RE: [PATCH 1/1] intel_pstate: Increase hold-off time before busyness is scaled

From	"Doug Smythies" <dsmythies@telus.net>
Newsgroups	linux.kernel
Subject	RE: [PATCH 1/1] intel_pstate: Increase hold-off time before busyness is scaled
Date	2016-02-19 17:40 +0100
Message-ID	<r3Wg2-7Up-15@gated-at.bofh.it> (permalink)
References	<r3uMO-4Fh-7@gated-at.bofh.it> <r3Rgm-4hQ-7@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

Hi Steph,

On 2016.02.19 03:12 Stephane Gasparini wrote:
>
> The issue you are reporting looks like one we improved on android by using 
> the average pstate instead of using the last requested pstate
>
> We know that this is improving the ffmpeg encoding performance when using the
> load algorithm.
>
> see patch attached
>
> This patch is only applied on get_target_pstate_use_cpu_load however you can give
> it a try on get_target_pstate_use_performance

Yes, that type of patch works on the load based approach.

However, I do not think it works on the performance based approach. Why not?
Well, and if I understand correctly, follow the math and you end up with:

scaled_busy = 100%

scaled_busy = (aperf * 100% / mperf) * (max_pstate / * ((aperf * max_pstate) / mperf))

... Doug

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

[PATCH 1/1] intel_pstate: Increase hold-off time before busyness is scaled Mel Gorman <mgorman@techsingularity.net> - 2016-02-18 12:20 +0100
  Re: [PATCH 1/1] intel_pstate: Increase hold-off time before busyness  is scaled "Rafael J. Wysocki" <rafael@kernel.org> - 2016-02-18 20:50 +0100
    RE: [PATCH 1/1] intel_pstate: Increase hold-off time before busyness is scaled "Doug Smythies" <dsmythies@telus.net> - 2016-02-18 22:10 +0100
      Re: [PATCH 1/1] intel_pstate: Increase hold-off time before busyness  is scaled Mel Gorman <mgorman@techsingularity.net> - 2016-02-19 11:50 +0100
    Re: [PATCH 1/1] intel_pstate: Increase hold-off time before busyness  is scaled "Rafael J. Wysocki" <rafael@kernel.org> - 2016-02-19 00:40 +0100
    Re: [PATCH 1/1] intel_pstate: Increase hold-off time before  busyness is scaled "Pandruvada, Srinivas" <srinivas.pandruvada@intel.com> - 2016-02-19 00:40 +0100
  Re: [PATCH 1/1] intel_pstate: Increase hold-off time before busyness is scaled Stephane Gasparini <stephane.gasparini@linux.intel.com> - 2016-02-19 12:20 +0100
    RE: [PATCH 1/1] intel_pstate: Increase hold-off time before busyness is scaled "Doug Smythies" <dsmythies@telus.net> - 2016-02-19 17:40 +0100

csiph-web