Fix handling of NULLs returned by aggregate combine functions.

anarazel · anarazel · commit c253b722f616 · 2017-11-23T17:15:36.000-08:00
When strict aggregate combine functions, used in multi-stage/parallel aggregation, returned NULL, we didn't check for that, invoking the combine function with NULL the next round, despite it being strict. The equivalent code invoking normal transition functions has a check for that situation, which did not get copied in a7de3dc. Fix the bug by adding the equivalent check. Based on a quick look I could not find any strict combine functions in core actually returning NULL, and it doesn't seem very likely external users have done so. So this isn't likely to have caused issues in practice. Add tests verifying transition / combine functions returning NULL is tested. Reported-By: Andres Freund Author: Andres Freund Discussion: https://postgr.es/m/20171121033642.7xvmjqrl4jdaaat3@alap3.anarazel.de Backpatch: 9.6, where parallel aggregation was introduced
diff --git a/src/backend/executor/nodeAgg.c b/src/backend/executor/nodeAgg.c
@@ -1064,6 +1064,17 @@ advance_combine_function(AggState *aggstate,
 			pergroupstate->noTransValue = false;
 			return;
 		}
+
+		if (pergroupstate->transValueIsNull)
+		{
+			/*
+			 * Don't call a strict function with NULL inputs.  Note it is
+			 * possible to get here despite the above tests, if the combinefn
+			 * is strict *and* returned a NULL on a prior cycle. If that
+			 * happens we will propagate the NULL all the way to the end.
+			 */
+			return;
+		}
 	}
 
 	/* We run the combine functions in per-input-tuple memory context */
diff --git a/src/test/regress/expected/aggregates.out b/src/test/regress/expected/aggregates.out
@@ -1974,3 +1974,76 @@ NOTICE:  sum_transfn called with 4
 (1 row)
 
 rollback;
+-- test that the aggregate transition logic correctly handles
+-- transition / combine functions returning NULL
+-- First test the case of a normal transition function returning NULL
+BEGIN;
+CREATE FUNCTION balkifnull(int8, int4)
+RETURNS int8
+STRICT
+LANGUAGE plpgsql AS $$
+BEGIN
+    IF $1 IS NULL THEN
+       RAISE 'erroneously called with NULL argument';
+    END IF;
+    RETURN NULL;
+END$$;
+CREATE AGGREGATE balk(
+    BASETYPE = int4,
+    SFUNC = balkifnull(int8, int4),
+    STYPE = int8,
+    "PARALLEL" = SAFE,
+    INITCOND = '0');
+SELECT balk(1) FROM tenk1;
+ balk 
+------
+     
+(1 row)
+
+ROLLBACK;
+-- Secondly test the case of a parallel aggregate combiner function
+-- returning NULL. For that use normal transition function, but a
+-- combiner function returning NULL.
+BEGIN ISOLATION LEVEL REPEATABLE READ;
+CREATE FUNCTION balkifnull(int8, int8)
+RETURNS int8
+PARALLEL SAFE
+STRICT
+LANGUAGE plpgsql AS $$
+BEGIN
+    IF $1 IS NULL THEN
+       RAISE 'erroneously called with NULL argument';
+    END IF;
+    RETURN NULL;
+END$$;
+CREATE AGGREGATE balk(
+    BASETYPE = int4,
+    SFUNC = int4_sum(int8, int4),
+    STYPE = int8,
+    COMBINEFUNC = balkifnull(int8, int8),
+    "PARALLEL" = SAFE,
+    INITCOND = '0'
+);
+-- force use of parallelism
+ALTER TABLE tenk1 set (parallel_workers = 4);
+SET LOCAL parallel_setup_cost=0;
+SET LOCAL max_parallel_workers_per_gather=4;
+SET LOCAL enable_indexscan = off;
+SET LOCAL enable_bitmapscan = off;
+EXPLAIN (COSTS OFF) SELECT balk(1) FROM tenk1;
+                  QUERY PLAN                  
+----------------------------------------------
+ Finalize Aggregate
+   ->  Gather
+         Workers Planned: 4
+         ->  Partial Aggregate
+               ->  Parallel Seq Scan on tenk1
+(5 rows)
+
+SELECT balk(1) FROM tenk1;
+ balk 
+------
+     
+(1 row)
+
+ROLLBACK;
diff --git a/src/test/regress/sql/aggregates.sql b/src/test/regress/sql/aggregates.sql
@@ -835,3 +835,68 @@ create aggregate my_half_sum(int4)
 select my_sum(one),my_half_sum(one) from (values(1),(2),(3),(4)) t(one);
 
 rollback;
+
+
+-- test that the aggregate transition logic correctly handles
+-- transition / combine functions returning NULL
+
+-- First test the case of a normal transition function returning NULL
+BEGIN;
+CREATE FUNCTION balkifnull(int8, int4)
+RETURNS int8
+STRICT
+LANGUAGE plpgsql AS $$
+BEGIN
+    IF $1 IS NULL THEN
+       RAISE 'erroneously called with NULL argument';
+    END IF;
+    RETURN NULL;
+END$$;
+
+CREATE AGGREGATE balk(
+    BASETYPE = int4,
+    SFUNC = balkifnull(int8, int4),
+    STYPE = int8,
+    "PARALLEL" = SAFE,
+    INITCOND = '0');
+
+SELECT balk(1) FROM tenk1;
+
+ROLLBACK;
+
+-- Secondly test the case of a parallel aggregate combiner function
+-- returning NULL. For that use normal transition function, but a
+-- combiner function returning NULL.
+BEGIN ISOLATION LEVEL REPEATABLE READ;
+CREATE FUNCTION balkifnull(int8, int8)
+RETURNS int8
+PARALLEL SAFE
+STRICT
+LANGUAGE plpgsql AS $$
+BEGIN
+    IF $1 IS NULL THEN
+       RAISE 'erroneously called with NULL argument';
+    END IF;
+    RETURN NULL;
+END$$;
+
+CREATE AGGREGATE balk(
+    BASETYPE = int4,
+    SFUNC = int4_sum(int8, int4),
+    STYPE = int8,
+    COMBINEFUNC = balkifnull(int8, int8),
+    "PARALLEL" = SAFE,
+    INITCOND = '0'
+);
+
+-- force use of parallelism
+ALTER TABLE tenk1 set (parallel_workers = 4);
+SET LOCAL parallel_setup_cost=0;
+SET LOCAL max_parallel_workers_per_gather=4;
+SET LOCAL enable_indexscan = off;
+SET LOCAL enable_bitmapscan = off;
+
+EXPLAIN (COSTS OFF) SELECT balk(1) FROM tenk1;
+SELECT balk(1) FROM tenk1;
+
+ROLLBACK;
