linux-kernel - Re: [RFC PATCH] sched: fair: reset task_group.load

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date: Thu, 21 Dec 2023 16:26:30 +0100
From: Vincent Guittot <vincent.guittot@...aro.org>
To: Aaron Lu <aaron.lu@...el.com>
Cc: Imran Khan <imran.f.khan@...cle.com>, mingo@...hat.com, peterz@...radead.org, 
	juri.lelli@...hat.com, dietmar.eggemann@....com, rostedt@...dmis.org, 
	bsegall@...gle.com, mgorman@...e.de, bristot@...hat.com, vschneid@...hat.com, 
	linux-kernel@...r.kernel.org
Subject: Re: [RFC PATCH] sched: fair: reset task_group.load_avg when there are
 no running tasks.

Hi Aaron,

On Thu, 21 Dec 2023 at 09:21, Aaron Lu <aaron.lu@...el.com> wrote:
>
> Hi Vincent,
>
> Thanks for the heads up.
>
> On Wed, Dec 20, 2023 at 06:31:08PM +0100, Vincent Guittot wrote:
> > Aaron,
> > Could you run the tests that you run for testing "Ratelimit update to
> > tg->load_avg" and check if this patch impacts your performance ?
>
> I run hackbench/netperf/postgres_sysbench with nr_thread=nr_cpu on a 2
> sockets/120cores/240cpus Intel server and didn't notice any performance
> change after applying your diff so I think it's not a problem.

Thanks for the tests.

I'm going to prepare a proper patch

>
> Regards,
> Aaron