From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
---|---|
To: | pgsql-committers(at)lists(dot)postgresql(dot)org |
Subject: | pgsql: Remove one memoize test case added by commit 069d0ff02. |
Date: | 2024-08-30 16:42:23 |
Message-ID: | E1sk4hb-0029Eo-3Z@gemulon.postgresql.org |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-committers |
Remove one memoize test case added by commit 069d0ff02.
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
Branch
------
master
Details
-------
https://git.postgresql.org/pg/commitdiff/3409b4db631f5471696127494e57193350b87b41
Modified Files
--------------
src/test/regress/expected/memoize.out | 30 ------------------------------
src/test/regress/sql/memoize.sql | 11 -----------
2 files changed, 41 deletions(-)
From | Date | Subject | |
---|---|---|---|
Next Message | Peter Eisentraut | 2024-08-30 19:42:20 | Re: pgsql: Implement pg_wal_replay_wait() stored procedure |
Previous Message | Peter Eisentraut | 2024-08-30 08:04:37 | pgsql: Update list of acknowledgments in release notes |