From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Hellwig Subject: Re: [patch v2 2/6] blk: dont allow discard request merge temporarily Date: Thu, 22 Mar 2012 02:28:51 -0400 Message-ID: <20120322062850.GA25288@infradead.org> References: <20120316073213.656519005@fusionio.com> <20120316073512.485027511@fusionio.com> <20120320162157.GE17071@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-raid-owner@vger.kernel.org To: "Martin K. Petersen" Cc: Shaohua Li , Vivek Goyal , linux-kernel@vger.kernel.org, linux-raid@vger.kernel.org, neilb@suse.de, axboe@kernel.dk List-Id: linux-raid.ids On Wed, Mar 21, 2012 at 10:18:54PM -0400, Martin K. Petersen wrote: > >>>>> "Shaohua" == Shaohua Li writes: > > Shaohua> Enabling discard merge is required for device with slow discard > Shaohua> (and very helpful for raid), > > Before RAID support there really wasn't much point. That's one of the > reasons the current discard merge code has survived despite being > completely broken. I've actually send repeated bug reports about it beeing broken when I enabled async discard in XFS which led to merges, and debugged it down to beeing a problem with merges. But Jens didn't like my patch to mark them nomerged, so we still couldn't commit the async discard support for XFS which would have helped quite a bit with discard performance.