Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759985AbXINMEO (ORCPT ); Fri, 14 Sep 2007 08:04:14 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753022AbXINMD6 (ORCPT ); Fri, 14 Sep 2007 08:03:58 -0400 Received: from scrub.xs4all.nl ([194.109.195.176]:3601 "EHLO scrub.xs4all.nl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752509AbXINMD5 (ORCPT ); Fri, 14 Sep 2007 08:03:57 -0400 Date: Fri, 14 Sep 2007 14:04:28 +0200 (CEST) From: Roman Zippel X-X-Sender: roman@scrub.home To: Peter Zijlstra cc: Ingo Molnar , linux-kernel@vger.kernel.org, Mike Galbraith Subject: Re: [announce] CFS-devel, performance improvements In-Reply-To: <1189703165.21778.258.camel@twins> Message-ID: References: <20070911200459.GA6974@elte.hu> <20070913075258.GA9173@elte.hu> <20070913142842.GA26016@elte.hu> <1189703165.21778.258.camel@twins> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1529 Lines: 43 Hi, On Thu, 13 Sep 2007, Peter Zijlstra wrote: > On Thu, 2007-09-13 at 18:50 +0200, Roman Zippel wrote: > > > I never claimed to understand every detail of CFS, I can _guess_ what > > _might_ have been intended, but from that it's impossible to know for > > certain how important they are. Let's take this patch fragment: > > > > delta_fair = se->delta_fair_sleep; > > we slept that much > > > - /* > > - * Fix up delta_fair with the effect of us running > > - * during the whole sleep period: > > - */ > > - if (sched_feat(SLEEPER_AVG)) > > - delta_fair = div64_likely32((u64)delta_fair * load, > > - load + se->load.weight); > > if we would have ran we would not have been removed from the rq and the > weight would have been: rq_weight + weight > > so compensate for us having been removed from the rq by scaling the > delta with: rq_weight/(rq_weight + weight) > > > - delta_fair = calc_weighted(delta_fair, se); > > scale for nice levels AFAICT the compensation part is already done by the scaling part, without the load part it largely mirrors what __update_stats_wait_end() does, i.e. it gets the same time as other tasks, which have been on the rq. bye, Roman - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/