From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Doug Smythies" Subject: RE: [RFT][PATCH v7.3 5/8] cpuidle: Return nohz hint from cpuidle_select() Date: Thu, 22 Mar 2018 13:46:49 -0700 Message-ID: <004001d3c21e$e867a3b0$b936eb10$@net> References: <2390019.oHdSGtR3EE@aspire.rjw.lan> <1635957.yuHkCe9oyz@aspire.rjw.lan> z4Bte42s61Konz4ByelYCQ Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: z4Bte42s61Konz4ByelYCQ Content-Language: en-ca Sender: linux-kernel-owner@vger.kernel.org To: "'Rafael J. Wysocki'" Cc: 'Frederic Weisbecker' , 'Thomas Gleixner' , 'Paul McKenney' , 'Thomas Ilsche' , 'Rik van Riel' , 'Aubrey Li' , 'Mike Galbraith' , 'LKML' , 'Linux PM' , 'Peter Zijlstra' List-Id: linux-pm@vger.kernel.org On 2018.03.22 10:40 Rafael J. Wysocki wrote: ...[snip]... >The difference between this and the original v7 (of patch [5/8]) is > what happens in menu_update(). This time next_timer_us is checked > properly and if that is above the tick boundary and a tick wakeup occurs, > the function simply sets mesured_us to a large constant and uses that to > update both the correction factor and data->intervals[] (the particular > value used in this patch was found through a bit of experimentation). > > Let's see how this works for Thomas and Doug. System idle test done for 74 minutes. After boot and after the system settles down for a couple of minutes, Processor package power is constant at 3.7 Watts. (great) Not worth a new graph to show a flat line. V7.3 average package power = 3.68 Watts. V7 average package power = 3.68 Watts V7.2+ average package power = 4.06 Watts (+10%) > For easier testing there is a git branch containing this patch (and the > rest of the series) at: > > git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git \ > idle-loop-v7.3 Thanks. I used this git branch this time and for the first time. Much easier. ... Doug