From: Peter Zijlstra <peterz@infradead.org>
To: John Stultz <jstultz@google.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
K Prateek Nayak <kprateek.nayak@amd.com>,
Joel Fernandes <joelagnelf@nvidia.com>,
Qais Yousef <qyousef@layalina.io>, Ingo Molnar <mingo@redhat.com>,
Juri Lelli <juri.lelli@redhat.com>,
Vincent Guittot <vincent.guittot@linaro.org>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Valentin Schneider <vschneid@redhat.com>,
Steven Rostedt <rostedt@goodmis.org>,
Ben Segall <bsegall@google.com>,
Zimuzo Ezeozue <zezeozue@google.com>,
Mel Gorman <mgorman@suse.de>, Will Deacon <will@kernel.org>,
Waiman Long <longman@redhat.com>,
Boqun Feng <boqun.feng@gmail.com>,
"Paul E. McKenney" <paulmck@kernel.org>,
Metin Kaya <Metin.Kaya@arm.com>,
Xuewen Yan <xuewen.yan94@gmail.com>,
Thomas Gleixner <tglx@linutronix.de>,
Daniel Lezcano <daniel.lezcano@linaro.org>,
Suleiman Souhlal <suleiman@google.com>,
kuyo chang <kuyo.chang@mediatek.com>, hupu <hupu.gm@gmail.com>,
kernel-team@android.com
Subject: Re: [RESEND][PATCH v18 5/8] sched: Fix runtime accounting w/ split exec & sched contexts
Date: Fri, 11 Jul 2025 15:28:42 +0200 [thread overview]
Message-ID: <20250711132842.GG905792@noisy.programming.kicks-ass.net> (raw)
In-Reply-To: <CANDhNCo0u4bdvMxCpoDaZtFFJw5s2KJU=FOeho116p_8LujAfA@mail.gmail.com>
On Thu, Jul 10, 2025 at 10:25:46AM -0700, John Stultz wrote:
> On Thu, Jul 10, 2025 at 2:45 AM Peter Zijlstra <peterz@infradead.org> wrote:
> > On Mon, Jul 07, 2025 at 08:43:52PM +0000, John Stultz wrote:
> > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > > index edcc7d59ecc3b..c34e0891193a7 100644
> > > --- a/kernel/sched/fair.c
> > > +++ b/kernel/sched/fair.c
> > > @@ -1143,30 +1143,40 @@ static void update_tg_load_avg(struct cfs_rq *cfs_rq)
> > > }
> > > #endif /* CONFIG_SMP */
> > >
> > > +static s64 update_se(struct rq *rq, struct sched_entity *se)
> > > {
> > > u64 now = rq_clock_task(rq);
> > > s64 delta_exec;
> > >
> > > + delta_exec = now - se->exec_start;
> > > if (unlikely(delta_exec <= 0))
> > > return delta_exec;
> > >
> > > + se->exec_start = now;
> > > + if (entity_is_task(se)) {
> > > + struct task_struct *donor = task_of(se);
> > > + struct task_struct *running = rq->curr;
> > > + /*
> > > + * If se is a task, we account the time against the running
> > > + * task, as w/ proxy-exec they may not be the same.
> > > + */
> > > + running->se.exec_start = now;
> > > + running->se.sum_exec_runtime += delta_exec;
> > >
> > > + trace_sched_stat_runtime(running, delta_exec);
> > > + account_group_exec_runtime(running, delta_exec);
> > >
> > > + /* cgroup time is always accounted against the donor */
> > > + cgroup_account_cputime(donor, delta_exec);
> > > + } else {
> > > + /* If not task, account the time against donor se */
> > > + se->sum_exec_runtime += delta_exec;
> > > }
> >
> > Bah.. this is all terrible :-) But yeah, I suppose this wil do.
>
> Yeah, :/ I'm happy to rework it further if you have ideas.
Not really; I stared at this for a bit yesterday. Its a confusing mess,
but I didn't come up with anything better.
next prev parent reply other threads:[~2025-07-11 13:28 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-07 20:43 [RESEND][PATCH v18 0/8] Single RunQueue Proxy Execution (v18) John Stultz
2025-07-07 20:43 ` [RESEND][PATCH v18 1/8] sched: Add CONFIG_SCHED_PROXY_EXEC & boot argument to enable/disable John Stultz
2025-07-07 20:43 ` [RESEND][PATCH v18 2/8] locking/mutex: Rework task_struct::blocked_on John Stultz
2025-07-07 20:43 ` [RESEND][PATCH v18 3/8] locking/mutex: Add p->blocked_on wrappers for correctness checks John Stultz
2025-07-08 6:43 ` K Prateek Nayak
2025-07-09 4:50 ` John Stultz
2025-07-07 20:43 ` [RESEND][PATCH v18 4/8] sched: Move update_curr_task logic into update_curr_se John Stultz
2025-07-07 20:43 ` [RESEND][PATCH v18 5/8] sched: Fix runtime accounting w/ split exec & sched contexts John Stultz
2025-07-10 9:45 ` Peter Zijlstra
2025-07-10 17:25 ` John Stultz
2025-07-11 13:28 ` Peter Zijlstra [this message]
2025-07-07 20:43 ` [RESEND][PATCH v18 6/8] sched: Add an initial sketch of the find_proxy_task() function John Stultz
2025-07-10 10:02 ` Peter Zijlstra
2025-07-11 0:43 ` John Stultz
2025-07-11 13:30 ` Peter Zijlstra
2025-07-12 3:58 ` John Stultz
2025-07-07 20:43 ` [RESEND][PATCH v18 7/8] sched: Fix proxy/current (push,pull)ability John Stultz
2025-07-07 20:43 ` [RESEND][PATCH v18 8/8] sched: Start blocked_on chain processing in find_proxy_task() John Stultz
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=20250711132842.GG905792@noisy.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=Metin.Kaya@arm.com \
--cc=boqun.feng@gmail.com \
--cc=bsegall@google.com \
--cc=daniel.lezcano@linaro.org \
--cc=dietmar.eggemann@arm.com \
--cc=hupu.gm@gmail.com \
--cc=joelagnelf@nvidia.com \
--cc=jstultz@google.com \
--cc=juri.lelli@redhat.com \
--cc=kernel-team@android.com \
--cc=kprateek.nayak@amd.com \
--cc=kuyo.chang@mediatek.com \
--cc=linux-kernel@vger.kernel.org \
--cc=longman@redhat.com \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=paulmck@kernel.org \
--cc=qyousef@layalina.io \
--cc=rostedt@goodmis.org \
--cc=suleiman@google.com \
--cc=tglx@linutronix.de \
--cc=vincent.guittot@linaro.org \
--cc=vschneid@redhat.com \
--cc=will@kernel.org \
--cc=xuewen.yan94@gmail.com \
--cc=zezeozue@google.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 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.