pgsql: Remove one memoize test case added by commit 069d0ff02.

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(-)

Browse pgsql-committers by date

  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