From mboxrd@z Thu Jan 1 00:00:00 1970 From: "H. Peter Anvin" Subject: Re: RAID-10 keeps aborting Date: Wed, 12 Jun 2013 20:13:19 -0700 Message-ID: <51B938CF.5070303@zytor.com> References: <51AC1440.7020505@zytor.com> <51ACBAA0.40604@zytor.com> <51ACD511.4030604@zytor.com> <51AE2A8C.4080508@zytor.com> <51AE3441.3000208@zytor.com> <51AEA4FE.3060900@zytor.com> <20130606142747.1fc17b7f@jlaw-desktop.mno.stratus.com> <20130610101505.33b32d07@jlaw-desktop.mno.stratus.com> <20130612131543.1c79e077@notabene.brown> <51B 7F41F.9000605@zytor.com> <51B885B8.9040600@zytor.com> <51B8897C.8000801@zytor.com> <20130613131051.25d5730d@notaben! e.brown> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20130613131051.25d5730d@notabene.brown> Sender: linux-raid-owner@vger.kernel.org To: NeilBrown Cc: "Martin K. Petersen" , Joe Lawrence , Dan Williams , linux-raid List-Id: linux-raid.ids On 06/12/2013 08:10 PM, NeilBrown wrote: > > Promising - thanks. > > However should we do the same thing in raid5.c too? As far as I can > tell, the default set by blk_set_stacking_limits() (which md calls) > is to allow WRITE_SAME if all all underlying devices do. But I'm > pretty sure raid5 will do the wrong thing with a WRITE_SAME > request. > Yes, if raid5 also bounces the array if the WRITE SAME request fails at the device we need to do the same thing there. -hpa