From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757885Ab3APB4s (ORCPT ); Tue, 15 Jan 2013 20:56:48 -0500 Received: from cn.fujitsu.com ([222.73.24.84]:12726 "EHLO song.cn.fujitsu.com" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1757289Ab3APB4q convert rfc822-to-8bit (ORCPT ); Tue, 15 Jan 2013 20:56:46 -0500 X-IronPort-AV: E=Sophos;i="4.84,476,1355068800"; d="scan'208";a="6594807" Subject: Re: [PATCH v3 05/22] sched: remove domain iterations in fork/exec/wake From: li guang To: Alex Shi Cc: Preeti U Murthy , Morten Rasmussen , "mingo@redhat.com" , "peterz@infradead.org" , "tglx@linutronix.de" , "akpm@linux-foundation.org" , "arjan@linux.intel.com" , "bp@alien8.de" , "pjt@google.com" , "namhyung@kernel.org" , "efault@gmx.de" , "vincent.guittot@linaro.org" , "gregkh@linuxfoundation.org" , "linux-kernel@vger.kernel.org" In-Reply-To: <50F4C027.1080806@intel.com> References: <1357375071-11793-1-git-send-email-alex.shi@intel.com> <1357375071-11793-6-git-send-email-alex.shi@intel.com> <20130109182102.GC2046@e103034-lin> <50EF9B69.3000201@linux.vnet.ibm.com> <1357891316.2860.6.camel@liguang.fnst.cn.fujitsu.com> <50F02823.1070909@intel.com> <1358154191.8818.15.camel@liguang.fnst.cn.fujitsu.com> <50F4C027.1080806@intel.com> Date: Wed, 16 Jan 2013 09:54:40 +0800 Message-ID: <1358301280.23348.6.camel@liguang.fnst.cn.fujitsu.com> Mime-Version: 1.0 X-Mailer: Evolution 2.30.3 X-MIMETrack: Itemize by SMTP Server on mailserver/fnst(Release 8.5.3|September 15, 2011) at 2013/01/16 09:55:59, Serialize by Router on mailserver/fnst(Release 8.5.3|September 15, 2011) at 2013/01/16 09:56:01, Serialize complete at 2013/01/16 09:56:01 Content-Transfer-Encoding: 8BIT Content-Type: text/plain; charset="UTF-8" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 在 2013-01-15二的 10:34 +0800，Alex Shi写道： > On 01/14/2013 05:03 PM, li guang wrote: > >>> > > This corner case may occur after "[PATCH v3 03/22] sched: fix > >>> > > find_idlest_group mess logical" brought in the local sched_group bias, > >>> > > and assume balancing runs on cpux2. > >>> > > ideally, find_idlest_group should find the real idlest(this case: sgy), > >>> > > then, this patch is reasonable. > >>> > > > >> > > >> > Sure. but seems it is a bit hard to go down the idlest group. > >> > > >> > and the old logical is real cost too much, on my 2 socket NHM/SNB > >> > server, hackbench can increase 2~5% performance. and no clean > >> > performance on kbuild/aim7 etc. > > what about remove local group bias? > > > Any theory profit for non local group? Usually, bias toward local group > will has cache locality profit. > but the disadvantage is miss correct balance sometime, if mostly like you said before it will bring in better performance, that's fine, I have no strong statistic to do more profound analysis. -- regards! li guang