[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <YCGAYEiyTKCO71E3@cmpxchg.org>
Date: Mon, 8 Feb 2021 13:18:08 -0500
From: Johannes Weiner <hannes@...xchg.org>
To: Chengming Zhou <zhouchengming@...edance.com>
Cc: mingo@...hat.com, peterz@...radead.org, juri.lelli@...hat.com,
vincent.guittot@...aro.org, rostedt@...dmis.org,
dietmar.eggemann@....com, linux-kernel@...r.kernel.org,
songmuchun@...edance.com
Subject: Re: [PATCH] psi: Add PSI_CPU_FULL state
On Sun, Feb 07, 2021 at 03:24:02PM +0800, Chengming Zhou wrote:
> The FULL state doesn't exist for the CPU resource at the system level,
> but exist at the cgroup level, means all non-idle tasks in a cgroup are
> delayed on the CPU resource which used by others outside of the cgroup.
>
> Co-developed-by: Muchun Song <songmuchun@...edance.com>
> Signed-off-by: Muchun Song <songmuchun@...edance.com>
> Signed-off-by: Chengming Zhou <zhouchengming@...edance.com>
Acked-by: Johannes Weiner <hannes@...xchg.org>
That metric's come up in our production environment recently as well,
it makes a lot of sense.
In addition to outside competition, this also applies to downtimes
enforced by cpu.max - another cgroup usecase that is worth mentioning
in the changelog & code comment.
Thanks
Powered by blists - more mailing lists