Re: Performance impact of lowering max_files_per_process

From: Thomas Kellerer <spam_eater(at)gmx(dot)net>
To: "pgsql-performance(at)postgresql(dot)org" <pgsql-performance(at)postgresql(dot)org>
Subject: Re: Performance impact of lowering max_files_per_process
Date: 2018-01-24 07:09:32
Message-ID: 88c11904-5821-1b3d-c616-caa1369d38c4@gmx.net
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-performance

Thomas Kellerer schrieb am 19.01.2018 um 17:48:
>
> I wonder what performance implications that has on a server with
> around 50-100 active connections (through pgBouncer).
>
> My understanding of the documentation is, that Postgres will work
> just fine if we lower the limit, it simply releases the cached file
> handles if the limit is reached. But I have no idea how expensive
> opening a file handle is in Linux.
>
> So assuming the sessions (and thus the queries) actually do need that
> many file handles, what kind of performance impact (if any) is to be
> expected by lowering that value for Postgres to e.g. 500?

I would be really interested in an answer.

In response to

Browse pgsql-performance by date

  From Date Subject
Next Message Michael Paquier 2018-01-24 07:15:59 Re: need help on memory allocation
Previous Message pavan95 2018-01-24 06:54:39 Re: 8.2 Autovacuum BUG ?