From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754178AbYEIH74 (ORCPT ); Fri, 9 May 2008 03:59:56 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751747AbYEIH7r (ORCPT ); Fri, 9 May 2008 03:59:47 -0400 Received: from mail.gmx.net ([213.165.64.20]:37930 "HELO mail.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751916AbYEIH7q (ORCPT ); Fri, 9 May 2008 03:59:46 -0400 X-Authenticated: #14349625 X-Provags-ID: V01U2FsdGVkX19ttgB1D4ttRjbLcMXv32LgStpxJkLVcr0GtWwdNO dWYX77E6Ynim0h Subject: Re: sysbench+mysql(oltp, readonly) 30% regression with 2.6.26-rc1 From: Mike Galbraith To: Peter Zijlstra Cc: "Zhang, Yanmin" , LKML , Ingo Molnar In-Reply-To: <1210319417.13978.207.camel@twins> References: <1210136148.3453.59.camel@ymzhang> <1210177575.6525.4.camel@lappy.programming.kicks-ass.net> <1210228531.3453.124.camel@ymzhang> <1210233617.4895.6.camel@marge.simson.net> <1210237267.3453.143.camel@ymzhang> <1210238114.11887.3.camel@marge.simson.net> <1210238622.13978.193.camel@twins> <1210295779.3453.155.camel@ymzhang> <1210315870.13978.204.camel@twins> <1210318362.15296.4.camel@marge.simson.net> <1210319417.13978.207.camel@twins> Content-Type: text/plain Date: Fri, 09 May 2008 09:59:43 +0200 Message-Id: <1210319983.5250.4.camel@marge.simson.net> Mime-Version: 1.0 X-Mailer: Evolution 2.12.0 Content-Transfer-Encoding: 7bit X-Y-GMX-Trusted: 0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2008-05-09 at 09:50 +0200, Peter Zijlstra wrote: > On Fri, 2008-05-09 at 09:32 +0200, Mike Galbraith wrote: > > On Fri, 2008-05-09 at 08:51 +0200, Peter Zijlstra wrote: > > > > > > -rc1. Do you have the fix below applied? > > > > > > > > > > Oooh - good catch, that seems to be a post -rc1 merge. > > > > > > > > > > Yes this is required. > > > > > > > With below patch+previous_fix_weight_calc, the result is improved, but is still > > > > about 10% worse than the one of pure 2.6.26-rc1. > > > > Number of threads: 16 > > > > read/write requests: 6104336 (50867.11 per sec.) > > > > > > > > > > So puzzling - could you try -git + fix_weight_calc, as I think that is > > > what Mike tested and proved good on his Quad. > > > > If he still has group scheduling enabled, my box agrees that there's a > > regression. I got mysql running, and tested with group scheduling both > > enabled and disabled, results attached. (for some reason, I can only > > test up to 64 threads with mysql though) > > Hm, ok. Does the patch at hand improve or regress the group config for > you? Oh, you want me to revert it and retest group? -Mike