DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma;
	h=mime-version:in-reply-to:references:date:message-id:subject:from:to
	:cc:content-type:content-transfer-encoding;
	b=Gk5nFWyqpIhLIojfGL6hgE5nXknY5gexVzcAAqGl7xg+AlwZJZD6yc0jh2bZBsSu3d
	TjefdDX70/yURI2K4m9tIphz5Prh2Ia285GZknbTMOOQkCoOOFs2GlRBIV54iFbvrJIC
	Dmi6EDhC36fg5yH8/FV20VS3Dwrr0xiVvAkbg=
MIME-Version: 1.0
In-Reply-To: 
 <482E80323A35A54498B8B70FF2B8798003ED1B9CF0@azsmsx504.amr.corp.intel.com>
References: <49ABDB1F.2020208@elitecore.com>
	<482E80323A35A54498B8B70FF2B8798003ED1B9CF0@azsmsx504.amr.corp.intel.com>
Date: Tue, 3 Mar 2009 23:51:01 -0700
Message-ID: <dcc563d10903032251y54a74c3cmaeb1f23f1d78d30b@mail.gmail.com>
Subject: Re: Shared Buffers
From: Scott Marlowe <scott.marlowe@gmail.com>
To: "Gauthier, Dave" <dave.gauthier@intel.com>
Cc: Siddharth Shah <siddharth.shah@elitecore.com>,
	"pgsql-general@postgresql.org" <pgsql-general@postgresql.org>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

On Mon, Mar 2, 2009 at 7:40 AM, Gauthier, Dave <dave.gauthier@intel.com> wr=
ote:
> I believe that op system side buffering can play a role too.=A0 I our cas=
e,
> the DB server (machine & op sys) caches data that it pulled from disk (no=
t
> necessarily from a DB) and also the disk servers do the same.=A0 If a blo=
ck
> was removed from the DB buffer cache to accommodate more recently request=
ed
> data, but the evicted block is live in memory on the DB server or the dis=
k
> server, it can pull from there instead of performing an expensive disk-IO=
.

This is very true for certain workloads.  If your db is bigger than
memory, and you only work on a tiny bit at a time, the kernel is often
better at caching than pgsql.  Run something like pgbench on a machine
with say 4 Gig of memory and a 40 Gig pgbench db dir, and you're
better off with 128M or something for shared_buffers than 1G often
times.  Truly random small access, has, for me, worked better with
moderate to smaller shared_buffers.  Plus if you need to run a few
memory hog queries, the kernel can flush out some free memory from
cache quickly, but shared_buffers is static.  So, the kernel file
cache is self tuning.

But you'll have to test it with your application to really see.