From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756065Ab0CHXhl (ORCPT ); Mon, 8 Mar 2010 18:37:41 -0500 Received: from hera.kernel.org ([140.211.167.34]:44724 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756012Ab0CHXhj (ORCPT ); Mon, 8 Mar 2010 18:37:39 -0500 Message-ID: <4B958ABC.3010401@kernel.org> Date: Tue, 09 Mar 2010 08:39:40 +0900 From: Tejun Heo User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.8) Gecko/20100228 SUSE/3.0.3-3.1 Thunderbird/3.0.3 MIME-Version: 1.0 To: Heiko Carstens CC: Oleg Nesterov , linux-kernel@vger.kernel.org, rusty@rustcorp.com.au, sivanich@sgi.com, torvalds@linux-foundation.org, mingo@elte.hu, peterz@infradead.org, dipankar@in.ibm.com, josh@freedesktop.org, paulmck@linux.vnet.ibm.com, akpm@linux-foundation.org, Martin Schwidefsky Subject: Re: [PATCH 2/4] stop_machine: reimplement using cpuhog References: <1268063603-7425-1-git-send-email-tj@kernel.org> <1268063603-7425-3-git-send-email-tj@kernel.org> <20100308171020.GC2557@osiris.boeblingen.de.ibm.com> <20100308182708.GA8504@redhat.com> <20100308193737.GA2466@osiris.boeblingen.de.ibm.com> In-Reply-To: <20100308193737.GA2466@osiris.boeblingen.de.ibm.com> X-Enigmail-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 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, 08 Mar 2010 23:36:45 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hello, On 03/09/2010 04:37 AM, Heiko Carstens wrote: >> How cpuhog can make a difference? Afaics, we shouldn't pass a >> blocking callback to hog_cpus/hog_one_cpu. > > Well, it might me true that this shouldn't be done. But I don't see > a reason why in general it wouldn't work to pass a function that > would block. So it's just a matter of time until somebody uses it > for such a purpose. For the current stop_machine implementation it > would be broken to pass a blocking function (preemption disabled, > interrupts disabled). Well, all current users don't block and it definitely can be enforced by turning off preemption around the callback. stop_machine() uses busy waiting for every state transition so something else blocking on a cpu could waste a lot of cpu cycles on other cpus even if the wait is guaranteed to be finite. Would that sooth your concern? Thanks. -- tejun