RE: [PATCH 0/7] sched/fair: Migrate 'misfit' tasks on asymmetric capacity systems

[Gaku Inami]

Hi

> -----Original Message-----
> From: linux-kernel-owner@xxxxxxxxxxxxxxx [mailto:linux-kernel-owner@xxxxxxxxxxxxxxx] On Behalf Of Morten Rasmussen
> Sent: Friday, February 16, 2018 1:21 AM
> To: peterz@xxxxxxxxxxxxx; mingo@xxxxxxxxxx
> Cc: valentin.schneider@xxxxxxx; dietmar.eggemann@xxxxxxx; vincent.guittot@xxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx;
> Morten Rasmussen <morten.rasmussen@xxxxxxx>
> Subject: [PATCH 0/7] sched/fair: Migrate 'misfit' tasks on asymmetric capacity systems
> 
<snip>
> 
> The patches have been tested on:
>    1. Arm Juno (r0): 2+4 Cortex A57/A53
>    2. Hikey960: 4+4 Cortex A73/A53
> 
> Test case:
> Big cpus are always kept busy. Pin a shorter running sysbench tasks to
> big cpus, while creating a longer running set of unpinned sysbench
> tasks.

Tested-by: Gaku Inami <gaku.inami.xh@xxxxxxxxxxx>

I tested as same in other SoC. It looks fine.

The patches have been tested on:
   3. Renesas R-Car H3 : 4+4 Cortex A57/A53

Results:
Single runs with completion time of each task
R-Car H3 (tip)
    total time:                          0.9415s
    total time:                          0.9582s
    total time:                          1.3275s
    total time:                          1.6752s

R-Car H3 (misfit)
    total time:                          0.9312s
    total time:                          0.9429s
    total time:                          0.9525s
    total time:                          0.9660s

10 run summary (tracking longest running task for each run)
	R-Car H3
	avg	max
tip     1.6752  1.6753
misfit  0.9890  1.0204

Regards,
Inami