From mboxrd@z Thu Jan 1 00:00:00 1970 From: John Robinson Subject: Re: standard performance (write speed 20Mb/s) Date: Mon, 18 Jul 2011 10:04:54 +0100 Message-ID: <4E23F736.30601@anonymous.org.uk> References: <201107162140.58883.raid1@fuckaround.org> <4E226464.2030200@hardwarefreak.com> <4E22D167.2010905@anonymous.org.uk> <20110717122230.GB2614@teal.hq.k1024.org> <4E22DABF.1020807@anonymous.org.uk> <20110717132833.GC2614@teal.hq.k1024.org> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20110717132833.GC2614@teal.hq.k1024.org> Sender: linux-raid-owner@vger.kernel.org To: Linux RAID List-Id: linux-raid.ids On 17/07/2011 14:28, Iustin Pop wrote: > On Sun, Jul 17, 2011 at 01:51:11PM +0100, John Robinson wrote: [...] >> doesn't work in magic sizes, so we should be using a more realistic >> benchmarking tool like bonnie++. > > Honestly, I don't find bonnie++ a realistic tool. fio is a much better > one; bonnie is quite old and inflexible. Ah OK, yes I agree with you there, but my general point remains: dd might be OK for producing one very specific metric in some cases, but that will not give a realistic impression of real use performance, so we should be using a more realistic benchmarking tool. Cheers, John.