From: Alvaro Herrera <alvherre@surnet.cl>
To: Donald Courtney <Donald.Courtney@Sun.COM>
Cc: Tom Arthurs <tarthurs@jobflash.com>
Cc: pgsql-performance@postgresql.org
Subject: Re: Postgresql on an AMD64 machine
Date: Tue, 7 Jun 2005 16:27:55 -0400
Message-ID: <20050607202755.GA28361@surnet.cl> (raw)
In-Reply-To: <42A6014C.30108@sun.com>
References: <1118080420.1644.23.camel@penguin1>
<b918cf3d05060613593a73a18a@mail.gmail.com>
<42A5F7B6.20502@sun.com>
<42A5FB70.8090807@jobflash.com>
<42A6014C.30108@sun.com>
On Tue, Jun 07, 2005 at 04:19:24PM -0400, Donald Courtney wrote:
> The system has 8 CPUs w/ 32 GB - I'm hoping to see some benefit to large
> caches -
> Am I missing something key with postgreSQL?
Yeah. Postgres makes extensive use of the kernel's cache (or, more
precisely, assumes that the kernel is doing some caching on its own).
So the bulk of the memory should be left to the kernel to handle, and
shared_buffers be set relatively slow.
This was the standard wisdom with releases previous to 8.0; I'm not sure
if anyone confirmed to still hold after the buffer manager changes in
8.0 and later in 8.1 -- we saw extensive redesign of the bufmgr on both,
so the behavior may have changed. If you wanna test, I'm sure lots of
people here will be interested in the results.
--
Alvaro Herrera (<alvherre[a]surnet.cl>)
"This is a foot just waiting to be shot" (Andrew Dunstan)
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: pgsql-performance@postgresql.org
Cc: alvherre@surnet.cl, Donald.Courtney@Sun.COM, tarthurs@jobflash.com
Subject: Re: Postgresql on an AMD64 machine
In-Reply-To: <20050607202755.GA28361@surnet.cl>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox