,6 +2138,124 @@ SELECT c collate "C", count(c) FROM pagg_tab3 GROUP BY c collate "C" ORDER BY 1;
  b |     5
 (4 rows)
 
+-- Partitionwise join should not be allowed too when the collation used by the
+-- join keys doesn't match the partition key collation.
+SET enable_partitionwise_join TO false;
+EXPLAIN (COSTS OFF)
+SELECT t1.c, count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c GROUP BY 1 ORDER BY t1.c COLLATE "C";
+                         QUERY PLAN                          
+-------------------------------------------------------------
+ Sort
+   Sort Key: t1.c COLLATE "C"
+   ->  HashAggregate
+         Group Key: t1.c
+         ->  Hash Join
+               Hash Cond: (t1.c = t2.c)
+               ->  Append
+                     ->  Seq Scan on pagg_tab3_p2 t1_1
+                     ->  Seq Scan on pagg_tab3_p1 t1_2
+               ->  Hash
+                     ->  Append
+                           ->  Seq Scan on pagg_tab3_p2 t2_1
+                           ->  Seq Scan on pagg_tab3_p1 t2_2
+(13 rows)
+
+SELECT t1.c, count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c GROUP BY 1 ORDER BY t1.c COLLATE "C";
+ c | count 
+---+-------
+ A |   100
+ B |   100
+(2 rows)
+
+SET enable_partitionwise_join TO true;
+EXPLAIN (COSTS OFF)
+SELECT t1.c, count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c GROUP BY 1 ORDER BY t1.c COLLATE "C";
+                         QUERY PLAN                          
+-------------------------------------------------------------
+ Sort
+   Sort Key: t1.c COLLATE "C"
+   ->  HashAggregate
+         Group Key: t1.c
+         ->  Hash Join
+               Hash Cond: (t1.c = t2.c)
+               ->  Append
+                     ->  Seq Scan on pagg_tab3_p2 t1_1
+                     ->  Seq Scan on pagg_tab3_p1 t1_2
+               ->  Hash
+                     ->  Append
+                           ->  Seq Scan on pagg_tab3_p2 t2_1
+                           ->  Seq Scan on pagg_tab3_p1 t2_2
+(13 rows)
+
+SELECT t1.c, count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c GROUP BY 1 ORDER BY t1.c COLLATE "C";
+ c | count 
+---+-------
+ A |   100
+ B |   100
+(2 rows)
+
+-- OK when the join clause uses the same collation as the partition key.
+EXPLAIN (COSTS OFF)
+SELECT t1.c COLLATE "C", count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c COLLATE "C" GROUP BY t1.c COLLATE "C" ORDER BY t1.c COLLATE "C";
+                            QUERY PLAN                            
+------------------------------------------------------------------
+ Sort
+   Sort Key: ((t1.c)::text) COLLATE "C"
+   ->  Append
+         ->  HashAggregate
+               Group Key: (t1.c)::text
+               ->  Hash Join
+                     Hash Cond: ((t1.c)::text = (t2.c)::text)
+                     ->  Seq Scan on pagg_tab3_p2 t1
+                     ->  Hash
+                           ->  Seq Scan on pagg_tab3_p2 t2
+         ->  HashAggregate
+               Group Key: (t1_1.c)::text
+               ->  Hash Join
+                     Hash Cond: ((t1_1.c)::text = (t2_1.c)::text)
+                     ->  Seq Scan on pagg_tab3_p1 t1_1
+                     ->  Hash
+                           ->  Seq Scan on pagg_tab3_p1 t2_1
+(17 rows)
+
+SELECT t1.c COLLATE "C", count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c COLLATE "C" GROUP BY t1.c COLLATE "C" ORDER BY t1.c COLLATE "C";
+ c | count 
+---+-------
+ A |    25
+ B |    25
+ a |    25
+ b |    25
+(4 rows)
+
+SET enable_partitionwise_join TO false;
+EXPLAIN (COSTS OFF)
+SELECT t1.c COLLATE "C", count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c COLLATE "C" GROUP BY t1.c COLLATE "C" ORDER BY t1.c COLLATE "C";
+                         QUERY PLAN                          
+-------------------------------------------------------------
+ Sort
+   Sort Key: ((t1.c)::text) COLLATE "C"
+   ->  HashAggregate
+         Group Key: (t1.c)::text
+         ->  Hash Join
+               Hash Cond: ((t1.c)::text = (t2.c)::text)
+               ->  Append
+                     ->  Seq Scan on pagg_tab3_p2 t1_1
+                     ->  Seq Scan on pagg_tab3_p1 t1_2
+               ->  Hash
+                     ->  Append
+                           ->  Seq Scan on pagg_tab3_p2 t2_1
+                           ->  Seq Scan on pagg_tab3_p1 t2_2
+(13 rows)
+
+SELECT t1.c COLLATE "C", count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c COLLATE "C" GROUP BY t1.c COLLATE "C" ORDER BY t1.c COLLATE "C";
+ c | count 
+---+-------
+ A |    25
+ B |    25
+ a |    25
+ b |    25
+(4 rows)
+
 DROP TABLE pagg_tab3;
 RESET enable_partitionwise_aggregate;
 RESET max_parallel_workers_per_gather;

