From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755892AbXD0OHq (ORCPT ); Fri, 27 Apr 2007 10:07:46 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755943AbXD0OHn (ORCPT ); Fri, 27 Apr 2007 10:07:43 -0400 Received: from mx2.mail.elte.hu ([157.181.151.9]:45504 "EHLO mx2.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755897AbXD0OF0 (ORCPT ); Fri, 27 Apr 2007 10:05:26 -0400 Date: Fri, 27 Apr 2007 16:05:20 +0200 From: Ingo Molnar To: hechacker1 Cc: linux-kernel@vger.kernel.org Subject: Re: "REPORT: sd-0.46 vs cfs-v6 vs mainline 2.6.21-rc7 Beryl + Video + Audio" Message-ID: <20070427140520.GA27854@elte.hu> References: <6700d24e0704262101v132bec29nf9fd6c93fe8748a@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <6700d24e0704262101v132bec29nf9fd6c93fe8748a@mail.gmail.com> User-Agent: Mutt/1.4.2.2i X-ELTE-VirusStatus: clean X-ELTE-SpamScore: -2.0 X-ELTE-SpamLevel: X-ELTE-SpamCheck: no X-ELTE-SpamVersion: ELTE 2.0 X-ELTE-SpamCheck-Details: score=-2.0 required=5.9 tests=BAYES_00 autolearn=no SpamAssassin version=3.0.3 -2.0 BAYES_00 BODY: Bayesian spam probability is 0 to 1% [score: 0.0000] Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org * hechacker1 wrote: > "REPORT: sd-0.46 vs cfs-v6 vs mainline 2.6.21-rc7 Beryl + Video + Audio" thanks for testing it out. one immediate observation i have is that you used a 2msec granularity setting on CFS, but even that did not cause context-switching as high as SD's rr_interval==2 setting: > cfs-v6: > 700m kernel # cat sched_granularity_ns > 2000000 > r b swpd free buff cache si so bi bo in cs us sy id > 1 0 0 100412 44 1519364 0 0 0 0 7426 7634 62 4 34 > 4 0 0 100288 44 1519364 0 0 0 0 7039 7442 60 6 34 > sd-0.46: > 700m kernel # cat rr_interval > 2 > r b swpd free buff cache si so bi bo in cs us sy id > 5 0 0 918052 536 832840 0 0 411 0 2387 15242 89 11 0 > 4 1 0 915600 536 834908 0 0 388 0 2283 15428 90 10 0 so SD context-switched twice as much and saturated the CPU fully, while under cfs-v6 there was 34% idle time left. That double context-switch rate and higher CPU utilization could easily result in you experiencing a 'smoother' desktop (and smoother video playback) on SD. could you try to maximize the preemption ratio on CFS by using a sched_granularity_ns of 0? Does that result in a higher context-switch rate and in better CPU utilization? Thanks, Ingo