linux-kernel - Re: [Eas-dev] [PATCH V4 0/3] sched: cpufreq: Allow remote callbacks

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] [day] [month] [year] [list]

Date:   Thu, 27 Jul 2017 20:44:03 -0700
From:   "Joel Fernandes (Google)" <joel.opensrc@...il.com>
To:     Juri Lelli <juri.lelli@....com>
Cc:     Viresh Kumar <viresh.kumar@...aro.org>,
        Joel Fernandes <joelaf@...gle.com>, eas-dev@...ts.linaro.org,
        linux-pm@...r.kernel.org, Peter Zijlstra <peterz@...radead.org>,
        Rafael Wysocki <rjw@...ysocki.net>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Ingo Molnar <mingo@...hat.com>,
        Srinivas Pandruvada <srinivas.pandruvada@...ux.intel.com>,
        Steve Muckle <smuckle.linux@...il.com>,
        Len Brown <lenb@...nel.org>
Subject: Re: [Eas-dev] [PATCH V4 0/3] sched: cpufreq: Allow remote callbacks

On Thu, Jul 27, 2017 at 12:21 AM, Juri Lelli <juri.lelli@....com> wrote:
[..]
>> >
>> > But even without that, if you see the routine
>> > init_entity_runnable_average() in fair.c, the new tasks are
>> > initialized in a way that they are seen as heavy tasks. And so even
>> > for the first time they run, freq should normally increase on the
>> > target CPU (at least with above application).i
>>
>> Ok, but the "heavy" in init_entity_runnable_average means for load,
>> not the util_avg. The util_avg is what's used for frequency scaling
>> IIUC and is set to 0 in that function no?
>>
>
> True for init_entity_runnable_average(), but for new task post_init_
> entity_util_avg() is then also called (from wake_up_new_task()), which
> modifies the initial util_avg value (depending on current rq {util,
> load}_avg.

Got it. That makes sense, thank you!

-Joel