Thread: pgsql: Temporary patch to help debug pg_walsummary test failures.
Temporary patch to help debug pg_walsummary test failures. The tests in 002_blocks.pl are failing in the buildfarm from time to time, but we don't know how to reproduce the failure elsewhere. The most obvious explanation seems to be the unexpected disappearance of a WAL summary file, so bump up the logging level in RemoveWalSummaryIfOlderThan to try to help us spot such problems, and print the cutoff time in addition to the removed filename. Also adjust 002_blocks.pl to dump out a directory listing of the relevant directory at various points. This patch should be reverted once we sort out what's happening here. Patch by me, reviewed by Nathan Bossart, who also reported the issue. Discussion: http://postgr.es/m/20240124170846.GA2643050@nathanxps13 Branch ------ master Details ------- https://git.postgresql.org/pg/commitdiff/5ddf9973477729cf161b4ad0a1efd52f4fea9c88 Modified Files -------------- src/backend/backup/walsummary.c | 7 +++++++ src/bin/pg_walsummary/t/002_blocks.pl | 14 ++++++++++++++ 2 files changed, 21 insertions(+)
On Fri, Jan 26, 2024 at 06:37:17PM +0000, Robert Haas wrote: > Temporary patch to help debug pg_walsummary test failures. > > This patch should be reverted once we sort out what's happening here. Not sure if that's worth fixing if this should be gone at some point, but koel has been complaining on this one: https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=koel&dt=2024-01-28%2016%3A19%3A03 -- Michael
Attachment
On Mon, 29 Jan 2024 at 12:40, Michael Paquier <michael@paquier.xyz> wrote: > Not sure if that's worth fixing if this should be gone at some point, > but koel has been complaining on this one: > https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=koel&dt=2024-01-28%2016%3A19%3A03 I think we should as we don't know how long it'll be before this gets reverted. In the meantime, having a buildfarm member red is annoying. David
On Tue, Jan 30, 2024 at 10:06 PM David Rowley <dgrowleyml@gmail.com> wrote: > On Mon, 29 Jan 2024 at 12:40, Michael Paquier <michael@paquier.xyz> wrote: > > Not sure if that's worth fixing if this should be gone at some point, > > but koel has been complaining on this one: > > https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=koel&dt=2024-01-28%2016%3A19%3A03 > > I think we should as we don't know how long it'll be before this gets > reverted. In the meantime, having a buildfarm member red is annoying. I included a fix for this in ea18eb7d625573dc369df619f7ff3b9e60e47531. Apologies for the inconvenience. -- Robert Haas EDB: http://www.enterprisedb.com