From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761354AbZAQIwh (ORCPT ); Sat, 17 Jan 2009 03:52:37 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756074AbZAQIw2 (ORCPT ); Sat, 17 Jan 2009 03:52:28 -0500 Received: from viefep16-int.chello.at ([62.179.121.36]:18548 "EHLO viefep16-int.chello.at" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756058AbZAQIw1 (ORCPT ); Sat, 17 Jan 2009 03:52:27 -0500 X-SourceIP: 213.46.9.244 Subject: Re: [git pull] scheduler fixes From: Peter Zijlstra To: Andrew Morton Cc: Ingo Molnar , torvalds@linux-foundation.org, linux-kernel@vger.kernel.org In-Reply-To: <20090116204049.f4d6ef1c.akpm@linux-foundation.org> References: <20090111144305.GA7154@elte.hu> <20090114121521.197dfc5e.akpm@linux-foundation.org> <1231964647.14825.59.camel@laptop> <20090116204049.f4d6ef1c.akpm@linux-foundation.org> Content-Type: text/plain Date: Sat, 17 Jan 2009 09:52:31 +0100 Message-Id: <1232182351.7141.37.camel@twins> Mime-Version: 1.0 X-Mailer: Evolution 2.24.2 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2009-01-16 at 20:40 -0800, Andrew Morton wrote: > On Wed, 14 Jan 2009 21:24:07 +0100 Peter Zijlstra wrote: > > > On Wed, 2009-01-14 at 12:15 -0800, Andrew Morton wrote: > > > On Sun, 11 Jan 2009 15:43:05 +0100 > > > Ingo Molnar wrote: > > > > > > > Please pull the latest sched-fixes-for-linus git tree > > > > > > In http://bugzilla.kernel.org/show_bug.cgi?id=12309 the reporters have > > > identified what appears to be a sched-related performance regression. > > > A fairly long-term one - post-2.6.18, perhaps. > > > > > > Testcase code has been added today. Could someone please take a look > > > sometime? > > > > There appear to be two different bug reports in there. One about iowait, > > and one I'm not quite sure what it is about. > > > > The second thing shows some numbers and a test case, but I fail to see > > what the problem is with it. > > I had no problem seeing the problem: a gigantic performance regression > in two CPU-scheduler intensive workloads. Right, but it wasn't clearly stated what the issue was, and there seem to be two with that testcase 1) the total running time increases 2) it causes some severe latency spikes Now why it was stuck in with that iowait thing I have no clue, as it doesn't do anything with iowait, I ran the thing (well, both things) and iowait is 0%. Of course we'll try and fix these issues -- but as far as I'm concerned its utterly unrelated to the iowait thing. > I can see some other problems, too. The universe is full of problems, mixing them all up doesn't get us anywhere.