From owner-freebsd-current@FreeBSD.ORG Tue Apr 24 11:34:37 2007 Return-Path: X-Original-To: freebsd-current@freebsd.org Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 4058216A40B for ; Tue, 24 Apr 2007 11:34:37 +0000 (UTC) (envelope-from anderson@freebsd.org) Received: from mh1.centtech.com (moat3.centtech.com [64.129.166.50]) by mx1.freebsd.org (Postfix) with ESMTP id 14E8F13C458 for ; Tue, 24 Apr 2007 11:34:36 +0000 (UTC) (envelope-from anderson@freebsd.org) Received: from neutrino.centtech.com (neutrino.centtech.com [10.177.171.220]) by mh1.centtech.com (8.13.8/8.13.8) with ESMTP id l3OBYZOH025275; Tue, 24 Apr 2007 06:34:36 -0500 (CDT) (envelope-from anderson@freebsd.org) Message-ID: <462DEB4A.6050700@freebsd.org> Date: Tue, 24 Apr 2007 06:34:34 -0500 From: Eric Anderson User-Agent: Thunderbird 2.0.0.0 (X11/20070420) MIME-Version: 1.0 To: "Daniel O'Connor" References: <20070424051420.GA84831@mero.morphisms.net> <200704241554.12605.doconnor@gsoft.com.au> <20070424084409.GA98777@keltia.freenix.fr> <200704241942.40874.doconnor@gsoft.com.au> In-Reply-To: <200704241942.40874.doconnor@gsoft.com.au> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.88.4/3154/Tue Apr 24 01:13:03 2007 on mh1.centtech.com X-Virus-Status: Clean X-Spam-Status: No, score=-2.6 required=8.0 tests=AWL,BAYES_00 autolearn=ham version=3.1.6 X-Spam-Checker-Version: SpamAssassin 3.1.6 (2006-10-03) on mh1.centtech.com Cc: freebsd-current@freebsd.org Subject: Re: ATA FLUSHCACHE X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Apr 2007 11:34:37 -0000 On 04/24/07 05:12, Daniel O'Connor wrote: > On Tuesday 24 April 2007 18:14, Ollivier Robert wrote: >> The main problem that I've found is that with a single disk >> configuration, there is a timeout then the system recovers but with a >> dual (or maybe more) disks involved, multiple/current timeouts make >> the system panic and that is not nice. >> >> I suspect that changing the timeout may just hide the real problem. > > Hmm, it is a non fatal error for gjournal, I'm kind of surprised it's a > fatal one for ZFS.. > > If the cache flush really failed (eg due to a stuffed disk) then there > really is a problem, but IMO it is likely this is going to be caught by > a read or a write operation very soon. > > If it is a transient error then panicing seems to be about the worse > response :) > Doesn't a failed ATA FLUSHCACHE mean that the device could not complete it's writing of cached bits to stable storage within the timeout period? That seems to me that the flushcache should be called more frequently then, so less writes have to be written out. Eric