From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757592Ab2LHBjy (ORCPT ); Fri, 7 Dec 2012 20:39:54 -0500 Received: from mx1.fusionio.com ([66.114.96.30]:49732 "EHLO mx1.fusionio.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757547Ab2LHBjw (ORCPT ); Fri, 7 Dec 2012 20:39:52 -0500 X-ASG-Debug-ID: 1354930791-03d6a50cb5d40520001-xx1T2L X-Barracuda-Envelope-From: clmason@fusionio.com Date: Fri, 7 Dec 2012 20:39:49 -0500 From: Chris Mason To: Dave Chinner CC: Chris Mason , Linus Torvalds , Ric Wheeler , Ingo Molnar , Christoph Hellwig , Martin Steigerwald , Linux Kernel Mailing List , "Theodore Ts'o" , linux-fsdevel Subject: Re: [PATCH, 3.7-rc7, RESEND] fs: revert commit bbdd6808 to fallocate UAPI Message-ID: <20121208013949.GD25713@shiny> X-ASG-Orig-Subj: Re: [PATCH, 3.7-rc7, RESEND] fs: revert commit bbdd6808 to fallocate UAPI Mail-Followup-To: Chris Mason , Dave Chinner , Chris Mason , Linus Torvalds , Ric Wheeler , Ingo Molnar , Christoph Hellwig , Martin Steigerwald , Linux Kernel Mailing List , Theodore Ts'o , linux-fsdevel References: <20121126025520.GC22858@thunk.org> <20121126091202.GO32450@dastard> <201212051148.28039.Martin@lichtvoll.de> <20121206120532.GA14100@infradead.org> <20121207011628.GB16373@gmail.com> <50C22923.90102@redhat.com> <20121207190306.GB14972@shiny> <20121208001705.GO27172@dastard> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline In-Reply-To: <20121208001705.GO27172@dastard> User-Agent: Mutt/1.5.21 (2011-07-01) X-Barracuda-Connect: mail1.int.fusionio.com[10.101.1.21] X-Barracuda-Start-Time: 1354930791 X-Barracuda-Encrypted: AES128-SHA X-Barracuda-URL: http://10.101.1.180:8000/cgi-mod/mark.cgi X-Barracuda-Bayes: INNOCENT GLOBAL 0.0158 1.0000 -1.9184 X-Barracuda-Spam-Score: -1.19 X-Barracuda-Spam-Status: No, SCORE=-1.19 using per-user scores of TAG_LEVEL=1000.0 QUARANTINE_LEVEL=1000.0 KILL_LEVEL=9.0 tests=CN_BODY_332, COMMA_SUBJECT X-Barracuda-Spam-Report: Code version 3.2, rules version 3.2.2.116392 Rule breakdown below pts rule name description ---- ---------------------- -------------------------------------------------- 0.60 COMMA_SUBJECT Subject is like 'Re: FDSDS, this is a subject' 0.12 CN_BODY_332 BODY: CN_BODY_332 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Dec 07, 2012 at 05:17:05PM -0700, Dave Chinner wrote: > On Fri, Dec 07, 2012 at 02:03:06PM -0500, Chris Mason wrote: [ dead and beaten fallocate ponies ] > > > On a single flash drive doing random 4K writes, xfs does 950MB/s into > > regular extents but only 400MB/s into preallocated extents. > > > > http://masoncoding.com/presentation/perf-linuxcon12/fallocate.png > > This is bordering on irrelevancy, but can you provide the workload > you were running to generate this graph? Random 4k writes could be > anything, really. This one was fio aio/dio, I'll dig out the job file and rerun it on 3.7-rc on Monday. Any real random write is going to show this with enough load. > > In my experience, applications that actually do processing between > random write IOs don't see anywhere near the same degradation as > such micro-benchmarks tend to indicate can occur with unwritten > extents. Are you seeing this level of degradation in real-world applications? > If you give me a reason to fix it (and the hardware to test it on), > I'm pretty sure I can bring the overhead down to just a few percent > on fully featured SSDs like FusionIO devices... We should have a card I can send, drop me the address. For the workload...that's harder. We can talk all day about what a normal random write workload is, but if you have a fio job that you think represents real world, I can run that. [ much nodding ;) ]