From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752907Ab0EaLrc (ORCPT ); Mon, 31 May 2010 07:47:32 -0400 Received: from hera.kernel.org ([140.211.167.34]:37162 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751762Ab0EaLrb (ORCPT ); Mon, 31 May 2010 07:47:31 -0400 Message-ID: <4C03A1C0.4020104@kernel.org> Date: Mon, 31 May 2010 13:47:12 +0200 From: Tejun Heo User-Agent: Mozilla/5.0 (X11; U; Linux i686 (x86_64); en-US; rv:1.9.1.9) Gecko/20100317 Thunderbird/3.0.4 MIME-Version: 1.0 To: Peter Zijlstra CC: mingo@elte.hu, linux-kernel@vger.kernel.org, Rusty Russell , Mike Galbraith Subject: Re: [PATCH 2/4] sched: implement __set_cpus_allowed() References: <1273747705-7829-1-git-send-email-tj@kernel.org> <1273747705-7829-3-git-send-email-tj@kernel.org> <1275292866.27810.21441.camel@twins> <4C03879A.8030505@kernel.org> <1275300084.27810.21850.camel@twins> <1275300165.27810.21858.camel@twins> <4C038A08.8090209@kernel.org> <1275300904.27810.21907.camel@twins> <4C038D18.9010006@kernel.org> <1275302796.27810.22049.camel@twins> In-Reply-To: <1275302796.27810.22049.camel@twins> X-Enigmail-Version: 1.0.1 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.2.3 (hera.kernel.org [127.0.0.1]); Mon, 31 May 2010 11:47:14 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hello, On 05/31/2010 12:46 PM, Peter Zijlstra wrote: > So workers _are_ thread bound and don't migrate, so for those I don't > see the problem, that is of course until we have to break affinity when > their CPU goes down, at which point we should clear PF_THREAD_BOUND I > think. > > For the rescue thread, why not set PF_THREAD_BOUND when its running > worklets and clear it when done? That way we get extra checking that > people won't migrate it when its not allowed. > > Does that work, or did I miss something? The rescuers migrate themselves so should be okay. I still think it would be better to migrate back detached workers. It's a slow path for sure but there's a big gaping hole between machine-slow and human-slow and works can be human-slow (ie. hotplug operation not finished in several minutes). I'll see if that's implementable w/o adding an additional interface. Thanks. -- tejun