diff options
| author | Tom Lane <tgl@sss.pgh.pa.us> | 2024-08-30 12:22:31 -0400 |
|---|---|---|
| committer | Tom Lane <tgl@sss.pgh.pa.us> | 2024-08-30 12:22:31 -0400 |
| commit | 3409b4db631f5471696127494e57193350b87b41 (patch) | |
| tree | 4d7f445af1de04e2dc2c3fd84adbe294ead1d581 /src/backend/utils/adt/misc.c | |
| parent | c39afc38cfec7c34b883095062a89a63b221521a (diff) | |
| download | postgresql-3409b4db631f5471696127494e57193350b87b41.tar.gz postgresql-3409b4db631f5471696127494e57193350b87b41.zip | |
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
Diffstat (limited to 'src/backend/utils/adt/misc.c')
0 files changed, 0 insertions, 0 deletions