Horton

Re: MultiXact\SLRU buffers configuration

Dilip Kumar <dilipbalaut@gmail.com>

View thread View on postgr.es
From: Dilip Kumar <dilipbalaut@gmail.com>
To: Andrey Borodin <amborodin86@gmail.com>
Cc: vignesh C <vignesh21@gmail.com>, i.lazarev@postgrespro.ru, Andrey Borodin <x4mmm@yandex-team.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 <pgsql-hackers@postgresql.org>
Date: 2023-01-11T05:58:06Z
Lists: pgsql-hackers 
On Mon, Jan 9, 2023 at 9:49 AM Andrey Borodin <amborodin86@gmail.com> wrote:
>
> On Tue, Jan 3, 2023 at 5:02 AM vignesh C <vignesh21@gmail.com> wrote:
> > does not apply on top of HEAD as in [1], please post a rebased patch:
> >
> Thanks! Here's the rebase.

I was looking into this patch, it seems like three different
optimizations are squeezed in a single patch
1) dividing buffer space in banks to reduce the seq search cost 2) guc
parameter for buffer size scale 3) some of the buffer size values are
modified compared to what it is on the head.  I think these are 3
patches which should be independently committable.

While looking into the first idea of dividing the buffer space in
banks, I see that it will speed up finding the buffers but OTOH while
searching the victim buffer it will actually can hurt the performance
the slru pages which are frequently accessed are not evenly
distributed across the banks.  So imagine the cases where we have some
banks with a lot of empty slots and other banks from which we
frequently have to evict out the pages in order to get the new pages
in.

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com

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.