Re: [PATCH v6 04/11] cpufreq/schedutil: use rt utilization tracking

From: Quentin Perret <quentin.perret@arm.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Vincent Guittot <vincent.guittot@linaro.org>,
	mingo@kernel.org, linux-kernel@vger.kernel.org,
	rjw@rjwysocki.net, juri.lelli@redhat.com,
	dietmar.eggemann@arm.com, Morten.Rasmussen@arm.com,
	viresh.kumar@linaro.org, valentin.schneider@arm.com,
	patrick.bellasi@arm.com, joel@joelfernandes.org,
	daniel.lezcano@linaro.org, Ingo Molnar <mingo@redhat.com>
Subject: Re: [PATCH v6 04/11] cpufreq/schedutil: use rt utilization tracking
Date: Fri, 22 Jun 2018 16:30:17 +0100	[thread overview]
Message-ID: <20180622153016.GA29031@e108498-lin.cambridge.arm.com> (raw)
In-Reply-To: <20180622152258.GF2512@hirez.programming.kicks-ass.net>

On Friday 22 Jun 2018 at 17:22:58 (+0200), Peter Zijlstra wrote:
> On Fri, Jun 22, 2018 at 01:37:13PM +0200, Peter Zijlstra wrote:
> > That is true.. So we could limit the scaling to the case where there is
> > no idle time, something like:
> > 
> > 	util = sg_cpu->util_cfs;
> > 
> > 	cap_cfs = (1024 - (sg_cpu->util_rt + ...));
> > 	if (util == cap_cfs)
> > 		util = sg_cpu->max;
> > 
> 
> OK, it appears this is more or less what the patches do. And I think
> there's a small risk/hole with this where util ~= cap_cfs but very close
> due to some unaccounted time.

So Vincent suggested at some point to add a margin to avoid that issue
IIRC. FWIW, this is what the overutilized flag of EAS does. It basically
says, if there isn't enough idle time in the system (cfs_util is too close
to cap_cfs), don't bother looking at the util signals because they'll be
kinda wrong.

So what about something like, go to max freq if overutilized ? Or
something similar on a per cpufreq policy basis ?

Thanks,
Quentin