From owner-freebsd-scsi Sat Mar 20 14: 4:20 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from misery.sdf.com (misery.sdf.com [204.244.213.49]) by hub.freebsd.org (Postfix) with SMTP id CBD0514C4A for ; Sat, 20 Mar 1999 14:04:17 -0800 (PST) (envelope-from tom@sdf.com) Received: from tom by misery.sdf.com with esmtp (Exim 1.82 #3) id 10OSpP-0005Pw-00; Sat, 20 Mar 1999 12:58:43 -0800 Date: Sat, 20 Mar 1999 12:58:40 -0800 (PST) From: Tom To: Greg Lehey Cc: Nick Hilliard , freebsd-scsi@FreeBSD.ORG Subject: Re: dpt raid-5 performance In-Reply-To: <19990321074613.V429@lemis.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sun, 21 Mar 1999, Greg Lehey wrote: > On Saturday, 20 March 1999 at 8:55:27 -0800, Tom wrote: > > > > On Fri, 19 Mar 1999, Nick Hilliard wrote: > > > >> If I set up a raid-5 system on these disks with a slice-size of 512K, the > >> write performance is terrible. Bonnie reports: > > > > 512k will not result in very good single process write performance. > > In fact, 512k is suboptimal for many operations on RAID-5 arrays. > > I disagree. It's pretty much optimal for Vinum. I'd be interested in > your reasoning. Not so optimum for a DPT card running RAID-5. FreeBSD will likely never send IOs big enough for the strip size of 512kb to ever be useful. > > If you are optimizing for a single process, use something smaller > > (like 8k). > > That's far, far too small. Why? > Greg > -- > See complete headers for address, home page and phone numbers > finger grog@lemis.com for PGP public key Tom To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message