Horton

Re: Add shared buffer hits to pg_stat_io

Andres Freund <andres@anarazel.de>

View thread View on postgr.es
From: Andres Freund <andres@anarazel.de>
To: Melanie Plageman <melanieplageman@gmail.com>
Cc: "Drouvot, Bertrand" <bertranddrouvot.pg@gmail.com>, Pg Hackers <pgsql-hackers@postgresql.org>, Maciek Sakrejda <m.sakrejda@gmail.com>, Justin Pryzby <pryzby@telsasoft.com>, smilingsamay@gmail.com, Kyotaro Horiguchi <horikyota.ntt@gmail.com>, Lukas Fittl <lukas@fittl.com>, Magnus Hagander <magnus@hagander.net>, Alvaro Herrera <alvherre@alvh.no-ip.org>
Date: 2023-03-08T19:23:42Z
Lists: pgsql-hackers 
On 2023-03-08 13:44:32 -0500, Melanie Plageman wrote:
> However, I am concerned that, while unlikely, this could be flakey.
> Something could happen to force all of those blocks out of shared
> buffers (even though they were just read in) before we hit them.

You could make the test query a simple nested loop self-join, that'll prevent
the page being evicted, because it'll still be pinned on the outer side, while
generating hits on the inner side.

Greetings,

Andres Freund

Commits

  1. Track shared buffer hits in pg_stat_io