From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753438AbZKNBY4 (ORCPT ); Fri, 13 Nov 2009 20:24:56 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753341AbZKNBYy (ORCPT ); Fri, 13 Nov 2009 20:24:54 -0500 Received: from mail-pz0-f171.google.com ([209.85.222.171]:34206 "EHLO mail-pz0-f171.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753339AbZKNBYx (ORCPT ); Fri, 13 Nov 2009 20:24:53 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; b=eu64GX5jL6gS1MnM1jeQUTdIb5+ye1r73HEJN4lg5NlaAy4fcMyZVVabfbFcgzifuf EcDmGo5iNCu90rSN4jQdfOMDjXirYlGMb7XB1iwVCaekqtykPnB6+mwHVhpBsaoFTvgm QyG/rwVnjdrQwqpcsufPFazfDjiZqDTNva5SA= MIME-Version: 1.0 In-Reply-To: <1258071249.22249.72.camel@gandalf.stny.rr.com> References: <1258071249.22249.72.camel@gandalf.stny.rr.com> Date: Fri, 13 Nov 2009 17:24:59 -0800 X-Google-Sender-Auth: b2ba1df373555c31 Message-ID: Subject: Re: RT wakeup woes in Linux 2.6.31.6 on Mac Mini From: Greg Steuck To: rostedt@goodmis.org Cc: linux-kernel@vger.kernel.org, Ingo Molnar , Thomas Gleixner , Peter Zijlstra Content-Type: text/plain; charset=ISO-8859-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Steven, Thanks for your reply. I believe the answer to my outliers question is - that's normal. I am lucky enough that 1ms delay is acceptable for my project and so I can stick with vanilla kernel for now. On Thu, Nov 12, 2009 at 4:14 PM, Steven Rostedt wrote: > Have you tried the -rt kernel? I have now. > I think you want "wakeup_rt", since that ignores SCHED_OTHER tasks. > SCHED_OTHER may wake up poorly, and hide the results of your RT task. Yes, done that now. > Looks like NEED_RESCHED is set, but interrupts are disabled. This is > typical for vanilla linux. I really suggest trying out the latest -rt > patch. With -rt9 I see a different set of interesting behaviors. I should mention that my task needs to send network packets. So, I end up trying to juggle priorities of irq/27-eth0, sirq-net-rx/1 and my rxtest tasks. If I make my task higher priority than the other two, I get interrupts delayed (because my task is being a hog sometimes). If I go the other way and my task gets lower priority, I end up with my task not getting to run when there is a lot of network activity which ultimately kills it. Thanks Greg -- nest.cx is Gmail hosted, use PGP for anything private. Key: http://tinyurl.com/ho8qg Fingerprint: 5E2B 2D0E 1E03 2046 BEC3 4D50 0B15 42BD 8DF5 A1B0