diff --git a/src/test/regress/sql/collate.icu.utf8.sql b/src/test/regress/sql/collate.icu.utf8.sql
index 9f7c06aa38ad1c3a9166fbefa6b20d1d51c4c71e..4eb1adf0287da598522aa3c99d718cbab1695b8d 100644 (file)
--- a/src/test/regress/sql/collate.icu.utf8.sql
+++ b/src/test/regress/sql/collate.icu.utf8.sql
@@ -828,6 +828,28 @@ EXPLAIN (COSTS OFF)
 SELECT c collate "C", count(c) FROM pagg_tab3 GROUP BY c collate "C" ORDER BY 1;
 SELECT c collate "C", count(c) FROM pagg_tab3 GROUP BY c collate "C" ORDER BY 1;
 
+-- Partitionwise join should not be allowed too when the collation used by the
+-- join keys doesn't match the partition key collation.
+SET enable_partitionwise_join TO false;
+EXPLAIN (COSTS OFF)
+SELECT t1.c, count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c GROUP BY 1 ORDER BY t1.c COLLATE "C";
+SELECT t1.c, count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c GROUP BY 1 ORDER BY t1.c COLLATE "C";
+
+SET enable_partitionwise_join TO true;
+EXPLAIN (COSTS OFF)
+SELECT t1.c, count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c GROUP BY 1 ORDER BY t1.c COLLATE "C";
+SELECT t1.c, count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c GROUP BY 1 ORDER BY t1.c COLLATE "C";
+
+-- OK when the join clause uses the same collation as the partition key.
+EXPLAIN (COSTS OFF)
+SELECT t1.c COLLATE "C", count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c COLLATE "C" GROUP BY t1.c COLLATE "C" ORDER BY t1.c COLLATE "C";
+SELECT t1.c COLLATE "C", count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c COLLATE "C" GROUP BY t1.c COLLATE "C" ORDER BY t1.c COLLATE "C";
+
+SET enable_partitionwise_join TO false;
+EXPLAIN (COSTS OFF)
+SELECT t1.c COLLATE "C", count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c COLLATE "C" GROUP BY t1.c COLLATE "C" ORDER BY t1.c COLLATE "C";
+SELECT t1.c COLLATE "C", count(t2.c) FROM pagg_tab3 t1 JOIN pagg_tab3 t2 ON t1.c = t2.c COLLATE "C" GROUP BY t1.c COLLATE "C" ORDER BY t1.c COLLATE "C";
+
 DROP TABLE pagg_tab3;
 
 RESET enable_partitionwise_aggregate;