From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754373AbZIHNSq (ORCPT ); Tue, 8 Sep 2009 09:18:46 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754073AbZIHNSo (ORCPT ); Tue, 8 Sep 2009 09:18:44 -0400 Received: from depni.sinp.msu.ru ([213.131.7.21]:52031 "EHLO depni.sinp.msu.ru" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754082AbZIHNSn (ORCPT ); Tue, 8 Sep 2009 09:18:43 -0400 X-Greylist: delayed 1291 seconds by postgrey-1.27 at vger.kernel.org; Tue, 08 Sep 2009 09:18:43 EDT From: Serge Belyshev To: Ingo Molnar Cc: Con Kolivas , linux-kernel@vger.kernel.org, Peter Zijlstra , Mike Galbraith Subject: Epic regression in throughput since v2.6.23 References: <20090906205952.GA6516@elte.hu> Date: Tue, 08 Sep 2009 12:57:09 +0000 In-Reply-To: <20090906205952.GA6516@elte.hu> (Ingo Molnar's message of "Sun, 6 Sep 2009 22:59:52 +0200") Message-ID: <87hbvdiogq.fsf@depni.sinp.msu.ru> User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/23.1 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi. I've done measurments of time taken by make -j4 kernel build on a quadcore box. Results are interesting: mainline kernel has regressed since v2.6.23 release by more than 10%. The following graph is time taken by "make -j4" (median over 9 runs) versus kernel version. The huge (10%) regressions since v2.6.23 is apparent. Note that tip/master c26f010 is better than current mainline. Also note that BFS is significantly better than both and shows the same throughput as vanilla v2.6.23: http://img403.imageshack.us/img403/7029/epicmakej4.png The following plot is a detailed comparison of time taken versus number of parallel jobs. Note that at "make -j4" (which equals number of hardware threads), BFS has the minimum (best performance), and tip/master -- maximum (worst). I've also tested mainline v2.6.31 (not shown on the graph) which produces similar, albeit a bit slower, results as the tip/master. http://img179.imageshack.us/img179/5335/epicbfstip.png Conclusion are 1) mainline has severely regressed since v2.6.23 2) BFS shows optimal performance at make -jN where N equals number of h/w threads, while current mainline scheduler performance is far from optimal in this case.