From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from brick.kernel.dk ([93.163.65.50]:36744 "EHLO kernel.dk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751029AbZDVGVd (ORCPT ); Wed, 22 Apr 2009 02:21:33 -0400 Date: Wed, 22 Apr 2009 08:21:32 +0200 From: Jens Axboe Subject: Re: Issue running random reads with verify on a raw device Message-ID: <20090422062132.GV4593@kernel.dk> References: <66dfd3fe0904101557g99d6b63r5a24a84cfe01ffbf@mail.gmail.com> <20090418175308.GE4593@kernel.dk> <66dfd3fe0904211631q2d5b7045o5664a3bdda100c19@mail.gmail.com> <20090422060528.GU4593@kernel.dk> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20090422060528.GU4593@kernel.dk> Sender: fio-owner@vger.kernel.org List-Id: fio@vger.kernel.org To: Radha Ramachandran Cc: fio@vger.kernel.org On Wed, Apr 22 2009, Jens Axboe wrote: > On Tue, Apr 21 2009, Radha Ramachandran wrote: > > Hi Jens, > > Ah right, I missed the offset. > > My interpretation of the options was that the check needs to be that > > the (new random block + offset) needs to be < both the real_file_size > > and io_size. > > > > Iam not sure i understand what you said very well, so the fix that I have is: > > I read up on the code, and I think your previous patch was correct. The > offset isn't added until later in the process, so we should indeed not > check the offset in this location. > > I'll test your previous patch and add it, sorry for the noise! Everything appears to be in working order, I have added your fix. Thanks! -- Jens Axboe