From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756757AbaISMp4 (ORCPT ); Fri, 19 Sep 2014 08:45:56 -0400 Received: from service87.mimecast.com ([91.220.42.44]:48415 "EHLO service87.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755848AbaISMpz convert rfc822-to-8bit (ORCPT ); Fri, 19 Sep 2014 08:45:55 -0400 Message-ID: <541C259E.4010207@arm.com> Date: Fri, 19 Sep 2014 13:46:22 +0100 From: Juri Lelli User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.0 MIME-Version: 1.0 To: Daniel Wagner , "peterz@infradead.org" CC: "mingo@redhat.com" , "juri.lelli@gmail.com" , "raistlin@linux.it" , "michael@amarulasolutions.com" , "fchecconi@gmail.com" , "vincent@legout.info" , "luca.abeni@unitn.it" , "linux-kernel@vger.kernel.org" , Li Zefan , "cgroups@vger.kernel.org" Subject: Re: [PATCH 2/3] sched/deadline: fix bandwidth check/update when migrating tasks between exclusive cpusets References: <1411118561-26323-1-git-send-email-juri.lelli@arm.com> <1411118561-26323-3-git-send-email-juri.lelli@arm.com> <541C17D6.5020608@bmw-carit.de> In-Reply-To: <541C17D6.5020608@bmw-carit.de> X-OriginalArrivalTime: 19 Sep 2014 12:45:52.0490 (UTC) FILETIME=[A59504A0:01CFD407] X-MC-Unique: 114091913455207301 Content-Type: text/plain; charset=WINDOWS-1252 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Daniel, On 19/09/14 12:47, Daniel Wagner wrote: > Hi, > > On 09/19/2014 11:22 AM, Juri Lelli wrote: >> Exclusive cpusets are the only way users can restrict SCHED_DEADLINE tasks >> affinity (performing what is commonly called clustered scheduling). >> Unfortunately, such thing is currently broken for two reasons: >> >> - No check is performed when the user tries to attach a task to >> an exlusive cpuset (recall that exclusive cpusets have an >> associated maximum allowed bandwidth). >> >> - Bandwidths of source and destination cpusets are not correctly >> updated after a task is migrated between them. >> >> This patch fixes both things at once, as they are opposite faces >> of the same coin. >> >> The check is performed in cpuset_can_attach(), as there aren't any >> points of failure after that function. The updated is split in two >> halves. We first reserve bandwidth in the destination cpuset, after >> we pass the check in cpuset_can_attach(). And we then release >> bandwidth from the source cpuset when the task's affinity is >> actually changed. Even if there can be time windows when sched_setattr() >> may erroneously fail in the source cpuset, we are fine with it, as >> we can't perfom an atomic update of both cpusets at once. >> >> Reported-by: Daniel Wagner > > Ack > > I have no special test for this, I just let my test running which was > fixed by patch #1. Works fine though. I'll plan to write some test for this. > Ok, thanks. Just mind that the problem fixed by patch 3/3 may sometime affect this too. I should have definitely put 3/3 on top of the patchset :/. Thanks, - Juri