[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <9d1680de-39e5-609c-7410-7baabfb079e5@gnuweeb.org>
Date: Mon, 2 Aug 2021 19:52:13 +0700
From: Ammar Faizi <ammarfaizi2@...weeb.org>
To: Dietmar Eggemann <dietmar.eggemann@....com>,
Ingo Molnar <mingo@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Juri Lelli <juri.lelli@...hat.com>,
Vincent Guittot <vincent.guittot@...aro.org>,
Steven Rostedt <rostedt@...dmis.org>,
Ben Segall <bsegall@...gle.com>, Mel Gorman <mgorman@...e.de>,
Daniel Bristot de Oliveira <bristot@...hat.com>
Cc: linux-kernel@...r.kernel.org, Ammar Faizi <ammarfaizi2@...il.com>
Subject: Re: WARNING: CPU: 0 PID: 12 at kernel/sched/fair.c:3306
update_blocked_averages+0x941/0x9a0
On 8/2/21 3:42 PM, Dietmar Eggemann wrote:
> So you're running with:
>
> 9e077b52d86a - sched/pelt: Check that *_avg are null when *_sum are
> (2021-06-17 Vincent Guittot)
>
> but not with:
>
> ceb6ba45dc80 - sched/fair: Sync load_sum with load_avg after dequeue
> (2021-07-02 Vincent Guittot)
>
> The SCHED_WARN_ON you're hitting is harmless and just tells you that the
> PELT load_avg and load_sum part of one of your cfs_rq's is not aligned.
> Has to be load (and not util or runnable) since load is the only one
> still not fixed in f55966571d5e.
>
> This should go away once you applied ceb6ba45dc80.
Alright, I have just moved to 5.14-rc4 and doesn't seem to have this
issue anymore.
Thanks for the response, Dietmar.
Ammar
Powered by blists - more mailing lists