linux-kernel - Re: [PATCH V3 2/2] thermal: cpufreq_cooling: Reuse sched_cpu

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<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