1berry/postgres
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Remove one memoize test case added by commit 069d0ff02.

Browse Source 
This test case turns out to depend on the assumption that a non-Var
subquery output that's underneath an outer join will always get
wrapped in a PlaceHolderVar.  But that behavior causes performance
regressions in some cases compared to what happened before v16.
The next commit will avoid inserting a PHV in the same cases where
pre-v16 did, and that causes get_memoized_path to not detect that
a memoize plan could be used.

Commit this separately, in hopes that we can restore the test after
making get_memoized_path smarter.  (It's failing to find memoize
plans in adjacent cases where no PHV was ever inserted, so there
is definitely room for improvement there.)

Discussion: https://postgr.es/m/CAG1ps1xvnTZceKK24OUfMKLPvDP2vjT-d+F2AOCWbw_v3KeEgg@mail.gmail.com
This commit is contained in:
Tom Lane 2024-08-30 12:22:31 -04:00
parent c39afc38cf
commit 3409b4db63
2 changed files with 0 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
src/test/regress/expected/memoize.out
View File

@ -160,36 +160,6 @@ WHERE s.c1 = s.c2 AND t1.unique1 < 1000;
1000 | 9.5000000000000000
(1 row)
-- Try with LATERAL references within PlaceHolderVars
SELECT explain_memoize('
SELECT COUNT(*), AVG(t1.twenty) FROM tenk1 t1 LEFT JOIN
LATERAL (SELECT t1.two+t2.two AS c1, t2.unique1 AS c2 FROM tenk1 t2) s ON TRUE
WHERE s.c1 = s.c2 AND t1.unique1 < 1000;', false);
explain_memoize
--------------------------------------------------------------------------------------
Aggregate (actual rows=1 loops=N)
-> Nested Loop (actual rows=1000 loops=N)
-> Seq Scan on tenk1 t1 (actual rows=1000 loops=N)
Filter: (unique1 < 1000)
Rows Removed by Filter: 9000
-> Memoize (actual rows=1 loops=N)
Cache Key: t1.two
Cache Mode: binary
Hits: 998 Misses: 2 Evictions: Zero Overflows: 0 Memory Usage: NkB
-> Seq Scan on tenk1 t2 (actual rows=1 loops=N)
Filter: ((t1.two + two) = unique1)
Rows Removed by Filter: 9999
(12 rows)
-- And check we get the expected results.
SELECT COUNT(*), AVG(t1.twenty) FROM tenk1 t1 LEFT JOIN
LATERAL (SELECT t1.two+t2.two AS c1, t2.unique1 AS c2 FROM tenk1 t2) s ON TRUE
WHERE s.c1 = s.c2 AND t1.unique1 < 1000;
count | avg
-------+--------------------
1000 | 9.0000000000000000
(1 row)
-- Ensure we do not omit the cache keys from PlaceHolderVars
SELECT explain_memoize('
SELECT COUNT(*), AVG(t1.twenty) FROM tenk1 t1 LEFT JOIN

11
src/test/regress/sql/memoize.sql
View File

@ -85,17 +85,6 @@ SELECT COUNT(*), AVG(t1.twenty) FROM tenk1 t1 LEFT JOIN
LATERAL (SELECT t1.two+1 AS c1, t2.unique1 AS c2 FROM tenk1 t2) s ON TRUE
WHERE s.c1 = s.c2 AND t1.unique1 < 1000;
-- Try with LATERAL references within PlaceHolderVars
SELECT explain_memoize('
SELECT COUNT(*), AVG(t1.twenty) FROM tenk1 t1 LEFT JOIN
LATERAL (SELECT t1.two+t2.two AS c1, t2.unique1 AS c2 FROM tenk1 t2) s ON TRUE
WHERE s.c1 = s.c2 AND t1.unique1 < 1000;', false);
-- And check we get the expected results.
SELECT COUNT(*), AVG(t1.twenty) FROM tenk1 t1 LEFT JOIN
LATERAL (SELECT t1.two+t2.two AS c1, t2.unique1 AS c2 FROM tenk1 t2) s ON TRUE
WHERE s.c1 = s.c2 AND t1.unique1 < 1000;
-- Ensure we do not omit the cache keys from PlaceHolderVars
SELECT explain_memoize('
SELECT COUNT(*), AVG(t1.twenty) FROM tenk1 t1 LEFT JOIN