From owner-freebsd-fs@FreeBSD.ORG Wed Dec 23 21:04:00 2009 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C4F371065692 for ; Wed, 23 Dec 2009 21:04:00 +0000 (UTC) (envelope-from bfriesen@simple.dallas.tx.us) Received: from blade.simplesystems.org (blade.simplesystems.org [65.66.246.74]) by mx1.freebsd.org (Postfix) with ESMTP id 79D788FC27 for ; Wed, 23 Dec 2009 21:04:00 +0000 (UTC) Received: from freddy.simplesystems.org (freddy.simplesystems.org [65.66.246.65]) by blade.simplesystems.org (8.13.8+Sun/8.13.8) with ESMTP id nBNL3xSN008615; Wed, 23 Dec 2009 15:03:59 -0600 (CST) Date: Wed, 23 Dec 2009 15:03:59 -0600 (CST) From: Bob Friesenhahn X-X-Sender: bfriesen@freddy.simplesystems.org To: Solon Lutz In-Reply-To: <1696529130.20091223212612@pyro.de> Message-ID: References: <568624531.20091215163420@pyro.de> <42952D86-6B4D-49A3-8E4F-7A1A53A954C2@spry.com> <957649379.20091216005253@pyro.de> <26F8D203-A923-47D3-9935-BE4BC6DA09B7@corp.spry.com> <1696529130.20091223212612@pyro.de> User-Agent: Alpine 2.01 (GSO 1266 2009-07-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; format=flowed; charset=US-ASCII X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.2.2 (blade.simplesystems.org [65.66.246.90]); Wed, 23 Dec 2009 15:03:59 -0600 (CST) Cc: freebsd-fs@freebsd.org Subject: Re: ZFS RaidZ2 with 24 drives? X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 23 Dec 2009 21:04:00 -0000 On Wed, 23 Dec 2009, Solon Lutz wrote: > I opted for two 12-disc raidz2. > Reasons were: Space is more important than performance. > > But performance is very poor - have a look at the iostats - sometimes nothing really seems > to happen for up to ten seconds, or very little data gets written. Might this be a problem > of the amd64 system having only 4GB of RAM? Any tuneable sysctls? Enabling prefetch didn't help...: The most likely cause is that several of your disks are not performing properly. Perhaps a disk is performing error recovery, or there is a bad cable, or maybe even too much chassis vibration. It only takes one pokey disk in a vdev to slow down the whole vdev. Using 'iostat -x 10' while your pool is under continous I/O load may help find the pokey disks. Bob -- Bob Friesenhahn bfriesen@simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer, http://www.GraphicsMagick.org/