From owner-freebsd-scsi@FreeBSD.ORG  Wed May 12 02:49:09 2004
Return-Path: <owner-freebsd-scsi@FreeBSD.ORG>
Delivered-To: freebsd-scsi@freebsd.org
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP
	id B132A16A4CF; Wed, 12 May 2004 02:49:09 -0700 (PDT)
Received: from mail.errors.firstcallgroup.co.uk
	(mail.errors.firstcallgroup.co.uk [213.167.69.198])
	by mx1.FreeBSD.org (Postfix) with ESMTP
	id 4CB5E43D39; Wed, 12 May 2004 02:49:09 -0700 (PDT)
	(envelope-from petefrench@keithprowse.com)
Received: from smaug.rattatosk ([172.16.1.8])
	by mail.errors.firstcallgroup.co.uk with esmtp (Exim 4.22)
	id 1BNqMN-000DTw-3g; Wed, 12 May 2004 10:49:07 +0100
Received: from [172.16.1.6] (helo=dilbert.firstcallgroup.co.uk)
	by smaug.rattatosk with esmtp (Exim 4.22)
	id 1BNqMM-0000QR-Si; Wed, 12 May 2004 10:49:06 +0100
Received: from petefrench by dilbert.firstcallgroup.co.uk with local (Exim
	4.30; FreeBSD)	id 1BNqMM-0002EO-Ry; Wed, 12 May 2004 10:49:06 +0100
To: schweikh@schweikhardt.net, scottl@freebsd.org
In-Reply-To: <40A13F22.80505@freebsd.org>
Message-Id: <E1BNqMM-0002EO-Ry@dilbert.firstcallgroup.co.uk>
From: Pete French <petefrench@keithprowse.com>
Date: Wed, 12 May 2004 10:49:06 +0100
cc: freebsd-scsi@freebsd.org
Subject: Re: 2120S Stripe - abysmal performance
X-BeenThere: freebsd-scsi@freebsd.org
X-Mailman-Version: 2.1.1
Precedence: list
List-Id: SCSI subsystem <freebsd-scsi.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-scsi>,
	<mailto:freebsd-scsi-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-scsi>
List-Post: <mailto:freebsd-scsi@freebsd.org>
List-Help: <mailto:freebsd-scsi-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-scsi>,
	<mailto:freebsd-scsi-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Wed, 12 May 2004 09:49:09 -0000

> Read caching should be turned off unless you have a very specific need
> for it.  Having it on is going to hurt sequential read performance by a
> 2x factor.  The only time is makes sense is when you have a relatively
> small data set that gets read repeatedly, with few other reads mixed in.

Interesting comment. Does that refer to this particular controller, to
caches on RAID controllers in general, or to caches on the drives themselves ?

-pete.