lkml.org 
[lkml]   [2018]   [Mar]   [20]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRE: [PATCHv2 0/7] sched/fair: Migrate 'misfit' tasks on asymmetric capacity systems
Date
Hi

> -----Original Message-----
> From: Morten Rasmussen [mailto:morten.rasmussen@arm.com]
> Sent: Thursday, March 15, 2018 11:47 PM
> To: peterz@infradead.org; mingo@redhat.com
> Cc: valentin.schneider@arm.com; dietmar.eggemann@arm.com; vincent.guittot@linaro.org; Gaku Inami
> <gaku.inami.xh@renesas.com>; linux-kernel@vger.kernel.org; Morten Rasmussen <morten.rasmussen@arm.com>
> 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@renesas.com>

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]

\
 
 \ /
  Last update: 2018-03-20 06:30    [W:0.104 / U:0.388 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site