[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <jhjzh2xtp45.mognet@arm.com>
Date: Tue, 01 Dec 2020 17:25:46 +0000
From: Valentin Schneider <valentin.schneider@....com>
To: Viresh Kumar <viresh.kumar@...aro.org>
Cc: Ingo Molnar <mingo@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Vincent Guittot <vincent.guittot@...aro.org>,
Amit Daniel Kachhap <amit.kachhap@...il.com>,
Daniel Lezcano <daniel.lezcano@...aro.org>,
Javi Merino <javi.merino@...nel.org>,
Zhang Rui <rui.zhang@...el.com>,
Amit Kucheria <amitk@...nel.org>, linux-kernel@...r.kernel.org,
Quentin Perret <qperret@...gle.com>,
Lukasz Luba <lukasz.luba@....com>, linux-pm@...r.kernel.org
Subject: Re: [PATCH V3 2/2] thermal: cpufreq_cooling: Reuse sched_cpu_util() for SMP platforms
Hi Viresh,
On 19/11/20 07:38, Viresh Kumar wrote:
> As can be clearly seen, the load and requested_power numbers are simply
> incorrect in the idle time based approach and the numbers collected from
> CPU's utilization are much closer to the reality.
>
PELT time-scaling can make the util signals behave strangely from an
external PoV. For instance, on a big.LITTLE system, the rq util of a LITTLE
CPU may suddenly drop if it was stuck on a too-low OPP for some time and
eventually reached the "right" OPP (i.e. got idle time).
Also, as Peter pointed out in [1], task migrations can easily confuse an
external observer that considers util to be "an image of the recent past".
This will need testing on asymmetric CPU capacity systems, IMO.
[1]: https://lore.kernel.org/r/20201120075527.GB2414@hirez.programming.kicks-ass.net
Powered by blists - more mailing lists