From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755190Ab0IMMb5 (ORCPT ); Mon, 13 Sep 2010 08:31:57 -0400 Received: from mailout-de.gmx.net ([213.165.64.22]:54137 "HELO mail.gmx.net" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with SMTP id S1750871Ab0IMMb4 (ORCPT ); Mon, 13 Sep 2010 08:31:56 -0400 X-Authenticated: #14349625 X-Provags-ID: V01U2FsdGVkX1+1vdomrDO1MZkvSET6HD6kSbzKilwjMY+PfFofbY xLyeb4oGES/hI0 Subject: Re: [RFC patch 1/2] sched: dynamically adapt granularity with nr_running From: Mike Galbraith To: Peter Zijlstra Cc: Ingo Molnar , Mathieu Desnoyers , LKML , Linus Torvalds , Andrew Morton , Steven Rostedt , Thomas Gleixner , Tony Lindgren In-Reply-To: <1284378235.2275.227.camel@laptop> References: <20100911173732.551632040@efficios.com> <20100911174003.051303123@efficios.com> <20100912061452.GA3383@elte.hu> <1284276098.9111.24.camel@marge.simson.net> <20100912181626.GB32327@Krystal> <1284351183.7321.36.camel@marge.simson.net> <20100913064153.GB14728@elte.hu> <1284361716.25120.19.camel@marge.simson.net> <1284366936.2275.27.camel@laptop> <1284369373.14710.11.camel@marge.simson.net> <1284370660.2275.86.camel@laptop> <1284371457.14888.9.camel@marge.simson.net> <1284371756.2275.108.camel@laptop> <1284374728.2275.159.camel@laptop> <1284378235.2275.227.camel@laptop> Content-Type: text/plain Date: Mon, 13 Sep 2010 14:32:18 +0200 Message-Id: <1284381138.7410.4.camel@marge.simson.net> Mime-Version: 1.0 X-Mailer: Evolution 2.24.1.1 Content-Transfer-Encoding: 7bit X-Y-GMX-Trusted: 0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 2010-09-13 at 13:43 +0200, Peter Zijlstra wrote: > On Mon, 2010-09-13 at 12:45 +0200, Peter Zijlstra wrote: > > What we want is real deadlines, the patch provides the infrastructure, > > let me frob something for that. > > Here, real deadline, but totally untested (except for compile). You're fast. Now to see if I can find the early forever Loop :) > Please read through the logic. The idea was to do as we always do, > except keep a deadline on enqueue for now + __sched_period, once we find > that a deadline expired, we force run that task. Yeah, I'll go read/piddle. -Mike