Re: pgsql: Improve BRIN minmax-multi opclass test coverage

2023-11-22 Thread Peter Eisentraut
On 22.08.23 08:43, Peter Eisentraut wrote: These new tests introduced a few new calls of the md5() function.  This should be avoided (see commit 208bf364a9).  You can replace these easily with the fipshash() function instead, but I think you then also need to change some of the constants in

Re: pgsql: Improve BRIN minmax-multi opclass test coverage

2023-08-22 Thread Peter Eisentraut
These new tests introduced a few new calls of the md5() function. This should be avoided (see commit 208bf364a9). You can replace these easily with the fipshash() function instead, but I think you then also need to change some of the constants in the tests. Could you look at this again?

pgsql: Improve BRIN minmax-multi opclass test coverage

2023-07-02 Thread Tomas Vondra
Improve BRIN minmax-multi opclass test coverage Per the code coverage report, the existing regression tests did not exercice some a couple important BRIN minmax-multi code paths. - The tests focused on testing planning with a range of scan key strategies, but not the execution. Fixed by adding