[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20191115115637.GH4131@hirez.programming.kicks-ass.net>
Date: Fri, 15 Nov 2019 12:56:37 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: Vincent Guittot <vincent.guittot@...aro.org>
Cc: linux-kernel <linux-kernel@...r.kernel.org>,
Ingo Molnar <mingo@...hat.com>,
Dietmar Eggemann <dietmar.eggemann@....com>,
Juri Lelli <juri.lelli@...hat.com>,
Steven Rostedt <rostedt@...dmis.org>,
Mel Gorman <mgorman@...e.de>,
Doug Smythies <dsmythies@...us.net>,
"open list:THERMAL" <linux-pm@...r.kernel.org>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Thomas Gleixner <tglx@...utronix.de>,
Sargun Dhillon <sargun@...gun.me>, Tejun Heo <tj@...nel.org>,
Xie XiuQi <xiexiuqi@...wei.com>, xiezhipeng1@...wei.com,
Srinivas Pandruvada <srinivas.pandruvada@...ux.intel.com>
Subject: Re: [PATCH v4] sched/freq: move call to cpufreq_update_util
On Fri, Nov 15, 2019 at 12:03:31PM +0100, Vincent Guittot wrote:
> On Fri, 15 Nov 2019 at 11:51, Peter Zijlstra <peterz@...radead.org> wrote:
> >
> > On Fri, Nov 15, 2019 at 11:46:01AM +0100, Vincent Guittot wrote:
> > > On Fri, 15 Nov 2019 at 11:37, Peter Zijlstra <peterz@...radead.org> wrote:
> >
> > > > Sure, but then it can still remember the value passed in last and use
> > > > that state later.
> > > >
> > > > It doesn't _have_ to completely discard values.
> > >
> > > yes but it means that we run at the "wrong" frequency during this
> > > period and also that the cpufreq must in this case set a kind of timer
> > > to resubmit a new frequency change out of scheduler event
> >
> > But if, as you say, we're completely shutting down the event stream
> > when everything has decayed, that's still true, right?
>
> But It doesn't because there is nothing else to do.
>
> This patch does 2 things:
> - fix the spurious call to cpufreq just before attaching a task
> - make sure cpufreq is still called when cfs is 0 but not irq/rt or dl
>
> There are somehow related but not fully
Right, but when everything is 0, we stop generating events because we
stop calling update_blocked_average(), so there will be a last event
when we hit all 0s and then nothing.
So no superfluous events.
And if that last event if thrown out because of rate-limiting ....
Powered by blists - more mailing lists