From owner-freebsd-stable Tue Sep 4 2: 6:29 2001 Delivered-To: freebsd-stable@freebsd.org Received: from mailhost.firstcallgroup.co.uk (dilbert.firstcallgroup.co.uk [194.203.69.166]) by hub.freebsd.org (Postfix) with ESMTP id 1959637B406; Tue, 4 Sep 2001 02:06:26 -0700 (PDT) Received: from pfrench by mailhost.firstcallgroup.co.uk with local (Exim 3.31 #1) id 15eC9z-0003e5-00; Tue, 04 Sep 2001 10:06:19 +0100 To: behanna@zbzoom.net, grog@FreeBSD.org Subject: Re: RAID5 Cc: stable@FreeBSD.ORG In-Reply-To: <20010904105035.C10292@wantadilla.lemis.com> Message-Id: From: Pete French Date: Tue, 04 Sep 2001 10:06:19 +0100 Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG > Interestingly, CPU isn't the performance issue most people (myself > once included) assume it is. Even on my original Vinum testbed, a > 468/66, CPU usage was barely measurable. That's probably why most > hardware RAID controllers use relatively slow CPUs. Interesting comment. I have acciddentally acquired apair of SMART 2SL controllers. One of which I am using as the boot device for the FreeBSD box (because iits theonly disc controller I've got - RAID 0). The other I was going to use to build an array, but I am having trouble finding any comoparative benchmarks as to how slow certain combinations of drives are under RAID-5. Are their certain numbers that make the processing "easier" for the onboard chip ? (*i.e. does 5 discs make life for it faster as it can split a byte onto 4 platters and allocate one for parity rather than dooing shifts all over the place ?) or is it best to just give it as many dricves as possible (8 in this case). -pcf. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message