From: John Ogness <john.ogness@linutronix.de>
To: "KHUENY.Gerhard" <Gerhard.KHUENY@bachmann.info>
Cc: "KHUENY.Gerhard" <Gerhard.KHUENY@bachmann.info>,
"'linux-rt-users@vger.kernel.org'"
<linux-rt-users@vger.kernel.org>
Subject: Re: Realtime throttling and Real-Time group scheduling
Date: Tue, 21 Oct 2025 16:49:36 +0206 [thread overview]
Message-ID: <87frbce2nb.fsf@jogness.linutronix.de> (raw)
In-Reply-To: <AM9PR05MB77775F0B030DB96B505F00FB9BF2A@AM9PR05MB7777.eurprd05.prod.outlook.com>
On 2025-10-21, KHUENY.Gerhard <Gerhard.KHUENY@bachmann.info> wrote:
>> > I'm running a 6.12.39-rt Linux kernel and have been experimenting with
>> > runtime throttling on my embedded hardware. However, it seems that
>> > the settings for sched_rt_period_us and sched_rt_runtime_us have no
>> > effect. In my kernel configuration, CONFIG_RT_GROUP_SCHED is not set.
>> >
>> > Is my understanding correct that CONFIG_RT_GROUP_SCHED is not required
>> > to throttle real-time tasks?
>>
>> Yes. But instead of adjusting "throttling", you adjust the guaranteed
>> bandwidth for !rt tasks. You can read about the fair deadline server in its
>> original commit message [0].
>>
>> Basically you can adjust these debugfs files:
>>
>> /sys/kernel/debug/sched/fair_server/cpu*/runtime
>>
>> to guarantee bandwith for !rt tasks.
>>
>> And yes, we are aware that proper documentation for this is missing.
>>
>> John Ogness
>>
>> [0]
>> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/Do
>> cumentation?&id=a110a81c52a9de73e2e57e826dd3bf0fd4c22226
>
> Thanks for clarification. So this means that if CONFIG_RT_GROUP_SCHED
> is not set, the parameters /proc/sys/kernel/sched_rt_period and
> /proc/sys/kernel/sched_rt_runtime have no effect?
They have no effect on the "RT throttling" feature, which does not exist
for CONFIG_RT_GROUP_SCHED=n. See where it was removed here [1].
However, the parameters are still used for admission control of
SCHED_DEADLINE tasks. And likewise they also affect what values can be
written to /sys/kernel/debug/sched/fair_server/cpu*/runtime to configure
the fair deadline server.
Note that this is all new starting with v6.12.
John Ogness
[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=5f6bd380c7bdbe10f7b4e8ddcceed60ce0714c6d
prev parent reply other threads:[~2025-10-21 14:43 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-20 8:54 Realtime throttling and Real-Time group scheduling KHUENY.Gerhard
2025-10-20 9:36 ` John Ogness
2025-10-21 9:13 ` KHUENY.Gerhard
2025-10-21 14:43 ` John Ogness [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87frbce2nb.fsf@jogness.linutronix.de \
--to=john.ogness@linutronix.de \
--cc=Gerhard.KHUENY@bachmann.info \
--cc=linux-rt-users@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.