From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754917AbaA1KBg (ORCPT ); Tue, 28 Jan 2014 05:01:36 -0500 Received: from cantor2.suse.de ([195.135.220.15]:54584 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754595AbaA1KBe (ORCPT ); Tue, 28 Jan 2014 05:01:34 -0500 Date: Tue, 28 Jan 2014 10:01:31 +0000 From: Mel Gorman To: riel@redhat.com Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, peterz@infradead.org, mingo@redhat.com, chegu_vinod@hp.com Subject: Re: [PATCH 6/9] numa,sched: normalize faults_cpu stats and weigh by CPU use Message-ID: <20140128100131.GS4963@suse.de> References: <1390860228-21539-1-git-send-email-riel@redhat.com> <1390860228-21539-7-git-send-email-riel@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline In-Reply-To: <1390860228-21539-7-git-send-email-riel@redhat.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Jan 27, 2014 at 05:03:45PM -0500, riel@redhat.com wrote: > From: Rik van Riel > > Tracing the code that decides the active nodes has made it abundantly clear > that the naive implementation of the faults_from code has issues. > > Specifically, the garbage collector in some workloads will access orders > of magnitudes more memory than the threads that do all the active work. > This resulted in the node with the garbage collector being marked the only > active node in the group. > > This issue is avoided if we weigh the statistics by CPU use of each task in > the numa group, instead of by how many faults each thread has occurred. > > To achieve this, we normalize the number of faults to the fraction of faults > that occurred on each node, and then multiply that fraction by the fraction > of CPU time the task has used since the last time task_numa_placement was > invoked. > > This way the nodes in the active node mask will be the ones where the tasks > from the numa group are most actively running, and the influence of eg. the > garbage collector and other do-little threads is properly minimized. > > On a 4 node system, using CPU use statistics calculated over a longer interval > results in about 1% fewer page migrations with two 32-warehouse specjbb runs > on a 4 node system, and about 5% fewer page migrations, as well as 1% better > throughput, with two 8-warehouse specjbb runs, as compared with the shorter > term statistics kept by the scheduler. > > Cc: Peter Zijlstra > Cc: Mel Gorman > Cc: Ingo Molnar > Cc: Chegu Vinod > Signed-off-by: Rik van Riel Major changes are related to the weight calculations to avoid overflow and the avg runtime is calculated based on a longer runtime than the v4 version. Both seem sane so Acked-by: Mel Gorman -- Mel Gorman SUSE Labs