Horton

Re: MultiXact\SLRU buffers configuration

x4mmm@yandex-team.ru

View thread View on postgr.es
From: "Andrey M. Borodin" <x4mmm@yandex-team.ru>
To: Alvaro Herrera <alvherre@alvh.no-ip.org>
Cc: vignesh C <vignesh21@gmail.com>, Andrew Borodin <amborodin86@gmail.com>, i.lazarev@postgrespro.ru, Yura Sokolov <y.sokolov@postgrespro.ru>, Andres Freund <andres@anarazel.de>, Thomas Munro <thomas.munro@gmail.com>, Gilles Darold <gilles@darold.net>, Tomas Vondra <tomas.vondra@enterprisedb.com>, Tomas Vondra <tomas.vondra@2ndquadrant.com>, Alexander Korotkov <aekorotkov@gmail.com>, Anastasia Lubennikova <a.lubennikova@postgrespro.ru>, Daniel Gustafsson <daniel@yesql.se>, Kyotaro Horiguchi <horikyota.ntt@gmail.com>, pgsql-hackers mailing list <pgsql-hackers@postgresql.org>
Date: 2024-02-03T17:32:45Z
Lists: pgsql-hackers

Attachments


> On 28 Jan 2024, at 23:17, Andrey M. Borodin <x4mmm@yandex-team.ru> wrote:
> 
> 
>> Perhaps a test to make the code reach the usleep(1000) can be written
>> using injection points (49cd2b93d7db)?
> 
> I've tried to prototype something like that. But interesting point between GetNewMultiXactId() and RecordNewMultiXact() is a critical section, and we cannot have injection points in critical sections...
> Also, to implement such a test we need "wait" type of injection points, see step 2 in attachment. With this type of injection points I can stop a backend amidst entering information about new MultiXact.

Here's the test draft. This test reliably reproduces sleep on CV when waiting next multixact to be filled into "members" SLRU.
Cost of having this test:
1. We need a new injection point type "wait" (in addition to "error" and "notice"). It cannot be avoided, because we need to sync at least 3 processed to observe condition we want.
2. We need new way to declare injection point that can happen inside critical section. I've called it "prepared injection point".

Complexity of having this test is higher than complexity of CV-sleep patch itself. Do we want it? If so I can produce cleaner version, currently all multixact tests are int injection_points test module.


Best regards, Andrey Borodin.

Commits

  1. Rework new SLRU test with injection points

  2. injection_point: Add injection_points.stats

  3. injection_points: Add initialization of shmem state when loading module

  4. Add injection-point test for new multixact CV usage

  5. Use conditional variable to wait for next MultiXact offset

  6. Improve performance of subsystems on top of SLRU

  7. Adjust VACUUM hastup LP_REDIRECT comments.

  8. Test replay of regression tests, attempt II.