From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1766003AbXHFS2B (ORCPT ); Mon, 6 Aug 2007 14:28:01 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753964AbXHFS1y (ORCPT ); Mon, 6 Aug 2007 14:27:54 -0400 Received: from mail.gmx.net ([213.165.64.20]:37242 "HELO mail.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1752325AbXHFS1x (ORCPT ); Mon, 6 Aug 2007 14:27:53 -0400 X-Authenticated: #4463548 X-Provags-ID: V01U2FsdGVkX184rtEvcm84slhmZWOM678gRDC+E2efweXHn5m8wT kzBKmjThc9SgoD Message-ID: <46B7763C.9030208@gmx.net> Date: Mon, 06 Aug 2007 21:27:56 +0200 From: Dimitrios Apostolou User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.10) Gecko/20070301 SeaMonkey/1.0.8 MIME-Version: 1.0 To: Andrew Morton CC: linux-kernel@vger.kernel.org Subject: Re: high system cpu load during intense disk i/o References: <200708031903.10063.jimis@gmx.net> <200708051903.12414.jimis@gmx.net> <20070805182811.a8992126.akpm@linux-foundation.org> <46B72E2E.5040906@gmx.net> <20070806103317.5688d6df.akpm@linux-foundation.org> In-Reply-To: <20070806103317.5688d6df.akpm@linux-foundation.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Y-GMX-Trusted: 0 Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Hi, Andrew Morton wrote: > I suspect I was fooled by the oprofile output, which showed tremendous > amounts of load in schedule() and switch_to(). The percentages which > opreport shows are the percentage of non-halted CPU time. So if you have a > function in the kernel which is using 1% of the total CPU, and the CPU is > halted for 95% of the time, it appears that the function is taking 20% of > CPU! > > The fix for that is to boot with the "idle=poll" boot parameter, to make > the CPU spin when it has nothing else to do. I'll test again the two_discs_bad situation after booting with that parameter. Thanks. > > I'm suspecting that your machine is just stuck in D state waiting for disk. > Did we have a sysrq-T trace? The amazing thing is that this doesn't happen! Every single cron jobs that keeps running (I intentionally said that before too) and never ends is in R state. By strace'ing the processes they just seem to be going *extremely* slow. I also changed the I/O elevator of hdb (the OS disk) to deadline from cfq, unfortunately with no results. That is why I 've been considering it a CPU scheduler issue. Dimitris