lkml.org 
[lkml]   [2021]   [Apr]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: [PATCH v4 3/3] sched/fair: Introduce a CPU capacity comparison helper
Date
On 06/04/21 17:37, Dietmar Eggemann wrote:
> On 01/04/2021 21:30, Valentin Schneider wrote:
>> While at it, replace group_smaller_{min, max}_cpu_capacity() with
>> comparisons of the source group's min/max capacity and the destination
>> CPU's capacity.
>
> IMHO, you haven't mentioned why you replace local sched group with dst
> CPU. I can see that only the capacity of the dst CPU makes really sense
> here. Might be worth mentioning in the patch header why. There is some
> of it in v3 6/7 but that's a different change.
>

Right, some of it got lost in the shuffling. This was a separate change in
v1 (4/8). I can reuse that changelog into:

"""
Also note that comparing capacity extrema of local and source sched_group's
doesn't make much sense when at the day of the day the imbalance will be
pulled by a known env->dst_cpu, whose capacity can be anywhere within the
local group's capacity extrema.

While at it, replace group_smaller_{min, max}_cpu_capacity() with
comparisons of the source group's min/max capacity and the destination
CPU's capacity.
"""

> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
>
> [...]

\
 
 \ /
  Last update: 2021-04-06 18:00    [W:0.047 / U:0.160 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site