From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756641Ab3BVJ6s (ORCPT ); Fri, 22 Feb 2013 04:58:48 -0500 Received: from e23smtp01.au.ibm.com ([202.81.31.143]:45773 "EHLO e23smtp01.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754180Ab3BVJ6o (ORCPT ); Fri, 22 Feb 2013 04:58:44 -0500 Message-ID: <51274143.1090200@linux.vnet.ibm.com> Date: Fri, 22 Feb 2013 17:58:27 +0800 From: Michael Wang User-Agent: Mozilla/5.0 (X11; Linux i686; rv:16.0) Gecko/20121011 Thunderbird/16.0.1 MIME-Version: 1.0 To: Peter Zijlstra CC: Mike Galbraith , Ingo Molnar , LKML , Paul Turner , Andrew Morton , alex.shi@intel.com, Ram Pai , "Nikunj A. Dadhania" , Namhyung Kim Subject: Re: [RFC PATCH v3 0/3] sched: simplify the select_task_rq_fair() References: <51079178.3070002@linux.vnet.ibm.com> <20130220104958.GA9152@gmail.com> <5125A7C8.8020308@linux.vnet.ibm.com> <1361427108.5861.41.camel@marge.simpson.net> <5125C607.8090909@linux.vnet.ibm.com> <1361434231.5861.61.camel@marge.simpson.net> <5125E40D.6050006@linux.vnet.ibm.com> <1361439789.5861.70.camel@marge.simpson.net> <5126D9A2.8090404@linux.vnet.ibm.com> <1361521270.26780.34.camel@laptop> <51273609.9080308@linux.vnet.ibm.com> <1361525962.26780.47.camel@laptop> In-Reply-To: <1361525962.26780.47.camel@laptop> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Content-Scanned: Fidelis XPS MAILER x-cbid: 13022209-1618-0000-0000-000003629F50 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 02/22/2013 05:39 PM, Peter Zijlstra wrote: > On Fri, 2013-02-22 at 17:10 +0800, Michael Wang wrote: >> On 02/22/2013 04:21 PM, Peter Zijlstra wrote: >>> On Fri, 2013-02-22 at 10:36 +0800, Michael Wang wrote: >>>> According to my understanding, in the old world, wake_affine() will >>>> only >>>> be used if curr_cpu and prev_cpu share cache, which means they are in >>>> one package, whatever search in llc sd of curr_cpu or prev_cpu, we >>>> won't >>>> have the chance to spread the task out of that package. >>> >>> Nah, look at where SD_WAKE_AFFINE is set. Only 'remote/big' NUMA domains >>> don't have it set, but 'small' NUMA systems will have it set over the >>> entire domain tree. >> >> Oh, I missed that point... >> >> But I don't get the reason to make NUMA level affine, cpus in different >> nodes share cache? doesn't make sense... > > Contrary, it makes more sense, the more expensive it is to run 'remote' > the better it is to pull 'related' tasks together. It increase the range to bound task, from one node to several, but also increase the range of target cpus, from one node's to several's, I still can't estimate the benefit, but I think I get the purpose, trying to make related tasks as close as possible, is that right? Let me think about this point, I do believe there will be better way to take care of this purpose. Regards, Michael Wang > > > > -- > 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/ >