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_v3ke...@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(-)
