From owner-freebsd-fs@FreeBSD.ORG Thu Apr 19 23:24:59 2007 Return-Path: X-Original-To: fs@freebsd.org Delivered-To: freebsd-fs@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 7042C16A401; Thu, 19 Apr 2007 23:24:59 +0000 (UTC) (envelope-from fbsd-fs@mawer.org) Received: from customer-domains.icp-qv1-irony14.iinet.net.au (customer-domains.icp-qv1-irony14.iinet.net.au [203.59.1.169]) by mx1.freebsd.org (Postfix) with ESMTP id B0B1513C459; Thu, 19 Apr 2007 23:24:58 +0000 (UTC) (envelope-from fbsd-fs@mawer.org) Received: from 203-206-173-235.perm.iinet.net.au (HELO [10.24.1.1]) ([203.206.173.235]) by iinet-mail.icp-qv1-irony14.iinet.net.au with ESMTP; 20 Apr 2007 07:14:13 +0800 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AgAAAByUJ0bLzq3r/2dsb2JhbAAN X-IronPort-AV: i="4.14,429,1170601200"; d="scan'208"; a="56706335:sNHT7364964" Message-ID: <4627F7BE.5090606@mawer.org> Date: Fri, 20 Apr 2007 09:14:06 +1000 From: Antony Mawer User-Agent: Thunderbird 1.5.0.10 (Windows/20070221) MIME-Version: 1.0 To: David Cecil References: <20070418104155.GA31727@eschew.pusen.org> <86hcrdlqak.fsf@dwp.des.no> <20070418144103.GB31727@eschew.pusen.org> <20070418155156.GB20441@keira.kiwi-computer.com> <20070418180200.GA32061@eschew.pusen.org> <86odlku5xg.fsf@dwp.des.no> <20070419173316.GA57227@keira.kiwi-computer.com> <4627EC02.8070103@nokia.com> In-Reply-To: <4627EC02.8070103@nokia.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Dag-Erling Sm?rgrav , rick-freebsd@kiwi-computer.com, piso@freebsd.org, fs@freebsd.org Subject: Re: ZFS + replacing failing hard-drive. 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: Thu, 19 Apr 2007 23:24:59 -0000 On 20/04/2007 8:24 AM, David Cecil wrote: > ext Rick C. Petty wrote: >> On Thu, Apr 19, 2007 at 10:25:31AM +0200, Dag-Erling Sm?rgrav wrote: >> >>> Yes. I have four brand new disks which are giving me DMA timeouts all >>> the time. >>> >>> There seem to be bugs in (or in relation with) the ata driver which >>> have surfaced only recently. >>> >>> Now that I think about it - could this be related to interrupt >>> filtering? Piso? If the ata driver is losing interrupts, it's no >>> wonder the transfers are timing out. >>> >> >> What do you mean by recently? I've seen this problem which started >> around >> 5.4-RELEASE (perhaps earlier) and on, including 6.0-R thru 6.2-stable >> as of >> a few weeks ago. Would the interrupt filtering be present on these >> systems? > > I would like to second Rick's comments. I've certainly seen the problem > in 6.0 and 6.1, and replacing older disks with new ones hasn't rectified > the problem. > > Regards, > Dave Just another "me too". I've seen (S)ATA-related problems on 6.x (mostly 6.0) based machines, in some cases these appear to have been physical drive errors, but I haven't been able to verify each individual case. I don't know if quality control is sorely lacking on newer SATA drives or if it's something else... it has caused me to question whether or not there might be a driver/OS level issue... --Antony