From: Peter Zijlstra <peterz@infradead.org>
To: Gabriele Monaco <gmonaco@redhat.com>
Cc: Juri Lelli <juri.lelli@redhat.com>,
linux-kernel@vger.kernel.org, Ingo Molnar <mingo@redhat.com>,
Clark Williams <williams@redhat.com>,
arighi@nvidia.com
Subject: Re: [RFC PATCH] sched/deadline: Avoid dl_server boosting with expired deadline
Date: Sat, 1 Nov 2025 01:08:03 +0100 [thread overview]
Message-ID: <20251101000803.GA2212249@noisy.programming.kicks-ass.net> (raw)
In-Reply-To: <2daa2e6217eeaa239616303626c0d73d808ae947.camel@redhat.com>
On Fri, Oct 31, 2025 at 04:41:22PM +0100, Gabriele Monaco wrote:
> On Fri, 2025-10-31 at 16:20 +0100, Peter Zijlstra wrote:
> > On Fri, Oct 31, 2025 at 02:24:17PM +0100, Gabriele Monaco wrote:
> > >
> > > Different scenario if I have the CPU busy with other tasks (e.g. RT
> > > policies), there I can see the server stopping and starting again.
> > > After I do this I seem to get a different behaviour (even some boosting
> > > after idle), I'm trying to understand what's going on.
> > >
>
> After running some heavy RT workload (stress-ng --cpu 10 --sched rr) I do see
> the server stopping and starting as the models would expect, but somehow it's
> always boosting as soon as it's started.
>
> Apparently dl_defer_running is always 1 in that scenario. Perhaps running idle
> counts as running something too, so it never defers. But I can't really see how
> this happens..
The transition [4], will retain dl_defer_running, such that a timely
re-start of the dl_server can immediately run again.
next prev parent reply other threads:[~2025-11-01 0:08 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-07 12:29 Gabriele Monaco
2025-10-14 9:30 ` Gabriele Monaco
2025-10-14 9:54 ` Peter Zijlstra
2025-10-14 10:05 ` Gabriele Monaco
2025-10-14 10:25 ` Peter Zijlstra
2025-10-14 15:32 ` Gabriele Monaco
2025-10-14 16:01 ` Juri Lelli
2025-10-14 19:33 ` Peter Zijlstra
2025-10-15 5:40 ` Juri Lelli
2025-10-20 14:11 ` Peter Zijlstra
2025-10-22 10:11 ` Gabriele Monaco
2025-10-30 18:42 ` Peter Zijlstra
2025-10-31 13:05 ` Peter Zijlstra
2025-10-31 13:24 ` Gabriele Monaco
2025-10-31 15:20 ` Peter Zijlstra
2025-10-31 15:41 ` Gabriele Monaco
2025-10-31 15:44 ` Peter Zijlstra
2025-10-31 15:51 ` Gabriele Monaco
2025-11-01 0:00 ` Peter Zijlstra
2025-11-11 9:58 ` Gabriele Monaco
2025-11-11 11:17 ` Peter Zijlstra
2025-11-11 11:24 ` Peter Zijlstra
2025-11-11 11:37 ` [tip: sched/core] sched/deadline: Fix dl_server stop condition tip-bot2 for Peter Zijlstra
2025-11-01 0:08 ` Peter Zijlstra [this message]
2025-11-01 8:43 ` [RFC PATCH] sched/deadline: Avoid dl_server boosting with expired deadline Gabriele Monaco
2025-11-11 11:37 ` [tip: sched/core] sched/deadline: Fix dl_server time accounting tip-bot2 for Peter Zijlstra
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=20251101000803.GA2212249@noisy.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=arighi@nvidia.com \
--cc=gmonaco@redhat.com \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=williams@redhat.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®