Received-SPF: pass (google.com: domain of linux-kernel+bounces-135599-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
From: Valentin Schneider <vschneid@redhat.com>
To: Alexandru Ardelean <alex@shruggie.ro>, linux-kernel@vger.kernel.org
Cc: mingo@redhat.com, peterz@infradead.org, juri.lelli@redhat.com,
 vincent.guittot@linaro.org, dietmar.eggemann@arm.com, rostedt@goodmis.org,
 bsegall@google.com, mgorman@suse.de, bristot@redhat.com,
 tian.xianting@h3c.com, steffen.aschbacher@stihl.de,
 gregkh@linuxfoundation.org
Subject: Re: [PATCH][V2] sched/rt: Print curr when RT throttling activated
In-Reply-To: <CAH3L5QqZ61H9Fk24R4K3vNdpmvBjnxHaxH7CRTT5Fa3tbot_hg@mail.gmail.com>
References: <20230516122202.954313-1-alex@shruggie.ro>
 <CAH3L5QoBqSOBHhoxSrYw6U34gqTPEhi_RB_Cve-YmBzYj3LXAQ@mail.gmail.com>
 <CAH3L5QqZ61H9Fk24R4K3vNdpmvBjnxHaxH7CRTT5Fa3tbot_hg@mail.gmail.com>
Date: Mon, 08 Apr 2024 17:25:50 +0200
Message-ID: <xhsmho7ajanb5.mognet@vschneid-thinkpadt14sgen2i.remote.csb>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable

On 01/04/24 18:47, Alexandru Ardelean wrote:
> On Thu, Jul 13, 2023 at 11:07=E2=80=AFPM Alexandru Ardelean <alex@shruggi=
e.ro> wrote:
>>
>> On Tue, May 16, 2023 at 3:22=E2=80=AFPM Alexandru Ardelean <alex@shruggi=
e.ro> wrote:
>> >
>> > From: Xianting Tian <tian.xianting@h3c.com>
>> >
>> > We may meet the issue, that one RT thread occupied the cpu by 950ms/1s,
>> > The RT thread maybe is a business thread or other unknown thread.
>> >
>> > Currently, it only outputs the print "sched: RT throttling activated"
>> > when RT throttling happen. It is hard to know what is the RT thread,
>> > For further analysis, we need add more prints.
>> >
>> > This patch is to print current RT task when RT throttling activated,
>> > It help us to know what is the RT thread in the first time.
>> >
>>
>> Adding Greg on this patch, since it 's been a while.
>> And also: ping :)
>
> Ping on this :)
>

AFAIA this has been proposed a few times in the past, the problem is that
printing the current task isn't the right thing to do as it may not be the
one that contributed most of the runtime that lead to throttling.

See https://lore.kernel.org/lkml/20221209163606.53a2370e@gandalf.local.home/