diff options
| author | David Rowley | 2025-10-08 23:38:33 +0000 |
|---|---|---|
| committer | David Rowley | 2025-10-08 23:38:33 +0000 |
| commit | a5a68dd6d5159626360f75ffde96eca879e6cc30 (patch) | |
| tree | b0e0d021cb79896e952b5fcf0c74e90db6b42d35 /src/test/regress/sql/window.sql | |
| parent | 5e89985928795f243dc287210c2aa016dfd00bfe (diff) | |
Make truncate_useless_pathkeys() consider WindowFuncs
truncate_useless_pathkeys() seems to have neglected to account for
PathKeys that might be useful for WindowClause evaluation. Modify it so
that it properly accounts for that.
Making this work required adjusting two things:
1. Change from checking query_pathkeys to check sort_pathkeys instead.
2. Add explicit check for window_pathkeys
For #1, query_pathkeys gets set in standard_qp_callback() according to the
sort order requirements for the first operation to be applied after the
join planner is finished, so this changes depending on which upper
planner operations a particular query needs. If the query has window
functions and no GROUP BY, then query_pathkeys gets set to
window_pathkeys. Before this change, this meant PathKeys useful for the
ORDER BY were not accounted for in queries with window functions.
Because of #1, #2 is now required so that we explicitly check to ensure
we don't truncate away PathKeys useful for window functions.
Author: David Rowley <[email protected]>
Discussion: https://postgr.es/m/CAApHDvrj3HTKmXoLMbUjTO=_MNMxM=cnuCSyBKidAVibmYPnrg@mail.gmail.com
Diffstat (limited to 'src/test/regress/sql/window.sql')
| -rw-r--r-- | src/test/regress/sql/window.sql | 13 |
1 files changed, 13 insertions, 0 deletions
diff --git a/src/test/regress/sql/window.sql b/src/test/regress/sql/window.sql index 85fc621c8db..37d837a2f66 100644 --- a/src/test/regress/sql/window.sql +++ b/src/test/regress/sql/window.sql @@ -1522,6 +1522,19 @@ SELECT * FROM FROM empsalary) emp WHERE first_emp = 1 OR last_emp = 1; +CREATE INDEX empsalary_salary_empno_idx ON empsalary (salary, empno); + +SET enable_seqscan = 0; + +-- Ensure no sorting is done and that the IndexScan maintains all pathkeys +-- useful for the final sort order. +EXPLAIN (COSTS OFF) +SELECT salary, empno, row_number() OVER (ORDER BY salary) rn +FROM empsalary +ORDER BY salary, empno; + +RESET enable_seqscan; + -- cleanup DROP TABLE empsalary; |
