From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753907AbaENDV4 (ORCPT ); Tue, 13 May 2014 23:21:56 -0400 Received: from e23smtp08.au.ibm.com ([202.81.31.141]:57612 "EHLO e23smtp08.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753132AbaENDVz (ORCPT ); Tue, 13 May 2014 23:21:55 -0400 Message-ID: <5372E148.7050805@linux.vnet.ibm.com> Date: Wed, 14 May 2014 11:21:44 +0800 From: Michael wang User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.4.0 MIME-Version: 1.0 To: Rik van Riel , Peter Zijlstra CC: LKML , Ingo Molnar , Mike Galbraith , Alex Shi , Paul Turner , Mel Gorman , Daniel Lezcano Subject: Re: [ISSUE] sched/cgroup: Does cpu-cgroup still works fine nowadays? References: <537192D3.5030907@linux.vnet.ibm.com> <20140513094737.GU30445@twins.programming.kicks-ass.net> <53721FD4.6060300@redhat.com> In-Reply-To: <53721FD4.6060300@redhat.com> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 14051403-5140-0000-0000-0000051CF7EB Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 05/13/2014 09:36 PM, Rik van Riel wrote: [snip] >> >> echo 2048 > /cgroup/c/cpu.shares >> >> Where [ABC].sh are spinners: > > I suspect the "are spinners" is key. > > Infinite loops can run all the time, while dbench spends a lot of > its time waiting for locks. That waiting may interfere with getting > as much CPU as it wants. That's what we are thinking, also we assume that by introducing load decay mechanism, it become harder for the sleepy tasks to gain enough slice, well, that currently just imagination, more investigation is needed ;-) Regards, Michael Wang >