From owner-freebsd-hackers Wed Mar 4 11:15:02 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id LAA00345 for freebsd-hackers-outgoing; Wed, 4 Mar 1998 11:15:02 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from Kitten.mcs.com (Kitten.mcs.com [192.160.127.90]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id LAA00286 for ; Wed, 4 Mar 1998 11:14:48 -0800 (PST) (envelope-from karl@Mars.mcs.net) Received: from Mars.mcs.net (karl@Mars.mcs.net [192.160.127.85]) by Kitten.mcs.com (8.8.7/8.8.2) with ESMTP id NAA06569; Wed, 4 Mar 1998 13:14:41 -0600 (CST) Received: (from karl@localhost) by Mars.mcs.net (8.8.7/8.8.2) id NAA08084; Wed, 4 Mar 1998 13:14:41 -0600 (CST) Message-ID: <19980304131441.31888@mcs.net> Date: Wed, 4 Mar 1998 13:14:41 -0600 From: Karl Denninger To: shimon@simon-shapiro.org Cc: grog@lemis.com, hackers@FreeBSD.ORG, blkirk@float.eli.net, jdn@acp.qiv.com, tlambert@primenet.com, sbabkin@dcn.att.com, Wilko Bulte Subject: Re: SCSI Bus redundancy... References: <19980304081523.61560@mcs.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.84 In-Reply-To: ; from Simon Shapiro on Wed, Mar 04, 1998 at 11:14:28AM -0800 Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Wed, Mar 04, 1998 at 11:14:28AM -0800, Simon Shapiro wrote: > > On 04-Mar-98 Karl Denninger wrote: > ... > > > Hmmm.... Well, I made some adjustments to the queueing algorythm in the > > controller this morning, and guess what - I now get ~17MB/Sec on two SCSI > > busses in RAID 0+1 mode. Now *that's* not bad. In RAID 5 mode I'm > > getting > > ~10MB/sec still, and I think I'm hitting the wall now on the disk I/O > > (since > > RAID 5 doesn't stripe data) rather than on the interface! > > These are good numbers. Play with RAID-5 stripe size. You may see jumps > in perfromance. > > > Curiously enough, turning read-ahead in the controller on actually slows > > it *down* a bit. Not much, but a little bit. > > Of course. For RAID-5 it is normal. I set the DPT to ZERO. > > Simon Do you have a computation available for the 'optimum' stripe size (in blocks)? -- -- Karl Denninger (karl@MCS.Net)| MCSNet - Serving Chicagoland and Wisconsin http://www.mcs.net/ | T1's from $600 monthly to FULL DS-3 Service | NEW! K56Flex support on ALL modems Voice: [+1 312 803-MCS1 x219]| EXCLUSIVE NEW FEATURE ON ALL PERSONAL ACCOUNTS Fax: [+1 312 803-4929] | *SPAMBLOCK* Technology now included at no cost To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message