From mboxrd@z Thu Jan 1 00:00:00 1970 From: Arjan van de Ven Subject: Re: [RFC][PATCH v5 00/14] sched: packing tasks Date: Mon, 11 Nov 2013 10:20:17 -0800 Message-ID: <52811FE1.2020404@linux.intel.com> References: <1382097147-30088-1-git-send-email-vincent.guittot@linaro.org> <20131111163630.GD26898@twins.programming.kicks-ass.net> <52810851.4090907@linux.intel.com> <20131111181805.GE29572@arm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from mga14.intel.com ([143.182.124.37]:45333 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754975Ab3KKSUU (ORCPT ); Mon, 11 Nov 2013 13:20:20 -0500 In-Reply-To: <20131111181805.GE29572@arm.com> Sender: linux-pm-owner@vger.kernel.org List-Id: linux-pm@vger.kernel.org To: Catalin Marinas Cc: Peter Zijlstra , Vincent Guittot , Linux Kernel Mailing List , Ingo Molnar , Paul Turner , Morten Rasmussen , Chris Metcalf , Tony Luck , "alex.shi@intel.com" , Preeti U Murthy , linaro-kernel , "len.brown@intel.com" , "l.majewski@samsung.com" , Jonathan Corbet , "Rafael J. Wysocki" , Paul McKenney , "linux-pm@vger.kernel.org" On 11/11/2013 10:18 AM, Catalin Marinas wrote: > > Even for symmetric configuration, the cost of moving a task to a CPU > includes wake-up cost plus the run-time cost which depends on the > P-state after wake-up (that's much trickier since we can't easily > estimate the cost of a P-state and it may change once you place a task > on it). yup including cache refill times (assuming you picked C states that flushed the cache, which will be the common case... but even if not, since you're moving at task the likelyhood of cache coldness is high)