upstream/postgresql
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2026-04-15 22:10:45 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

pg_plan_advice: Handle non-repeatable TABLESAMPLE scans.

Browse source 
When a tablesample routine says that it is not repeatable across
scans, set_tablesample_rel_pathlist will (usually) materialize it,
confusing pg_plan_advice's plan walker machinery. To fix, update that
machinery to view such Material paths as essentially an extension of
the underlying scan.

Reported-by: Alexander Lakhin <exclusion@gmail.com>
Discussion: http://postgr.es/m/CA+TgmobOOmmXSJz3e+cjTY-bA1+W0dqVDqzxUBEvGtW62whYGg@mail.gmail.com
This commit is contained in:
Robert Haas 2026-04-13 08:46:25 -04:00
parent a8b61c23c5
commit 3311ccc3d2
7 changed files with 101 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
contrib/pg_plan_advice/Makefile
View file

@ -22,6 +22,8 @@ PGFILEDESC = "pg_plan_advice - help the planner get the right plan"
REGRESS = gather join_order join_strategy partitionwise prepared \
scan semijoin syntax
EXTRA_INSTALL = contrib/tsm_system_time
EXTRA_CLEAN = pgpa_parser.h pgpa_parser.c pgpa_scanner.c
ifdef USE_PGXS

38
contrib/pg_plan_advice/expected/scan.out
View file

@ -770,3 +770,41 @@ SELECT * FROM (SELECT * FROM scan_table s WHERE a = 1 OFFSET 0);
(7 rows)
COMMIT;
-- Test a non-repeatable tablesample method with a scan-level Materialize.
CREATE EXTENSION tsm_system_time;
CREATE TABLE scan_tsm (i int);
EXPLAIN (COSTS OFF, PLAN_ADVICE)
SELECT 1 FROM (SELECT i FROM scan_tsm TABLESAMPLE system_time (1000)),
LATERAL (SELECT i LIMIT 1);
QUERY PLAN
----------------------------------------------------------------------
Nested Loop
-> Materialize
-> Sample Scan on scan_tsm
Sampling: system_time ('1000'::double precision)
-> Limit
-> Result
Generated Plan Advice:
JOIN_ORDER(scan_tsm unnamed_subquery#2)
NESTED_LOOP_PLAIN(unnamed_subquery#2)
NO_GATHER(unnamed_subquery#2 scan_tsm "*RESULT*"@unnamed_subquery)
(10 rows)
-- Same, but with the scan-level Materialize on the inner side of a join.
EXPLAIN (COSTS OFF, PLAN_ADVICE)
SELECT 1 FROM (SELECT 1 AS x LIMIT 1),
LATERAL (SELECT x FROM scan_tsm TABLESAMPLE system_time (1000));
QUERY PLAN
--------------------------------------------------------------------
Nested Loop
-> Limit
-> Result
-> Materialize
-> Sample Scan on scan_tsm
Sampling: system_time ('1000'::double precision)
Generated Plan Advice:
JOIN_ORDER(unnamed_subquery scan_tsm)
NESTED_LOOP_PLAIN(scan_tsm)
NO_GATHER(unnamed_subquery scan_tsm "*RESULT*"@unnamed_subquery)
(10 rows)

12
contrib/pg_plan_advice/pgpa_join.c
View file

@ -363,9 +363,11 @@ pgpa_decompose_join(pgpa_plan_walker_context *walker, Plan *plan,
/*
* The planner may have chosen to place a Material node on the
* inner side of the MergeJoin; if this is present, we record it
* as part of the join strategy.
* as part of the join strategy. (However, scan-level Materialize
* nodes are an exception.)
*/
if (elidedinner == NULL && IsA(innerplan, Material))
if (elidedinner == NULL && IsA(innerplan, Material) &&
!pgpa_is_scan_level_materialize(innerplan))
{
elidedinner = pgpa_descend_node(pstmt, &innerplan);
strategy = JSTRAT_MERGE_JOIN_MATERIALIZE;
@ -390,9 +392,11 @@ pgpa_decompose_join(pgpa_plan_walker_context *walker, Plan *plan,
/*
* The planner may have chosen to place a Material or Memoize node
* on the inner side of the NestLoop; if this is present, we
* record it as part of the join strategy.
* record it as part of the join strategy. (However, scan-level
* Materialize nodes are an exception.)
*/
if (elidedinner == NULL && IsA(innerplan, Material))
if (elidedinner == NULL && IsA(innerplan, Material) &&
!pgpa_is_scan_level_materialize(innerplan))
{
elidedinner = pgpa_descend_node(pstmt, &innerplan);
strategy = JSTRAT_NESTED_LOOP_MATERIALIZE;

