From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753835AbbCBRfp (ORCPT ); Mon, 2 Mar 2015 12:35:45 -0500 Received: from mail-wi0-f178.google.com ([209.85.212.178]:36520 "EHLO mail-wi0-f178.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753537AbbCBRfm (ORCPT ); Mon, 2 Mar 2015 12:35:42 -0500 Message-ID: <1425317738.9880.17.camel@gmail.com> Subject: Re: [PATCH v4 2/2] cpusets,isolcpus: add file to show isolated cpus in cpuset From: Mike Galbraith To: Tejun Heo Cc: Peter Zijlstra , Rik van Riel , Zefan Li , linux-kernel@vger.kernel.org, Clark Williams , Ingo Molnar , Luiz Capitulino , David Rientjes , cgroups@vger.kernel.org Date: Mon, 02 Mar 2015 18:35:38 +0100 In-Reply-To: <20150302160903.GE17694@htj.duckdns.org> References: <1424882288-2910-1-git-send-email-riel@redhat.com> <1424882288-2910-3-git-send-email-riel@redhat.com> <54EEFE15.3010005@huawei.com> <20150226121231.6fcba7e8@annuminas.surriel.com> <20150302090933.GH21418@twins.programming.kicks-ass.net> <1425300290.5863.17.camel@gmail.com> <20150302152924.GD17694@htj.duckdns.org> <1425312177.12094.15.camel@gmail.com> <20150302160903.GE17694@htj.duckdns.org> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.12.11 Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 2015-03-02 at 11:09 -0500, Tejun Heo wrote: > On Mon, Mar 02, 2015 at 05:02:57PM +0100, Mike Galbraith wrote: > > Well, those are the only ones we can do anything about. Dirt simple > > diddling of the workqueue default mask as sched domains are > > added/removed should do it I think. Automatically moving any existing > > unbound worker away from isolated cores at the same time would be a > > bonus, most important is that no new threads sneak in. > > Worker pools are immutable once created and configuraiton changes are > achieved by creating new pools and draining old ones but at any rate > making it follow config changes is almost trivial. Figuring out > configuration policy might take a bit of effort tho. Can you point me > to what specific configuration it should be following? For cpusets, an exclusive set should become taboo to unbound workers when load balancing is turned off. The user making sched domains go away is a not so subtle hint that he wants no random interference, as he is trying to assume full responsibility for task placement therein. In my trees, I let the user turn rt cpupri/push/pull off as well, as that further reduces jitter. -Mike