From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1750756AbbCSIyg (ORCPT ); Thu, 19 Mar 2015 04:54:36 -0400 Received: from mail-we0-f180.google.com ([74.125.82.180]:33636 "EHLO mail-we0-f180.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750837AbbCSIyc (ORCPT ); Thu, 19 Mar 2015 04:54:32 -0400 Message-ID: <1426755269.4168.101.camel@gmail.com> Subject: Re: [PATCH 0/4 V5] workqueue: Introduce low-level unbound wq sysfs cpumask v5 From: Mike Galbraith To: Lai Jiangshan Cc: linux-kernel@vger.kernel.org Date: Thu, 19 Mar 2015 09:54:29 +0100 In-Reply-To: <1426653617-3240-1-git-send-email-laijs@cn.fujitsu.com> References: <1426136412-7594-1-git-send-email-laijs@cn.fujitsu.com> <1426653617-3240-1-git-send-email-laijs@cn.fujitsu.com> 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 Wed, 2015-03-18 at 12:40 +0800, Lai Jiangshan wrote: > This patchset mostly copies from Frederic and split the apply_workqueue_attrs() > as TJ's suggest. I plugged these into rt and gave them a go, had no trouble, and no unbound workqueues perturbing 7 isolated sockets (56 cores). Poking at the mask heftily after dropping the shield and giving the box plenty of generic work to do generated no excitement. Nice boring testdrive. > This patchset still doesn't include the patch "workqueue: Allow changing attributions > of ordered workqueues". After a brief stare, it looked ok to wedge that one in as well. Box didn't tell me I shouldn't have done that. -Mike