RE: [PATCHv2 0/7] sched/fair: Migrate 'misfit' tasks on asymmetric capacity systems

[Gaku Inami]

Hi

> -----Original Message-----
> From: Morten Rasmussen [mailto:morten.rasmussen@xxxxxxx]
> Sent: Thursday, March 15, 2018 11:47 PM
> To: peterz@xxxxxxxxxxxxx; mingo@xxxxxxxxxx
> Cc: valentin.schneider@xxxxxxx; dietmar.eggemann@xxxxxxx; vincent.guittot@xxxxxxxxxx; Gaku Inami
> <gaku.inami.xh@xxxxxxxxxxx>; linux-kernel@xxxxxxxxxxxxxxx; Morten Rasmussen <morten.rasmussen@xxxxxxx>
> Subject: [PATCHv2 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
> 

I have tested this on our R-Car again and it works well. In addition,
I confirmed that this patch-set also brings performance improvement to
other benchmarks(e.g. memory load latency in LMbench). You can add:

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

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:                          0.9435s
    total time:                          0.9952s
    total time:                          1.3511s
    total time:                          1.6747s

R-Car H3 (misfit)
    total time:                          0.9387s
    total time:                          0.9280s
    total time:                          0.9616s
    total time:                          0.9934s

10 run summary (tracking longest running task for each run)
	R-Car H3
	avg	max
tip     1.6737  1.6758
misfit  0.9980  1.0409

Regards,
Inami

[snip]