Re: [RFC PATCH 0/1] sched/pelt: Change PELT halflife at runtime

[Dietmar Eggemann <dietmar.eggemann@arm.com>]

+ Kajetan Puchalski <kajetan.puchalski@arm.com>

On 20/09/2022 16:07, Jian-Min Liu wrote:
> 
> Update some test data in android phone to support switching PELT HL 
> is helpful functionality.
> 
> We switch runtime PELT HL during runtime by difference scenario e.g.
> pelt8 in playing game, pelt32 in camera video. Support runntime
> switching PELT HL is flexible for different workloads.
> 
> the below table show performance & power data points: 
> 
> ---------------------------------------------------------------------
> --|                      | PELT
> halflife                                |
> |                      |----------------------------------------------|
> |                      |       32      |       16      |       8      |
> |                      |----------------------------------------------|
> |                      | avg  min  avg | avg  min  avg | avg  min  avg|
> | Scenarios            | fps  fps  pwr | fps  fps  pwr | fps  fps  pwr|
> |---------------------------------------------------------------------|
> | HOK game 60fps       | 100  100  100 | 105 *134* 102 | 104 *152* 106|
> | HOK game 90fps       | 100  100  100 | 101 *114* 101 | 103 *129* 105|
> | HOK game 120fps      | 100  100  100 | 102 *124* 102 | 105 *134* 105|
> | FHD video rec. 60fps | 100  100  100 | n/a  n/a  n/a | 100  100  103|
> | Camera snapshot      | 100  100  100 | n/a  n/a  n/a | 100  100  102|
> -----------------------------------------------------------------------
> 
> HOK ... Honour Of Kings, Video game
> FHD ... Full High Definition
> fps ... frame per second
> pwr ... power consumption
> 
> table values are in %

I assume that you are specifically interested in those higher min fps
numbers which can be achieved with a tolerable energy consumption
increase when running the game with 16ms or even 8ms PELT halflife.

We see a similar effect when running the UI performance benchmark
Jankbench.

So you need this runtime-switchable PELT multiplier. Would this sched
feature interface:

https://lkml.kernel.org/r/YwyOzgbbUbB+JmSH@hirez.programming.kicks-ass.net

be sufficient for you? People don't like to support `changing PELT
halflife` via an official sysctl.

[...]