From owner-freebsd-stable@FreeBSD.ORG Thu Dec 16 09:02:12 2004 Return-Path: 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 19A7016A4CE for ; Thu, 16 Dec 2004 09:02:12 +0000 (GMT) Received: from mail03.syd.optusnet.com.au (mail03.syd.optusnet.com.au [211.29.132.184]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2BB7243D4C for ; Thu, 16 Dec 2004 09:02:11 +0000 (GMT) (envelope-from PeterJeremy@optushome.com.au) Received: from cirb503493.alcatel.com.au (c211-30-75-229.belrs2.nsw.optusnet.com.au [211.30.75.229]) iBG927LP014864 (version=TLSv1/SSLv3 cipher=EDH-RSA-DES-CBC3-SHA bits=168 verify=NO); Thu, 16 Dec 2004 20:02:08 +1100 Received: from cirb503493.alcatel.com.au (localhost.alcatel.com.au [127.0.0.1])iBG927xP091998; Thu, 16 Dec 2004 20:02:07 +1100 (EST) (envelope-from pjeremy@cirb503493.alcatel.com.au) Received: (from pjeremy@localhost)iBG926Sk091997; Thu, 16 Dec 2004 20:02:06 +1100 (EST) (envelope-from pjeremy) Date: Thu, 16 Dec 2004 20:02:06 +1100 From: Peter Jeremy To: Gianluca Message-ID: <20041216090206.GC91817@cirb503493.alcatel.com.au> References: <20041213052628.GB78120@meer.net> <6.1.2.0.2.20041215190056.02f9bfb8@mail.rfnj.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <6.1.2.0.2.20041215190056.02f9bfb8@mail.rfnj.org> User-Agent: Mutt/1.4.2i cc: freebsd-stable@freebsd.org cc: asym Subject: Re: drive failure during rebuild causes page fault X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 16 Dec 2004 09:02:12 -0000 On Wed, 2004-Dec-15 19:16:59 -0500, asym wrote: [audio jukebox] >>what would be your recommendations for this particular (and very limited) >>application? > >Honestly I'd probably go for a RAID1+0 setup. It wastes half the space in >total for mirroring, but it has none of the performance penalties of >RAID-5, If you're just talking about audio, then RAID-5 would seem a better choice. You get much higher effective space utilisation (75-90% rather than 50%) and even the degraded bandwidth is plenty for serving a couple of audio streams. > and upto half the drives in the array can fail without anything but >speed being degraded. Normally, you replace a drive soon after it fails. The risks of a second drive failing should be fairly low. Note that you should try to get drives from different batches - all vendors have the occasional bad batch and you don't want all your drives to die at once. >RAID5 sacrifices write speed and redundancy for the sake of space. Since >you're using IDE and the drives are pretty cheap, I don't see the need for >such a sacrifice. For Gianluca's application, write speed wouldn't seem to be an issue. Redundancy may or may not be an issue - it depends how quickly a failed drive can be replaced and whether the risk of one of the other drives failing during this period is acceptable. The main advantage of RAID-5 is increased space - and this would seem to be an important issue. -- Peter Jeremy