From owner-freebsd-stable@FreeBSD.ORG Wed Jun 1 15:07:58 2005 Return-Path: X-Original-To: freebsd-stable@freebsd.org Delivered-To: freebsd-stable@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id BEBF216A41C for ; Wed, 1 Jun 2005 15:07:58 +0000 (GMT) (envelope-from brucegb@realtime.net) Received: from ruth.realtime.net (ruth.realtime.net [205.238.132.69]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4E27F43D48 for ; Wed, 1 Jun 2005 15:07:58 +0000 (GMT) (envelope-from brucegb@realtime.net) Received: from tigerfish2.my.domain (unverified [70.113.33.56]) by realtime.net (Realtime Communications Advanced E-Mail Services V9.2) with ESMTP id 84901233 for multiple; Wed, 01 Jun 2005 10:07:56 -0500 Received: from tigerfish2.my.domain (localhost [127.0.0.1]) by tigerfish2.my.domain (8.13.3/8.13.3) with ESMTP id j51F7sbq062336; Wed, 1 Jun 2005 10:07:54 -0500 (CDT) (envelope-from brucegb@tigerfish2.my.domain) Received: (from brucegb@localhost) by tigerfish2.my.domain (8.13.3/8.13.3/Submit) id j51F7sFD062335; Wed, 1 Jun 2005 10:07:54 -0500 (CDT) (envelope-from brucegb) Date: Wed, 1 Jun 2005 10:07:54 -0500 From: Bruce Burden To: Steven Hartland Message-ID: <20050601150754.GE20906@tigerfish2.my.domain> References: <006201c56633$5bc48c20$b3db87d4@multiplay.co.uk> <20050531233612.GD20906@tigerfish2.my.domain> <429D0C65.6010308@alumni.rice.edu> <003401c56696$0858c4d0$b3db87d4@multiplay.co.uk> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <003401c56696$0858c4d0$b3db87d4@multiplay.co.uk> User-Agent: Mutt/1.4.2.1i X-Server: High Performance Mail Server - http://surgemail.com Cc: freebsd-stable@freebsd.org Subject: Re: asr ( 2015S ) support in 5.4 amd64? X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 01 Jun 2005 15:07:58 -0000 Hi Steve, On Wed, Jun 01, 2005 at 11:38:17AM +0100, Steven Hartland wrote: > Thanks for that info. Have you had experience with the card > itself? Just did a few benchmarks and considering the disks > attached ( RAID 5 ) the performance is shockingly bad > 20->30MB/s read off the device node no other IO happening > ( measured using dd ). > Does anyone have any recomendations for other SCSI > RAID cards that can provide good performance and amd64 > support? > My 3210S generates around 45Mps: su-2.05b# dd if=ft_sill_photos.zip of=/dev/null 4040211+1 records in 4040211+1 records out 2068588162 bytes transferred in 46.935343 secs (44073145 bytes/sec) su-2.05b# dd if=ft_sill_photos.zip of=/dev/null bs=65536 31564+1 records in 31564+1 records out 2068588162 bytes transferred in 45.793030 secs (45172555 bytes/sec) Compared to my 39320: su-2.05b# cd /spare su-2.05b# dd if=ft_sill_photos.zip of=/dev/null bs=65536 31564+1 records in 31564+1 records out 2068588162 bytes transferred in 84.538472 secs (24469193 bytes/sec) which is where the system files are mounted (/, /var, /usr, etc). Both cards are installed in 64 bit/66 MHz slots. The system disk is a 10K IBM U160 disk, the RAID is composed of Seagate U320 drives. Still, performance is limited to U160 levels due to the controllers or the drives... Bruce -- ------------------------------------------------------------------------ "I like bad!" Bruce Burden Austin, TX. - Thuganlitha The Power and the Prophet Robert Don Hughes