Horton

Re: heavily contended lwlocks with long wait queues scale badly

Robert Haas <robertmhaas@gmail.com>

View thread View on postgr.es
From: Robert Haas <robertmhaas@gmail.com>
To: Andres Freund <andres@anarazel.de>
Cc: pgsql-hackers@postgresql.org, Thomas Munro <thomas.munro@gmail.com>, Yura Sokolov <y.sokolov@postgrespro.ru>
Date: 2022-10-31T18:40:28Z
Lists: pgsql-hackers 
On Thu, Oct 27, 2022 at 12:59 PM Andres Freund <andres@anarazel.de> wrote:
> After pulling my
> hair out for quite a while to try to understand that behaviour, I figured out
> that it's just a side-effect of *removing* some other contention.

I've seen this kind of pattern on multiple occasions. I don't know if
they were all caused by this, or what, but I certainly like the idea
of making it better.

-- 
Robert Haas
EDB: http://www.enterprisedb.com

Commits

  1. lwlock: Fix quadratic behavior with very long wait lists