Disable parallel plans for RIGHT_SEMI joins

RIGHT_SEMI joins rely on the HEAP_TUPLE_HAS_MATCH flag to guarantee
that only the first match for each inner tuple is considered.
However, in a parallel hash join, the inner relation is stored in a
shared global hash table that can be probed by multiple workers
concurrently.  This allows different workers to inspect and set the
match flags of the same inner tuples at the same time.

If two workers probe the same inner tuple concurrently, both may see
the match flag as unset and emit the same tuple, leading to duplicate
output rows and violating RIGHT_SEMI join semantics.

For now, we disable parallel plans for RIGHT_SEMI joins.  In the long
term, it may be possible to support parallel execution by performing
atomic operations on the match flag, for example using a CAS or
similar mechanism.

Backpatch to v18, where RIGHT_SEMI join was introduced.

Bug: #19094
Reported-by: Lori Corbani <Lori.Corbani@jax.org>
Diagnosed-by: Tom Lane <tgl@sss.pgh.pa.us>
Author: Richard Guo <guofenglinux@gmail.com>
Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us>
Discussion: https://postgr.es/m/19094-6ed410eb5b256abd@postgresql.org
Backpatch-through: 18

diff --git a/src/backend/optimizer/path/joinpath.c b/src/backend/optimizer/path/joinpath.c
index 7aa8f5d799cac8652736004a1b09956b30b05ef0..af5aa8aea845b4ee768b10f527ebe13bfbbb52e9 100644 (file)
--- a/src/backend/optimizer/path/joinpath.c
+++ b/src/backend/optimizer/path/joinpath.c
@@ -2399,13 +2399,25 @@ hash_inner_and_outer(PlannerInfo *root,
 
        /*
         * If the joinrel is parallel-safe, we may be able to consider a
-        * partial hash join.  However, we can't handle JOIN_UNIQUE_OUTER,
-        * because the outer path will be partial, and therefore we won't be
-        * able to properly guarantee uniqueness.  Also, the resulting path
-        * must not be parameterized.
+        * partial hash join.
+        *
+        * However, we can't handle JOIN_UNIQUE_OUTER, because the outer path
+        * will be partial, and therefore we won't be able to properly
+        * guarantee uniqueness.
+        *
+        * Similarly, we can't handle JOIN_RIGHT_SEMI, because the hash table
+        * is either a shared hash table or a private hash table per backend.
+        * In the shared case, there is no concurrency protection for the
+        * match flags, so multiple workers could inspect and set the flags
+        * concurrently, potentially producing incorrect results.  In the
+        * private case, each worker has its own copy of the hash table, so no
+        * single process has all the match flags.
+        *
+        * Also, the resulting path must not be parameterized.
         */
        if (joinrel->consider_parallel &&
            save_jointype != JOIN_UNIQUE_OUTER &&
+           save_jointype != JOIN_RIGHT_SEMI &&
            outerrel->partial_pathlist != NIL &&
            bms_is_empty(joinrel->lateral_relids))
        {
@@ -2439,13 +2451,12 @@ hash_inner_and_outer(PlannerInfo *root,
             * total inner path will also be parallel-safe, but if not, we'll
             * have to search for the cheapest safe, unparameterized inner
             * path.  If doing JOIN_UNIQUE_INNER, we can't use any alternative
-            * inner path.  If full, right, right-semi or right-anti join, we
-            * can't use parallelism (building the hash table in each backend)
-            * because no one process has all the match bits.
+            * inner path.  If full, right, or right-anti join, we can't use
+            * parallelism (building the hash table in each backend) because
+            * no one process has all the match bits.
             */
            if (save_jointype == JOIN_FULL ||
                save_jointype == JOIN_RIGHT ||
-               save_jointype == JOIN_RIGHT_SEMI ||
                save_jointype == JOIN_RIGHT_ANTI)
                cheapest_safe_inner = NULL;
            else if (cheapest_total_inner->parallel_safe)

diff --git a/src/test/regress/expected/join.out b/src/test/regress/expected/join.out
index f3de6971c2eced1eadacf2733bfbd2c9b41667cc..6738ba316e684b4a44c62d80bf2abf9d3fb667ea 100644 (file)
--- a/src/test/regress/expected/join.out
+++ b/src/test/regress/expected/join.out
@@ -3075,6 +3075,33 @@ select * from tbl_rs t1 join
  3 | 3 | 4 | 4
 (6 rows)
 
+--
+-- regression test for bug with parallel-hash-right-semi join
+--
+begin;
+-- encourage use of parallel plans
+set local parallel_setup_cost=0;
+set local parallel_tuple_cost=0;
+set local min_parallel_table_scan_size=0;
+set local max_parallel_workers_per_gather=4;
+-- ensure we don't get parallel hash right semi join
+explain (costs off)
+select * from tenk1 t1
+where exists (select 1 from tenk1 t2 where fivethous = t1.fivethous)
+and t1.fivethous < 5;
+                    QUERY PLAN                    
+--------------------------------------------------
+ Gather
+   Workers Planned: 4
+   ->  Parallel Hash Semi Join
+         Hash Cond: (t1.fivethous = t2.fivethous)
+         ->  Parallel Seq Scan on tenk1 t1
+               Filter: (fivethous < 5)
+         ->  Parallel Hash
+               ->  Parallel Seq Scan on tenk1 t2
+(8 rows)
+
+rollback;
 --
 -- regression test for bug #13908 (hash join with skew tuples & nbatch increase)
 --

diff --git a/src/test/regress/sql/join.sql b/src/test/regress/sql/join.sql
index 3533fd3600c8aad6f9bb4a0c8560b10bb1cda34d..87865041e34edb08f64465f6b753a2e1a8b969bd 100644 (file)
--- a/src/test/regress/sql/join.sql
+++ b/src/test/regress/sql/join.sql
@@ -759,6 +759,26 @@ select * from tbl_rs t1 join
             (select t1.a+t3.a from tbl_rs t3) and t2.a < 5)
   on true;
 
+--
+-- regression test for bug with parallel-hash-right-semi join
+--
+
+begin;
+
+-- encourage use of parallel plans
+set local parallel_setup_cost=0;
+set local parallel_tuple_cost=0;
+set local min_parallel_table_scan_size=0;
+set local max_parallel_workers_per_gather=4;
+
+-- ensure we don't get parallel hash right semi join
+explain (costs off)
+select * from tenk1 t1
+where exists (select 1 from tenk1 t2 where fivethous = t1.fivethous)
+and t1.fivethous < 5;
+
+rollback;
+
 --
 -- regression test for bug #13908 (hash join with skew tuples & nbatch increase)
 --