From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from [95.166.99.235] ([95.166.99.235]:38541 "EHLO kernel.dk" rhost-flags-FAIL-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1750751AbZKCUwM (ORCPT ); Tue, 3 Nov 2009 15:52:12 -0500 Date: Tue, 3 Nov 2009 21:52:17 +0100 From: Jens Axboe Subject: Re: fio-1.34.1, what we are doing with it and some patches we use. Message-ID: <20091103205216.GP8742@kernel.dk> References: <321292794.59661256869305878.JavaMail.root@zimbra.oss.co.nz> <336580134.59771256869521664.JavaMail.root@zimbra.oss.co.nz> <20091031070123.GW10727@kernel.dk> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20091031070123.GW10727@kernel.dk> Sender: fio-owner@vger.kernel.org List-Id: fio@vger.kernel.org To: Glen Ogilvie Cc: fio@vger.kernel.org, Michael O'Sullivan On Sat, Oct 31 2009, Jens Axboe wrote: > On Fri, Oct 30 2009, Glen Ogilvie wrote: > > Dear Jens Axboe and the FIO mailing list. > > > > I have been working with Mike O'Sullivan, a senior lecturer at the > > University of Auckland, New Zealand. He has been adapting fio 1.34.1 > > to work with iolog files and also to be able to read a "wait" command > > to allow the iolog file to specify a wait (in millisecs) before the > > next io. Mike's not completely confident that his changes are correct > > in the overall fio picture, but they are working with the iolog files > > we are using. What we did: > > > > 1) We incorporated wait into iolog file reading; 2) We made some > > modifications so that read_iolog worked. > > > > We have attached a patch for fio-1.34.1.tar.bz2 along with some > > demonstration fio config files and iolog files. > > > > We are doing this so we can use an open source SPC-1 emulator to > > generate SPC-1 like workloads and then run them in fio. > > > > Hope some of this work is useful. Feed back is welcome, we are not > > experts in FIO and SPC-1, so this may have problems. > > Interesting! I think the patch you attached is reversed, you want to > diff old tree -> new tree. Otherwise the patch looks nice and simple, > one of the hunks look like a generic bug fix for leaking memory and > probably should be applied first as it isn't really part of this > "feature". > > Another thing to keep in mind is the format of the iolog file. Did you > check whether the old versions just ignore the 'wait' line? If yes, we > can keep the format. Otherwise we probably need to bump it. I fixed up the style and committed it, thanks a lot for contributing this! -- Jens Axboe