From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753907Ab0BIKOR (ORCPT ); Tue, 9 Feb 2010 05:14:17 -0500 Received: from casper.infradead.org ([85.118.1.10]:58975 "EHLO casper.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752496Ab0BIKOQ (ORCPT ); Tue, 9 Feb 2010 05:14:16 -0500 Subject: Re: Fwd: Possible performance improvement? From: Peter Zijlstra To: Pranith Kumar Cc: LKML In-Reply-To: <430c80e91002090127u1742d043ub29f1c547fe73590@mail.gmail.com> References: <430c80e91002090103l5751d569pd306ca1f0ccca8ba@mail.gmail.com> <430c80e91002090127u1742d043ub29f1c547fe73590@mail.gmail.com> Content-Type: text/plain; charset="UTF-8" Date: Tue, 09 Feb 2010 11:14:16 +0100 Message-ID: <1265710456.11509.181.camel@laptop> Mime-Version: 1.0 X-Mailer: Evolution 2.28.1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2010-02-09 at 14:57 +0530, Pranith Kumar wrote: > I recently happened to come across this thesis[1] which > presents some very concrete results with stats regarding > the performance of Linux CFS with an implementation of Redline. > > It would really be great if you could take some time out of your > busy schedule and quickly look up the figures to see the performance > comparison and if we could adapt some ideas. I am willing to give it > a try if you think its worth it. > [1] http://scholarworks.umass.edu/cgi/viewcontent.cgi?article=1071&context=open_access_dissertations Looks to propose a rather simple semi-static edf based cpu scheduler. If you're interested in that, there is a group actively working on a deadline scheduler for linux: http://lkml.org/lkml/2009/10/16/161