11
contrib/pg_plan_advice/pgpa_scan.c
View file

@ -120,6 +120,17 @@ pgpa_build_scan(pgpa_plan_walker_context *walker, Plan *plan,
break;
}
}
else if (pgpa_is_scan_level_materialize(plan))
{
/*
* Non-repeatable tablesample methods can be wrapped in a Materialize
* node that must be treated as part of the scan itself. See
* set_tablesample_rel_pathlist().
*/
rti = pgpa_scanrelid(plan->lefttree);
relids = bms_make_singleton(rti);
strategy = PGPA_SCAN_ORDINARY;
}
else if ((relids = pgpa_relids(plan)) != NULL)
{
switch (nodeTag(plan))

29
contrib/pg_plan_advice/pgpa_walker.c
View file

@ -16,6 +16,7 @@
#include "pgpa_scan.h"
#include "pgpa_walker.h"
#include "access/tsmapi.h"
#include "nodes/plannodes.h"
#include "parser/parsetree.h"
#include "utils/lsyscache.h"
@ -609,6 +610,34 @@ pgpa_scanrelid(Plan *plan)
}
}
/*
* Check whether a plan node is a Material node that should be treated as
* a scan. Currently, this only happens when set_tablesample_rel_pathlist
* inserts a Material node to protect a SampleScan that uses a non-repeatable
* tablesample method.
*
* (Most Material nodes we're likely to encounter are actually part of the
* join strategy: nested loops and merge joins can choose to materialize the
* inner sides of the join. The cases identified here are the rare
* exceptions.)
*/
bool
pgpa_is_scan_level_materialize(Plan *plan)
{
Plan *child;
SampleScan *sscan;
TsmRoutine *tsm;
if (!IsA(plan, Material))
return false;
child = plan->lefttree;
if (child == NULL || !IsA(child, SampleScan))
return false;
sscan = (SampleScan *) child;
tsm = GetTsmRoutine(sscan->tablesample->tsmhandler);
return !tsm->repeatable_across_scans;
}
/*
* Construct a new Bitmapset containing non-RTE_JOIN members of 'relids'.
*/

1
contrib/pg_plan_advice/pgpa_walker.h
View file

@ -114,6 +114,7 @@ extern void pgpa_add_future_feature(pgpa_plan_walker_context *walker,
extern ElidedNode *pgpa_last_elided_node(PlannedStmt *pstmt, Plan *plan);
extern Bitmapset *pgpa_relids(Plan *plan);
extern Index pgpa_scanrelid(Plan *plan);
extern bool pgpa_is_scan_level_materialize(Plan *plan);
extern Bitmapset *pgpa_filter_out_join_relids(Bitmapset *relids, List *rtable);
extern bool pgpa_walker_would_advise(pgpa_plan_walker_context *walker,

12
contrib/pg_plan_advice/sql/scan.sql
View file

@ -196,3 +196,15 @@ SELECT * FROM (SELECT * FROM scan_table s WHERE a = 1 OFFSET 0) x;
EXPLAIN (COSTS OFF, PLAN_ADVICE)
SELECT * FROM (SELECT * FROM scan_table s WHERE a = 1 OFFSET 0);
COMMIT;
-- Test a non-repeatable tablesample method with a scan-level Materialize.
CREATE EXTENSION tsm_system_time;
CREATE TABLE scan_tsm (i int);
EXPLAIN (COSTS OFF, PLAN_ADVICE)
SELECT 1 FROM (SELECT i FROM scan_tsm TABLESAMPLE system_time (1000)),
LATERAL (SELECT i LIMIT 1);
-- Same, but with the scan-level Materialize on the inner side of a join.
EXPLAIN (COSTS OFF, PLAN_ADVICE)
SELECT 1 FROM (SELECT 1 AS x LIMIT 1),
LATERAL (SELECT x FROM scan_tsm TABLESAMPLE system_time (1000));