Re: Safe vm.overcommit_ratio for Large Multi-Instance PostgreSQL Fleet

From: Frédéric Yhuel <frederic(dot)yhuel(at)dalibo(dot)com>
To: Frits Hoogland <frits(dot)hoogland(at)gmail(dot)com>
Cc: Joe Conway <mail(at)joeconway(dot)com>, Priya V <mailme0216(at)gmail(dot)com>, pgsql-performance(at)lists(dot)postgresql(dot)org
Subject: Re: Safe vm.overcommit_ratio for Large Multi-Instance PostgreSQL Fleet
Date: 2025-08-19 17:40:10
Message-ID: 98eb084c-457d-4638-8f1f-d14f9eb2a634@dalibo.com
Views: Whole Thread | Raw Message | Download mbox | Resend email
Thread:
Lists: pgsql-performance

On 8/19/25 17:37, Frits Hoogland wrote:
> The specific issue I see in certain cases leading to unreasonable swap usage is Linux workingset detection kicking in

Do you have a way to highlight that precisely? I mean, can you prove
that it is Linux workingset detection that is causing swapping? I've
also encountered surprising cases where the swap fills up despite there
being plenty of available memory (lots of page cache). However these
cases were not associated with slowdowns or other problems. I only
became aware of them because a client was anxious about her swap usage.

In response to

Browse pgsql-performance by date

  From Date Subject
Next Message Ertan Küçükoglu 2025-08-26 08:21:52 Keeping some tables in cache
Previous Message Frits Hoogland 2025-08-19 15:37:10 Re: Safe vm.overcommit_ratio for Large Multi-Instance PostgreSQL Fleet