X-Original-To: pgsql-performance-postgresql.org@postgresql.org
Received: from localhost (mx1.hub.org [200.46.208.251])
	by postgresql.org (Postfix) with ESMTP id 5983B9FA18C
	for <pgsql-performance-postgresql.org@postgresql.org>;
	Wed, 13 Sep 2006 18:21:48 -0300 (ADT)
Received: from postgresql.org ([200.46.204.71])
	by localhost (mx1.hub.org [200.46.208.251]) (amavisd-new, port 10024)
	with ESMTP id 98907-08 for
	<pgsql-performance-postgresql.org@postgresql.org>;
	Wed, 13 Sep 2006 18:21:42 -0300 (ADT)
X-Greylist: delayed 00:19:36.848357 by SQLgrey-
Received: from palunko.srce.hr (palunko.srce.hr [161.53.2.67])
	by postgresql.org (Postfix) with ESMTP id 9DA0E9FA17D
	for <pgsql-performance@postgresql.org>;
	Wed, 13 Sep 2006 18:21:41 -0300 (ADT)
Received: from [10.0.0.10] (cmung3367.cmu.carnet.hr [193.198.141.65])
	by palunko.srce.hr (8.13.8/8.13.8) with ESMTP id k8DL1nxW005916
	for <pgsql-performance@postgresql.org>;
	Wed, 13 Sep 2006 23:01:50 +0200 (CEST)
Message-ID: <450871C9.1010709@fer.hr>
Date: Wed, 13 Sep 2006 23:02:01 +0200
From: Ivan Voras <ivoras@fer.hr>
User-Agent: Thunderbird 1.5.0.5 (Windows/20060719)
MIME-Version: 1.0
To: pgsql-performance@postgresql.org
Subject: Re: Poor performance on seq scan
References: <20060913160857.599538B460E@mx2.hub.org>
In-Reply-To: <20060913160857.599538B460E@mx2.hub.org>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
X-Scanned-By: MIMEDefang 2.55 on 161.53.2.67
X-Virus-Scanned: Maia Mailguard 1.0.1
X-Archive-Number: 200609/138
X-Sequence-Number: 20824

pgsql-performance-owner@postgresql.org wrote:

> This board has Intel chipset. I cannot remember the exact type but it
> was not in the low end category.
> dmesg says:
> 
> <Intel ICH7 SATA300 controller>
> kernel: ad4: 152626MB <SAMSUNG HD160JJ ZM100-33> at ata2-master SATA150
> kernel: ad4: 152627MB <SAMSUNG HD160JJ ZM100-33> at ata3-master SATA150

There have been reported problems with ICH7 on FreeBSD mailing lists,
though I can't find any that affect performance.

> Components: 2
> Balance: round-robin
> Slice: 4096

See if changing balance algorithm to "split", and slice size to 8192 or
more, while keeping vfs.read_max to 16 or more helps your performance.

(e.g. gmirror configure -b split -s 8192 gm0)

Also, how is your file system mounted? (what does output from 'mount' say?)