Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.34 as permitted sender) client-ip=23.128.96.34;
Sender: Ingo Molnar <mingo.kernel.org@gmail.com>
Date:   Mon, 25 Sep 2023 10:27:36 +0200
From:   Ingo Molnar <mingo@kernel.org>
To:     Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc:     Valentin Schneider <vschneid@redhat.com>,
        linux-kernel@vger.kernel.org,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Ingo Molnar <mingo@redhat.com>,
        Juri Lelli <juri.lelli@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Steven Rostedt <rostedt@goodmis.org>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH] sched/rt: Make rt_rq->pushable_tasks updates drive
 rto_mask
Message-ID: <ZRFEeGKGzE+dY6n6@gmail.com>
References: <20230811112044.3302588-1-vschneid@redhat.com>
 <20230815142121.MoZplZUr@linutronix.de>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <20230815142121.MoZplZUr@linutronix.de>
Precedence: bulk


* Sebastian Andrzej Siewior <bigeasy@linutronix.de> wrote:

> On 2023-08-11 12:20:44 [+0100], Valentin Schneider wrote:
> > Sebastian noted that the rto_push_work IRQ work can be queued for a CPU
> > that has an empty pushable_tasks list, which means nothing useful will be
> > done in the IPI other than queue the work for the next CPU on the rto_mask.
> > 
> > rto_push_irq_work_func() only operates on tasks in the pushable_tasks list,
> > but the conditions for that irq_work to be queued (and for a CPU to be
> > added to the rto_mask) rely on rq_rt->nr_migratory instead.
> > 
> > nr_migratory is increased whenever an RT task entity is enqueued and it has
> > nr_cpus_allowed > 1. Unlike the pushable_tasks list, nr_migratory includes a
> > rt_rq's current task. This means a rt_rq can have a migratible current, N
> > non-migratible queued tasks, and be flagged as overloaded / have its CPU
> > set in the rto_mask, despite having an empty pushable_tasks list.
> > 
> > Make an rt_rq's overload logic be driven by {enqueue,dequeue}_pushable_task().
> > Since rt_rq->{rt_nr_migratory,rt_nr_total} become unused, remove them.
> > 
> > Note that the case where the current task is pushed away to make way for a
> > migration-disabled task remains unchanged: the migration-disabled task has
> > to be in the pushable_tasks list in the first place, which means it has
> > nr_cpus_allowed > 1.
> > 
> > Link: http://lore.kernel.org/r/20230801152648._y603AS_@linutronix.de
> > Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> > Signed-off-by: Valentin Schneider <vschneid@redhat.com>
> > ---
> > This is lightly tested, this looks to be working OK but I don't have nor am
> > I aware of a test case for RT balancing, I suppose we want something that
> > asserts we always run the N highest prio tasks for N CPUs, with a small
> > margin for migrations?
> 
> I don't see the storm of IPIs I saw before. So as far that goes:
>    Tested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

I've applied Valentin's initial fix to tip:sched/core, for an eventual
v6.7 merge, as it addresses the IPI storm bug. Let me know if merging
this is not desirable for some reason.

> What I still observe is:
> - CPU0 is idle. CPU0 gets a task assigned from CPU1. That task receives
>   a wakeup. CPU0 returns from idle and schedules the task.
>   pull_rt_task() on CPU1 and sometimes on other CPU observe this, too.
>   CPU1 sends irq_work to CPU0 while at the time rto_next_cpu() sees that
>   has_pushable_tasks() return 0. That bit was cleared earlier (as per
>   tracing).
> 
> - CPU0 is idle. CPU0 gets a task assigned from CPU1. The task on CPU0 is
>   woken up without an IPI (yay). But then pull_rt_task() decides that
>   send irq_work and has_pushable_tasks() said that is has tasks left
>   so….
>   Now: rto_push_irq_work_func() run once once on CPU0, does nothing,
>   rto_next_cpu() return CPU0 again and enqueues itself again on CPU0.
>   Usually after the second or third round the scheduler on CPU0 makes
>   enough progress to remove the task/ clear the CPU from mask.

Just curious, any progress on solving this?

Thanks,

	Ingo