From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S935397AbdCWUug (ORCPT ); Thu, 23 Mar 2017 16:50:36 -0400 Received: from hqemgate14.nvidia.com ([216.228.121.143]:1859 "EHLO hqemgate14.nvidia.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932359AbdCWUue (ORCPT ); Thu, 23 Mar 2017 16:50:34 -0400 X-PGP-Universal: processed; by hqpgpgate101.nvidia.com on Thu, 23 Mar 2017 13:50:32 -0700 Message-ID: <58D43490.3080807@nvidia.com> Date: Thu, 23 Mar 2017 13:48:16 -0700 From: Sai Gurrappadi User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.7.0 MIME-Version: 1.0 To: "Rafael J. Wysocki" , Linux PM , Peter Zijlstra CC: LKML , Srinivas Pandruvada , Viresh Kumar , Juri Lelli , Vincent Guittot , Patrick Bellasi , Joel Fernandes , Morten Rasmussen , Ingo Molnar , Thomas Gleixner , Peter Boonstoppel Subject: Re: [RFC][PATCH v3 2/2] cpufreq: schedutil: Avoid reducing frequency of busy CPUs prematurely References: <4366682.tsferJN35u@aspire.rjw.lan> <2185243.flNrap3qq1@aspire.rjw.lan> <3300960.HE4b3sK4dn@aspire.rjw.lan> <2997922.DidfPadJuT@aspire.rjw.lan> <58D42173.2080205@nvidia.com> In-Reply-To: <58D42173.2080205@nvidia.com> X-NVConfidentiality: public Content-Type: text/plain; charset="windows-1252" Content-Transfer-Encoding: 7bit X-Originating-IP: [172.17.187.121] X-ClientProxiedBy: HQMAIL106.nvidia.com (172.18.146.12) To HQMAIL101.nvidia.com (172.20.187.10) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 03/23/2017 12:26 PM, Sai Gurrappadi wrote: > > Hm, sorry I am a bit confused perhaps you could help me understand the problem/solution better :) > > Say we have the this simple case of only a single periodic task running on one CPU, wouldn't the PELT update on wakeup cause a frequency update which updates the sg_cpu->saved_idle_calls value here? That would then cause the frequency update on idle entry to always skip dropping frequency right? Apologies, this example here is flawed because on task dequeue, its utilization isn't removed. There is no problem in this case... -Sai