From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Lezcano Subject: Re: [PATCH v5] cpuidle: Fix last_residency division Date: Fri, 1 Jul 2016 16:32:06 +0200 Message-ID: <57767EE6.4080108@linaro.org> References: <1467383054-1959-1-git-send-email-shreyas@linux.vnet.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Received: from mail-wm0-f50.google.com ([74.125.82.50]:38180 "EHLO mail-wm0-f50.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752470AbcGAOcI (ORCPT ); Fri, 1 Jul 2016 10:32:08 -0400 Received: by mail-wm0-f50.google.com with SMTP id r201so31906291wme.1 for ; Fri, 01 Jul 2016 07:32:07 -0700 (PDT) In-Reply-To: <1467383054-1959-1-git-send-email-shreyas@linux.vnet.ibm.com> Sender: linux-pm-owner@vger.kernel.org List-Id: linux-pm@vger.kernel.org To: "Shreyas B. Prabhu" , rjw@rjwysocki.net Cc: linux-pm@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, nicolas.pitre@linaro.org, bsingharora@gmail.com On 07/01/2016 04:24 PM, Shreyas B. Prabhu wrote: > Snooze is a poll idle state in powernv and pseries platforms. Snooze > has a timeout so that if a cpu stays in snooze for more than target > residency of the next available idle state, then it would exit thereb= y > giving chance to the cpuidle governor to re-evaluate and > promote the cpu to a deeper idle state. Therefore whenever snooze exi= ts > due to this timeout, its last_residency will be target_residency of n= ext > deeper state. > > commit e93e59ce5b85 ("cpuidle: Replace ktime_get() with local_clock()= ") > changed the math around last_residency calculation. Specifically, whi= le > converting last_residency value from nanoseconds to microseconds it d= oes > right shift by 10. Due to this, in snooze timeout exit scenarios > last_residency calculated is roughly 2.3% less than target_residency = of > next available state. This pattern is picked up get_typical_interval(= ) > in the menu governor and therefore expected_interval in menu_select()= is > frequently less than the target_residency of any state but snooze. > > Due to this we are entering snooze at a higher rate, thereby affectin= g > the single thread performance. > > Fix this by using precise division via ktime_us_delta. > > Reported-by: Anton Blanchard > Bisected-by: Shilpasri G Bhat > Signed-off-by: Shreyas B. Prabhu > --- Acked-by: Daniel Lezcano --=20 Linaro.org =E2=94=82 Open source software fo= r ARM SoCs =46ollow Linaro: Facebook | Twitter | Blog