Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752089AbXB1JJW (ORCPT ); Wed, 28 Feb 2007 04:09:22 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752096AbXB1JJW (ORCPT ); Wed, 28 Feb 2007 04:09:22 -0500 Received: from rgminet01.oracle.com ([148.87.113.118]:52261 "EHLO rgminet01.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752089AbXB1JJU (ORCPT ); Wed, 28 Feb 2007 04:09:20 -0500 Date: Wed, 28 Feb 2007 10:07:50 +0100 From: Jens Axboe To: Ingo Molnar Cc: Suparna Bhattacharya , linux-kernel@vger.kernel.org, Linus Torvalds , Arjan van de Ven , Christoph Hellwig , Andrew Morton , Alan Cox , Ulrich Drepper , Zach Brown , Evgeniy Polyakov , "David S. Miller" , Davide Libenzi , Thomas Gleixner Subject: Re: A quick fio test (was Re: [patch 00/13] Syslets, "Threadlets", generic AIO support, v3) Message-ID: <20070228090750.GQ3733@kernel.dk> References: <20070223162508.GA16782@kernel.dk> <20070223171348.GA27838@in.ibm.com> <20070226135736.GF3822@kernel.dk> <20070226141315.GA15631@in.ibm.com> <20070226144548.GH3822@kernel.dk> <20070227043331.GA29942@in.ibm.com> <20070227094211.GR3822@kernel.dk> <20070227123932.GA8720@in.ibm.com> <20070228083100.GM3733@kernel.dk> <20070228083805.GB9705@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20070228083805.GB9705@elte.hu> X-Brightmail-Tracker: AAAAAQAAAAI= X-Whitelist: TRUE Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1482 Lines: 34 On Wed, Feb 28 2007, Ingo Molnar wrote: > > * Jens Axboe wrote: > > > Engine Depth Batch Bw (KiB/sec) > > libaio 20000 8 21,125 > > syslet 20000 8 19,610 > > i'd like to do something more about this to be more in line with libaio > - if nothing else then for the bragging rights ;-) It seems to me that a > drop of ~7% in throughput cannot be explained with any CPU overhead, it > must be some sort of queueing + IO scheduling effect - right? syslet shows a slightly higher overhead, but nothing that will account for any bandwidth change in this test. The box is obviously mostly idle when running this test, it's not very CPU consuming. The IO pattern issued is not the same, since libaio would commit IO [0..7], then [8..15] and so on, where syslet would expose [0,8,16,24,32,40,48,56] and then [1,9,17,25,33,41,49,57] etc. If iodepth_batch is set to 1 you'd get a closer match wrt io pattern, but at a higher cost (increased system calls, and 8 times as many pending async threads). That gets it to 20,253KiB/s here with ~1000 as many context switches. So in short, it's harder to compare with real storage, as access patterns don't translate very easily -- Jens Axboe - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/