From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756014AbYIQW3m (ORCPT ); Wed, 17 Sep 2008 18:29:42 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753963AbYIQW3e (ORCPT ); Wed, 17 Sep 2008 18:29:34 -0400 Received: from pih-relay08.plus.net ([212.159.14.20]:57206 "EHLO pih-relay08.plus.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753892AbYIQW3e (ORCPT ); Wed, 17 Sep 2008 18:29:34 -0400 Message-ID: <48D184CC.2040204@yahoo.com> Date: Wed, 17 Sep 2008 23:29:32 +0100 From: Sitsofe Wheeler User-Agent: Thunderbird 2.0.0.16 (Macintosh/20080707) MIME-Version: 1.0 Newsgroups: gmane.linux.kernel To: Arjan van de Ven CC: linux-kernel@vger.kernel.org, Ingo Molnar , peterz@infradead.org Subject: Re: How how latent should non-preemptive scheduling be? References: <48D17B47.7080704@yahoo.com> <20080917145400.29d1809c@infradead.org> In-Reply-To: <20080917145400.29d1809c@infradead.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Plusnet-Relay: 06898238ff689d37dae1556e44f11224 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Arjan van de Ven wrote: > On Wed, 17 Sep 2008 22:48:55 +0100 > Sitsofe Wheeler wrote: > >> Arjan van de Ven wrote: >>> this says you haven't done "make install" on the latencytop >>> directory so it's not translating things for you.. can you do that >>> please? >>> Cause Maximum >>> > Percentage > > Scheduler: waiting for cpu 208 msec 59.4 % > > > you're rather CPU bound, and your process was woken up but didn't run for over 200 milliseconds.. > that sounds like a scheduler fairness issue! I'm at a bit of a loss to explain this. I'm not using the group scheduler and the load average is less than 0.4. CPU usage does seem to spike a fair bit (I'm not sure why rhythmbox needs 50%+ for decoding oggs from time to time) but there always seems to be 20% CPU free... I don't know where to start debugging this one and I'm suspicious of the way the problem would happen every 30 seconds too... (this laptop is using ath5k for its wifi)