Message-ID: <42A63F62.40007@arbash-meinel.com>
Date: Tue, 07 Jun 2005 19:44:18 -0500
From: John A Meinel <john@arbash-meinel.com>
User-Agent: Mozilla Thunderbird 1.0.2-1.3.3 (X11/20050513)
MIME-Version: 1.0
To: Neil Conway <neilc@samurai.com>
Cc: Tom Arthurs <tarthurs@jobflash.com>,
	Donald Courtney <Donald.Courtney@Sun.COM>, pgsql-performance@postgresql.org
Subject: Re: Postgresql on an AMD64 machine
References: <1118080420.1644.23.camel@penguin1>
	<b918cf3d05060613593a73a18a@mail.gmail.com>
	<42A5F7B6.20502@sun.com> <42A5FB70.8090807@jobflash.com>
	<42A6014C.30108@sun.com> <42A605E8.8040607@jobflash.com>
	<42A639C3.40606@samurai.com>
In-Reply-To: <42A639C3.40606@samurai.com>
Content-Type: multipart/signed; micalg=pgp-sha1;
	protocol="application/pgp-signature";
	boundary="------------enig0B10D113C2C726FE382298D2"

This is an OpenPGP/MIME signed message (RFC 2440 and 3156)
--------------enig0B10D113C2C726FE382298D2
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit

Neil Conway wrote:
> Tom Arthurs wrote:
> 
>> Yes, shared buffers in postgres are not used for caching
> 
> 
> Shared buffers in Postgres _are_ used for caching, they just form a
> secondary cache on top of the kernel's IO cache. Postgres does IO
> through the filesystem, which is then cached by the kernel. Increasing
> shared_buffers means that less memory is available for the kernel to
> cache IO -- increasing shared_buffers has been shown to be a net
> performance loss beyond a certain point. Still, there is value in
> shared_buffers as it means we can avoid a read() system call for hot
> pages. We can also do better buffer replacement in the PG shared buffer
> than the kernel can do (e.g. treating IO caused by VACUUM specially).
> 

As I recall, one of the performance problems with a large shared_buffers
is that there are some commands which require looking at *all* of the
shared buffer space. So the larger it gets, the longer those functions take.

>> My biggest challenge with solaris/sparc is trying to reduce context
>> switching.
> 
> 
> It would be interesting to see if this is improved with current sources,
> as Tom's bufmgr rewrite should have hopefully have reduced this problem.
> 

These might be what was fixed with Tom's rewrite. I don't really know.

John
=:->

> -Neil
> 
> ---------------------------(end of broadcast)---------------------------
> TIP 4: Don't 'kill -9' the postmaster


--------------enig0B10D113C2C726FE382298D2
Content-Type: application/pgp-signature; name="signature.asc"
Content-Description: OpenPGP digital signature
Content-Disposition: attachment; filename="signature.asc"

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.1 (GNU/Linux)
Comment: Using GnuPG with Fedora - http://enigmail.mozdev.org

iD8DBQFCpj9kJdeBCYSNAAMRAqRAAKCN3lh88n5FfN1Dy3fjxFNcH1iHzQCeMiX5
A0FKVRf/Vz5BxaumMUPE4fY=
=Zo6E
-----END PGP SIGNATURE-----

--------------enig0B10D113C2C726FE382298D2--