From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751377AbbJDG67 (ORCPT ); Sun, 4 Oct 2015 02:58:59 -0400 Received: from LGEAMRELO12.lge.com ([156.147.23.52]:42036 "EHLO lgeamrelo12.lge.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751199AbbJDG66 (ORCPT ); Sun, 4 Oct 2015 02:58:58 -0400 X-Original-SENDERIP: 156.147.1.126 X-Original-MAILFROM: byungchul.park@lge.com X-Original-SENDERIP: 10.177.222.33 X-Original-MAILFROM: byungchul.park@lge.com Date: Sun, 4 Oct 2015 15:58:19 +0900 From: Byungchul Park To: Peter Zijlstra Cc: mingo@kernel.org, linux-kernel@vger.kernel.org, fweisbec@gmail.com, tglx@linutronix.de Subject: Re: [PATCH v3 2/2] sched: consider missed ticks when updating global cpu load Message-ID: <20151004065819.GS6455@byungchulpark-X58A-UD3R> References: <1443771974-27077-1-git-send-email-byungchul.park@lge.com> <1443771974-27077-3-git-send-email-byungchul.park@lge.com> <20151002155906.GD3816@twins.programming.kicks-ass.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20151002155906.GD3816@twins.programming.kicks-ass.net> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Oct 02, 2015 at 05:59:06PM +0200, Peter Zijlstra wrote: > On Fri, Oct 02, 2015 at 04:46:14PM +0900, byungchul.park@lge.com wrote: > > From: Byungchul Park > > > > in hrtimer_interrupt(), the first tick_program_event() can be failed > > because the next timer could be already expired due to, > > (see the comment in hrtimer_interrupt()) > > > > - tracing > > - long lasting callbacks > > If anything keeps interrupts disabled for longer than 1 tick, you'd > better go fix that. tracing and long lasting callbacks are not my case. > > > - being scheduled away when running in a VM this is my case. > > Not sure how much I should care about that, and this patch is completely > wrong for that anyhow. do you mean, in upper case, we must assume ticks occur with 1 tick interval when update_process_times() is called even though more than 1 tick is actually passed in host? right? i am really wondering it. i would admit i was wrong if what you mean is same as what i understand. > > And this case in hrtimer_interrupt() is basically a fail case, if you > hit that, you've got bigger problems. The solution is to rework things > so you don't get there. > > > > in the case that the first tick_program_event() is failed, the second > > tick_program_event() set the expired time to more than one tick later. > > then next tick can happen after more than one tick, even though tick is > > not stopped by e.g. NOHZ. > > > > when the next tick occurs, update_process_times() -> scheduler_tick() > > -> update_cpu_load_active() is performed, assuming the distance between > > last tick and current tick is 1 tick! it's wrong in this case. thus, > > this abnormal case should be considered in update_cpu_load_active(). > > Everything in update_process_times() assumes 1 tick, just fixing up > one function inside that callchain is wrong -- I've already told you > that. anyway, it's wrong for update_process_times() to assume 1 tick because tick_irq_exit() -> tick_nohz_irq_exit() -> tick_nohz_full_update_tick() -> tick_nohz_restart_sched_tick() can happen at full NOHZ as i already said. in this full NOHZ case for tick to restart from non-idle, 1. update_process_times() -> account_process_tick() must be able to handle more than one tick, or tick_nohz_restart_sched_tick() should handle the case additionally. (i think the latter is better.) i will try to modify the code to handle it if you agree with me. 2. to handle full NOHZ, tick_nohz_restart_sched_tick() should call update_cpu_load_active() instead of update_cpu_load_nohz() with my 1/2 patch and 2/2 patch, or we should modify update_cpu_load_nohz() to know full NOHZ, which currently don't know full NOHZ. (you may agree with the latter.) in any case, 1/2 patch is necessary which current code is absolutely missing. peter, what do you think about my opinion? and about my 1/2 patch? i will modify 2/2 patch depending on your feedback. > > > -- > 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/