From: Lai Jiangshan Subject: Re: [PATCHSET wq/for-3.10] workqueue: NUMA affinity for unbound workqueues Date: Mon, 25 Mar 2013 00:04:19 +0800 Message-ID: References: <1363737629-16745-1-git-send-email-tj@kernel.org> <20130320185708.GB31256@htj.dyndns.org> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Cc: laijs@cn.fujitsu.com, axboe@kernel.dk, jack@suse.cz, fengguang.wu@intel.com, jmoyer@redhat.com, zab@redhat.com, linux-kernel@vger.kernel.org, herbert@gondor.apana.org.au, davem@davemloft.net, linux-crypto@vger.kernel.org To: Tejun Heo Return-path: Received: from mail-ia0-f170.google.com ([209.85.210.170]:54060 "EHLO mail-ia0-f170.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754029Ab3CXQEU (ORCPT ); Sun, 24 Mar 2013 12:04:20 -0400 In-Reply-To: <20130320185708.GB31256@htj.dyndns.org> Sender: linux-crypto-owner@vger.kernel.org List-ID: Hi, TJ After long time(again) thought. I think this patchset has this problem: the work may be running on wrong CPU when there is online cpu in its wq's cpumask. example: node0(cpu0,cpu1),node1(cpu2,cpu3), wq's cpumask: 1,3 the pwq of this wq on the node1's cpumask: 3 current online cpu: 0-2. so the cpumask of worker tasks of the pwq on node1 is actually cpu_all_mask. so the work scheduled from cpu2 can be executed on cpu0 or cpu2. we expect it is executed on cpu1 only. It can be fixed by swapping pwqs(node's pwq <-> default pwq) when cpuhotplug. But could you reschedule this patchset to wq/for-3.11? the whole patchset is more complicated than my brain. If you agree, I will rebase my patches again. Thanks, Lai On Thu, Mar 21, 2013 at 2:57 AM, Tejun Heo wrote: > On Tue, Mar 19, 2013 at 05:00:19PM -0700, Tejun Heo wrote: >> and also available in the following git branch. >> >> git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq.git review-numa > > Branch rebased on top of the current wq/for-3.10 with updated patches. > The new comit ID is 9555fbc12d786a9eae7cf7701a6718a0c029173e. > > Thanks. > > -- > tejun > -- > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > Please read the FAQ at http://www.tux.org/lkml/