linux-kernel - Re: [Patch v9 1/8] sched/pelt: Add support to track thermal pressure

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]

Date:   Thu, 13 Feb 2020 20:11:19 +0530
From:   Amit Kucheria <amit.kucheria@...durent.com>
To:     Thara Gopinath <thara.gopinath@...aro.org>
Cc:     Ingo Molnar <mingo@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>, ionela.voinescu@....com,
        Vincent Guittot <vincent.guittot@...aro.org>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Zhang Rui <rui.zhang@...el.com>, qperret@...gle.com,
        Daniel Lezcano <daniel.lezcano@...aro.org>,
        Viresh Kumar <viresh.kumar@...aro.org>,
        Steven Rostedt <rostedt@...dmis.org>,
        Will Deacon <will@...nel.org>,
        Catalin Marinas <catalin.marinas@....com>,
        Sudeep Holla <sudeep.holla@....com>,
        Juri Lelli <juri.lelli@...hat.com>, corbet@....net,
        LKML <linux-kernel@...r.kernel.org>,
        Amit Daniel Kachhap <amit.kachhap@...il.com>,
        Javi Merino <javi.merino@...nel.org>
Subject: Re: [Patch v9 1/8] sched/pelt: Add support to track thermal pressure

On Thu, Feb 13, 2020 at 7:41 PM Thara Gopinath
<thara.gopinath@...aro.org> wrote:
>
> On 02/13/2020 07:29 AM, Amit Kucheria wrote:
> > On Wed, Jan 29, 2020 at 4:06 AM Thara Gopinath
> > <thara.gopinath@...aro.org> wrote:
> >>

<snip>

> >> + * Unlike rt/dl utilization tracking that track time spent by a cpu
> >> + * running a rt/dl task through util_avg, the average thermal pressure is
> >> + * tracked through load_avg. This is because thermal pressure signal is
> >> + * weighted "delta" capacity and is not binary(util_avg is binary). "delta
> >
> > May I suggest a slight rewording here and in the commit description,
> >
> >    This is because the thermal pressure signal is weighted "delta"
> > capacity unlike util_avg which is binary.
>
> Sure! Will fix it.
>
> >
> > It would also help, if you expanded on what you mean by binary in the
> > commit description and how the delta capacity is weighted.
>
> I don't understand this. Binary means  0 or 1.

So the value returned by util_avg is literally 0 or 1? In which case
ignore my comment. I'll read the math again later.

> delta capacity is time
> weighted, i will update this.

Thanks.