upstream/postgresql
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2026-07-15 04:40:58 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix volatile function evaluation in eager aggregation

Browse source 
Pushing aggregates containing volatile functions below a join can
violate volatility semantics by changing the number of times the
function is executed.

Here we check the Aggref nodes in the targetlist and havingQual for
volatile functions and disable eager aggregation when such functions
are present.

Author: Richard Guo <guofenglinux@gmail.com>
Reviewed-by: Matheus Alcantara <matheusssilv97@gmail.com>
Discussion: https://postgr.es/m/CAMbWs48A53PY1Y4zoj7YhxPww9fO1hfnbdntKfA855zpXfVFRA@mail.gmail.com
This commit is contained in:
Richard Guo 2026-04-06 11:54:08 +09:00
parent bd94845e8c
commit 3a08a2a8b4
3 changed files with 63 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
src/backend/optimizer/plan/initsplan.c
View file

@ -810,6 +810,17 @@ create_agg_clause_infos(PlannerInfo *root)
Assert(aggref->aggorder == NIL);
Assert(aggref->aggdistinct == NIL);
/*
* We cannot push down aggregates that contain volatile functions.
* Doing so would change the number of times the function is
* evaluated.
*/
if (contain_volatile_functions((Node *) aggref))
{
eager_agg_applicable = false;
break;
}
/*
* If there are any securityQuals, do not try to apply eager
* aggregation if any non-leakproof aggregate functions are present.

38
src/test/regress/expected/eager_aggregate.out
View file

@ -428,6 +428,44 @@ GROUP BY t1.a ORDER BY t1.a;
RESET geqo;
RESET geqo_threshold;
-- Ensure eager aggregation is not applied because random() is a volatile
-- function
EXPLAIN (COSTS OFF)
SELECT t1.a, avg(t2.c + random())
FROM eager_agg_t1 t1
JOIN eager_agg_t2 t2 ON t1.b = t2.b
GROUP BY t1.a ORDER BY t1.a;
QUERY PLAN
-----------------------------------------------------
GroupAggregate
Group Key: t1.a
-> Sort
Sort Key: t1.a
-> Hash Join
Hash Cond: (t2.b = t1.b)
-> Seq Scan on eager_agg_t2 t2
-> Hash
-> Seq Scan on eager_agg_t1 t1
(9 rows)
EXPLAIN (COSTS OFF)
SELECT t1.a, avg(t2.c) FILTER (WHERE random() > 0.5)
FROM eager_agg_t1 t1
JOIN eager_agg_t2 t2 ON t1.b = t2.b
GROUP BY t1.a ORDER BY t1.a;
QUERY PLAN
-----------------------------------------------------
GroupAggregate
Group Key: t1.a
-> Sort
Sort Key: t1.a
-> Hash Join
Hash Cond: (t2.b = t1.b)
-> Seq Scan on eager_agg_t2 t2
-> Hash
-> Seq Scan on eager_agg_t1 t1
(9 rows)
DROP TABLE eager_agg_t1;
DROP TABLE eager_agg_t2;
DROP TABLE eager_agg_t3;

14
src/test/regress/sql/eager_aggregate.sql
View file

@ -163,6 +163,20 @@ GROUP BY t1.a ORDER BY t1.a;
RESET geqo;
RESET geqo_threshold;
-- Ensure eager aggregation is not applied because random() is a volatile
-- function
EXPLAIN (COSTS OFF)
SELECT t1.a, avg(t2.c + random())
FROM eager_agg_t1 t1
JOIN eager_agg_t2 t2 ON t1.b = t2.b
GROUP BY t1.a ORDER BY t1.a;
EXPLAIN (COSTS OFF)
SELECT t1.a, avg(t2.c) FILTER (WHERE random() > 0.5)
FROM eager_agg_t1 t1
JOIN eager_agg_t2 t2 ON t1.b = t2.b
GROUP BY t1.a ORDER BY t1.a;
DROP TABLE eager_agg_t1;
DROP TABLE eager_agg_t2;
DROP TABLE eager_agg_t3;