Remove one memoize test case added by commit 069d0ff02.
Tom Lane <tgl@sss.pgh.pa.us>
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
Files
| Path | Change | +/− |
|---|---|---|
| src/test/regress/expected/memoize.out | modified | +0 −30 |
| src/test/regress/sql/memoize.sql | modified | +0 −11 |
Discussion
- Significant Execution Time Difference Between PG13.14 and PG16.4 for Query on information_schema Tables. 26 messages · 2024-08-26 → 2024-09-18