From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751990Ab2LEHnz (ORCPT ); Wed, 5 Dec 2012 02:43:55 -0500 Received: from mx1.fusionio.com ([66.114.96.30]:55857 "EHLO mx1.fusionio.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751482Ab2LEHnv (ORCPT ); Wed, 5 Dec 2012 02:43:51 -0500 X-ASG-Debug-ID: 1354693429-03d6a508b815fb20001-xx1T2L X-Barracuda-Envelope-From: JAxboe@fusionio.com Message-ID: <50BEFB2D.2000008@fusionio.com> Date: Wed, 5 Dec 2012 08:43:41 +0100 From: Jens Axboe MIME-Version: 1.0 To: Jeff Moyer CC: "linux-kernel@vger.kernel.org" , "linux-mm@kvack.org" , Zach Brown , "tj@kernel.org" , Peter Zijlstra , Ingo Subject: Re: [patch,v2] bdi: add a user-tunable cpu_list for the bdi flusher threads References: <50BE5988.3050501@fusionio.com> <50BE5C99.6070703@fusionio.com> X-ASG-Orig-Subj: Re: [patch,v2] bdi: add a user-tunable cpu_list for the bdi flusher threads In-Reply-To: Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit X-Barracuda-Connect: mail1.int.fusionio.com[10.101.1.21] X-Barracuda-Start-Time: 1354693429 X-Barracuda-Encrypted: AES128-SHA X-Barracuda-URL: http://10.101.1.180:8000/cgi-mod/mark.cgi X-Barracuda-Bayes: INNOCENT GLOBAL 0.0000 1.0000 -2.0210 X-Barracuda-Spam-Score: -2.02 X-Barracuda-Spam-Status: No, SCORE=-2.02 using per-user scores of TAG_LEVEL=1000.0 QUARANTINE_LEVEL=1000.0 KILL_LEVEL=9.0 tests= X-Barracuda-Spam-Report: Code version 3.2, rules version 3.2.2.116129 Rule breakdown below pts rule name description ---- ---------------------- -------------------------------------------------- Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 2012-12-04 23:26, Jeff Moyer wrote: > Jens Axboe writes: > >>>>> @@ -437,6 +488,14 @@ static int bdi_forker_thread(void *ptr) >>>>> spin_lock_bh(&bdi->wb_lock); >>>>> bdi->wb.task = task; >>>>> spin_unlock_bh(&bdi->wb_lock); >>>>> + mutex_lock(&bdi->flusher_cpumask_mutex); >>>>> + ret = set_cpus_allowed_ptr(task, >>>>> + bdi->flusher_cpumask); >>>>> + mutex_unlock(&bdi->flusher_cpumask_mutex); >>>> >>>> It'd be very useful if we had a kthread_create_cpu_on_cpumask() instead >>>> of a _node() variant, since the latter could easily be implemented on >>>> top of the former. But not really a show stopper for the patch... >>> >>> Hmm, if it isn't too scary, I might give this a try. >> >> Should not be, pretty much just removing the node part of the create >> struct passed in and making it a cpumask. And for the on_node() case, >> cpumask_of_ndoe() will do the trick. > > I think it's a bit more involved than that. If you look at > kthread_create_on_node, the node portion only applies to where the > memory comes from, it says nothing of scheduling. To whit: > > /* > * root may have changed our (kthreadd's) priority or CPU mask. > * The kernel thread should not inherit these properties. > */ > sched_setscheduler_nocheck(create.result, SCHED_NORMAL, ¶m); > set_cpus_allowed_ptr(create.result, cpu_all_mask); > > So, if I were to make the change you suggested, I would be modifying the > existing behaviour. The way things stand, I think > kthread_create_on_node violates the principal of least surprise. ;-) I > would prefer a variant that affected scheduling behaviour as well as > memory placement. Tejun, Peter, Ingo, what are your opinions? Huh you are right, I completely missed that set_cpus_allowed_ptr() uses cpu_all_mask and not mask_of_node(node). Doesn't make a lot of sense to me... And yes, in any case, it definitely is a bad API, not very logical. -- Jens Axboe