Re: [PATCH 6/8] cpufreq/schedutil: sum per-sched class utilization

From	Peter Zijlstra <peterz@infradead.org>
Newsgroups	linux.kernel
Subject	Re: [PATCH 6/8] cpufreq/schedutil: sum per-sched class utilization
Date	2016-03-16 19:40 +0100
Message-ID	<rdowp-4gp-5@gated-at.bofh.it> (permalink)
References	(1 earlier) <rcteN-7Q2-1@gated-at.bofh.it> <rd4R3-7Rt-7@gated-at.bofh.it> <rdedJ-5Je-41@gated-at.bofh.it> <rdedI-5Je-39@gated-at.bofh.it> <rdomL-4bz-31@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Wed, Mar 16, 2016 at 11:20:45AM -0700, Steve Muckle wrote:
> On 03/16/2016 12:38 AM, Peter Zijlstra wrote:
> > Somewhere in the giant discussions I mentioned that we should be looking
> > at a CPPC like interface and pass {min,max} tuples to the cpufreq
> > selection thingy.
> > 
> > In that same discussion I also mentioned that we must compute min as the
> > hard dl reservation, but that for max we can actually use the avg dl +
> > avg rt + avg cfs.
> > 
> > That way there is far more room for selecting a sensible frequency.
> 
> Doesn't the above min/max policy mean that the platform will likely
> underserve the task load? If avg dl+rt+cfs represents our best estimate
> of the work to be done, I would think that should be the min.

Can't be the min, avg_dl might (and typically will be) must lower than
the worst case utilization estimates.

However if we use that as our min, peaks in DL utilization will not
complete, because we run at too low a frequency.

Therefore, the min must be given by our worst case utilization
reservation, not by the actual avg consumed.

Thread

[PATCH 6/8] cpufreq/schedutil: sum per-sched class utilization Michael Turquette <mturquette@baylibre.com> - 2016-03-14 06:30 +0100
  Re: [PATCH 6/8] cpufreq/schedutil: sum per-sched class utilization Peter Zijlstra <peterz@infradead.org> - 2016-03-15 22:40 +0100
    Re: [PATCH 6/8] cpufreq/schedutil: sum per-sched class utilization Peter Zijlstra <peterz@infradead.org> - 2016-03-16 08:40 +0100
      Re: [PATCH 6/8] cpufreq/schedutil: sum per-sched class utilization Steve Muckle <steve.muckle@linaro.org> - 2016-03-16 19:30 +0100
        Re: [PATCH 6/8] cpufreq/schedutil: sum per-sched class utilization Peter Zijlstra <peterz@infradead.org> - 2016-03-16 19:40 +0100
          Re: [PATCH 6/8] cpufreq/schedutil: sum per-sched class utilization Steve Muckle <steve.muckle@linaro.org> - 2016-03-16 20:20 +0100

csiph-web