Postgres Pro
Downloads
Home   >   mailing lists

Re: [PERFORM] [performance] fast reads on a busy server - Mailing list pgsql-cluster-hackers

From Ants Aasma
Subject Re: [PERFORM] [performance] fast reads on a busy server
Date
Msg-id CA+CSw_sryMFRS45ptRq4TYNCREgDKpSS+cyh-f_s-VpiYOLwBA@mail.gmail.com
Whole thread Raw
In response to Re: [performance] fast reads on a busy server  (Willy-Bas Loos <willybas@gmail.com>)
Responses Re: [PERFORM] [performance] fast reads on a busy server  (Willy-Bas Loos <willybas@gmail.com>)
List pgsql-cluster-hackers
Tree view

On Jun 27, 2012 2:29 PM, "Willy-Bas Loos" <willybas@gmail.com> wrote:
> Should i use a larger shared_buffers for the other cluster(s) too, so that i bypass the inefficient OS file-cache?

Once the in-memory cluster has filled its shared buffers, the pages go cold for the OS cache and get replaced with pages of other clusters that are actually referenced.

Ants Aasma

pgsql-cluster-hackers by date:

Previous
From: Willy-Bas Loos
Date:
Subject: Re: [performance] fast reads on a busy server
Next
From: Willy-Bas Loos
Date:
Subject: Re: [PERFORM] [performance] fast reads on a busy server