Re: [PATCH v2 3/3] cpufreq: schedutil: map raw required frequency to driver frequency
From: Steve Muckle
Date: Mon May 30 2016 - 12:48:42 EST
On Fri, May 27, 2016 at 01:41:02PM +0800, Wanpeng Li wrote:
> 2016-05-26 10:53 GMT+08:00 Steve Muckle <steve.muckle@xxxxxxxxxx>:
> > The slow-path frequency transition path is relatively expensive as it
> > requires waking up a thread to do work. Should support be added for
> > remote CPU cpufreq updates that is also expensive since it requires an
> > IPI. These activities should be avoided if they are not necessary.
> > To that end, calculate the actual driver-supported frequency required by
> > the new utilization value in schedutil by using the recently added
> > cpufreq_driver_resolve_freq callback. If it is the same as the
> > previously requested driver frequency then there is no need to continue
> > with the update assuming the cpu frequency limits have not changed. This
> > will have additional benefits should the semantics of the rate limit be
> > changed to apply solely to frequency transitions rather than to
> > frequency calculations in schedutil.
> sugov_should_update_freq() still be called before get_nex_freq() after
> the patch applied, so rate limit still apply to both frequency
> transitions and frequency calculations, right?
Yes this series does not change the semantics of the rate limit. It
only includes the changes required for resolving raw target frequencies
to driver-supported frequencies so redundant operations can be avoided.
FWIW the approach I took to change the rate_limit semantics  just
moves where last_freq_update_time is set. I was going to return to that
once these changes are complete.