Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753880AbYLSNba (ORCPT ); Fri, 19 Dec 2008 08:31:30 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752697AbYLSNbW (ORCPT ); Fri, 19 Dec 2008 08:31:22 -0500 Received: from e28smtp02.in.ibm.com ([59.145.155.2]:44235 "EHLO e28smtp02.in.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750874AbYLSNbV (ORCPT ); Fri, 19 Dec 2008 08:31:21 -0500 Date: Fri, 19 Dec 2008 19:04:24 +0530 From: Vaidyanathan Srinivasan To: Ingo Molnar Cc: Linux Kernel , Suresh B Siddha , Venkatesh Pallipadi , Peter Zijlstra , Dipankar Sarma , Balbir Singh , Vatsa , Gautham R Shenoy , Andi Kleen , David Collier-Brown , Tim Connors , Max Krasnyansky , Gregory Haskins , Pavel Machek , Andrew Morton Subject: Re: [PATCH v7 0/8] Tunable sched_mc_power_savings=n Message-ID: <20081219133424.GG22463@dirshya.in.ibm.com> Reply-To: svaidy@linux.vnet.ibm.com References: <20081218175313.29812.4781.stgit@drishya.in.ibm.com> <20081218201938.GB12376@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline In-Reply-To: <20081218201938.GB12376@elte.hu> User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3498 Lines: 83 * Ingo Molnar [2008-12-18 21:19:38]: > > * Vaidyanathan Srinivasan wrote: > > > Hi, > > > > The existing power saving loadbalancer CONFIG_SCHED_MC attempts to run > > the workload in the system on minimum number of CPU packages and tries > > to keep rest of the CPU packages idle for longer duration. Thus > > consolidating workloads to fewer packages help other packages to be in > > idle state and save power. The current implementation is very > > conservative and does not work effectively across different workloads. > > Initial idea of tunable sched_mc_power_savings=n was proposed to enable > > tuning of the power saving load balancer based on the system > > configuration, workload characteristics and end user requirements. > > > > The power savings and performance of the given workload in an under > > utilised system can be controlled by setting values of 0, 1 or 2 to > > /sys/devices/system/cpu/sched_mc_power_savings with 0 being highest > > performance and least power savings and level 2 indicating maximum power > > savings even at the cost of slight performance degradation. > > > > Please refer to the following discussions and article for details. > > > > [1]Making power policy just work > > http://lwn.net/Articles/287924/ > > > > [2][RFC v1] Tunable sched_mc_power_savings=n > > http://lwn.net/Articles/287882/ > > > > v2: http://lwn.net/Articles/297306/ > > v3: http://lkml.org/lkml/2008/11/10/260 > > v4: http://lkml.org/lkml/2008/11/21/47 > > v5: http://lkml.org/lkml/2008/12/11/178 > > v6: http://lwn.net/Articles/311830/ > > > > The following series of patch demonstrates the basic framework for > > tunable sched_mc_power_savings. > > > > This version of the patch incorporates comments and feedback received > > on the previous post from Andrew Morton. > > > > Changes form v6: > > ---------------- > > * Convert BALANCE_FOR_xx_POWER and related macros to inline functions > > based on comments from Andrew and Ingo. > > * Ran basic kernelbench test and did not see any performance variation > > due to the changes. > > > > Changes form v5: > > --------------- > > * Fixed the sscanf bug and checking for (p->flags & PF_KTHREAD) > > * Dropped the RFC prefix to indicate that the patch is ready for > > testing and inclusion > > * Patch series against 2.6.28-rc8 kernel > > thanks, applied - and i started testing them. It needed some help here and > there to resolve conflicts with pending cpumask changes. Could you please > double-check the merged up end result in the latest scheduler devel tree: > > http://people.redhat.com/mingo/tip.git/README Hi Ingo, I reviewed and tested the tip tree. The merge looks good. I did not find any other cpumask API warnings after the one you have fixed in commit 220e7f617826e0527bbc523ba859f6a4bae0bfe1 Results in tip at: 2.6.28-rc8-tip-sv-01393-gc79978a SchedMC Run Time Package Idle Energy Power 0 80.50 51.47% 54.00% 1.00x J 1.00y W 1 78.89 43.37% 62.86% 0.95x J 0.97y W 2 75.37 30.28% 76.00% 0.91x J 0.98y W Thanks, Vaidy -- 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/