Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932677AbcC3H7W (ORCPT ); Wed, 30 Mar 2016 03:59:22 -0400 Received: from mail-lb0-f195.google.com ([209.85.217.195]:36393 "EHLO mail-lb0-f195.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753137AbcC3H7V (ORCPT ); Wed, 30 Mar 2016 03:59:21 -0400 MIME-Version: 1.0 In-Reply-To: <20160330064455.GQ3408@twins.programming.kicks-ass.net> References: <1413938203-224610-1-git-send-email-wanpeng.li@linux.intel.com> <544779D1.4060309@arm.com> <20160329184722.0d54b946@gandalf.local.home> <20160330064455.GQ3408@twins.programming.kicks-ass.net> Date: Wed, 30 Mar 2016 15:59:19 +0800 Message-ID: Subject: Re: [PATCH v3] sched/deadline: do not try to push tasks if pinned task switches to dl From: Wanpeng Li To: Peter Zijlstra Cc: Steven Rostedt , Juri Lelli , Wanpeng Li , Ingo Molnar , Kirill V Tkhai , "linux-kernel@vger.kernel.org" Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 834 Lines: 23 2016-03-30 14:44 GMT+08:00 Peter Zijlstra : > On Tue, Mar 29, 2016 at 06:47:22PM -0400, Steven Rostedt wrote: >> I'm looking at some old changes for sched-deadline, and I stumbled >> across this. As I'm working on sched deadline tests, I've discovered >> that they can't have cpu affinity. They are limited to their sched >> domains. That is, sched deadline tasks have whatever affinity that the root domain I think. >> domain they happen to be in has. >> >> Is there a condition where rq != task_rq(p) and p->nr_cpus_allowed > 1 >> isn't true? > > When holding rq->lock, no. I suppose the patch was just to mirror rt and > someone 'forgot' about the extra constraints on dl tasks. > sched_class::switched_from() methods can drop rq->lock before your great balance_callback patchset. :-) Regards, Wanpeng Li