linux-kernel - Re: [RFC PATCH 1/1] sched/pelt: Introduce PELT multiplier

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: <YwzOf5WV5G8dQBGb@hirez.programming.kicks-ass.net>
Date:   Mon, 29 Aug 2022 16:34:39 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Quentin Perret <qperret@...gle.com>
Cc:     Vincent Guittot <vincent.guittot@...aro.org>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Ingo Molnar <mingo@...nel.org>,
        Morten Rasmussen <morten.rasmussen@....com>,
        Vincent Donnefort <vdonnefort@...gle.com>,
        Patrick Bellasi <patrick.bellasi@...bug.net>,
        Abhijeet Dharmapurikar <adharmap@...cinc.com>,
        Jian-Min <Jian-Min.Liu@...iatek.com>,
        Qais Yousef <qais.yousef@....com>, linux-kernel@...r.kernel.org
Subject: Re: [RFC PATCH 1/1] sched/pelt: Introduce PELT multiplier

On Mon, Aug 29, 2022 at 02:23:17PM +0000, Quentin Perret wrote:

> I'll let folks in CC comment about their use-case in more details, but
> there's definitely been an interest in tuning this thing at run-time

An interest and it making sense are two very distinct things that bear
no relation to one another in any way.

> FWIW. Typically a larger half-life will be fine with predictable
> workloads with little inputs from users (e.g. fullscreen video playback)
> while a lower one can be preferred in highly interactive cases (games,

As per always; consider the combined workload.

> ...). The transient state is fun to reason about, but it really
> shouldn't be too common AFAIK.

Once you give away control there is no taking it back, and userspace
*will* do stupid things and expect unicorns.

> With that said I'd quite like to see numbers to back that claim.
> Measuring power while running a video (for instance) with various HL
> values should help. And similarly it shouldn't be too hard to get
> performance numbers.

I'm thinking this all needs far more than mere numbers to justify.