From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756286AbXD2Hzd (ORCPT ); Sun, 29 Apr 2007 03:55:33 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756314AbXD2Hzd (ORCPT ); Sun, 29 Apr 2007 03:55:33 -0400 Received: from holomorphy.com ([66.93.40.71]:47779 "EHLO holomorphy.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756286AbXD2Hyy (ORCPT ); Sun, 29 Apr 2007 03:54:54 -0400 Date: Sun, 29 Apr 2007 00:54:36 -0700 From: William Lee Irwin III To: Willy Tarreau Cc: Ingo Molnar , Kasper Sandberg , Linus Torvalds , Andrew Morton , Gene Heskett , linux-kernel@vger.kernel.org, Con Kolivas , Nick Piggin , Mike Galbraith , Arjan van de Ven , Peter Williams , Thomas Gleixner , caglar@pardus.org.tr, Mark Lord , Zach Carter , buddabrod Subject: Re: [patch] CFS scheduler, -v6 Message-ID: <20070429075436.GZ31925@holomorphy.com> References: <1177596399.14496.1.camel@localhost> <200704261041.04838.gene.heskett@gmail.com> <1177618164.14496.5.camel@localhost> <20070427115344.GA30706@elte.hu> <20070427115526.GA7699@elte.hu> <1177774551.21279.8.camel@localhost> <1177809512.9756.10.camel@localhost> <20070429053022.GB23638@1wt.eu> <20070429065900.GB32281@elte.hu> <20070429071627.GC23638@1wt.eu> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20070429071627.GC23638@1wt.eu> Organization: The Domain of Holomorphy User-Agent: Mutt/1.5.13 (2006-08-11) Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Sun, Apr 29, 2007 at 09:16:27AM +0200, Willy Tarreau wrote: > In fact, what I'd like to see in 2.6.22 is something better for everybody > and with *no* regression, even if it's not perfect. I had the feeling > that SD matched that goal right now, except for Mike who has not tested > recent versions. Don't get me wrong, I still think that CFS is a more > interesting long-term target. But it may require more time to satisfy > everyone. At least with one of them in 2.6.22, we won't waste time > comparing to current mainline. I think it'd be a good idea to merge scheduler classes before changing over the policy so future changes to policy have smaller code impact. Basically, get scheduler classes going with the mainline scheduler. There are other pieces that can be merged earlier, too, for instance, the correction to the comment in init/main.c. Directed yields can probably also go in as nops or -ENOSYS returns if not fully implemented, though I suspect there shouldn't be much in the way of implementing them. p->array vs. p->on_rq can be merged early too. Common code for rbtree- based priority queues can be factored out of cfq, cfs, and hrtimers. There are extensive /proc/ reporting changes, large chunks of which could go in before the policy as well. I'm camping in this weekend, so I'll see what I can eke out. -- wli