[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Ytf6B19HjYGPvJZ/@worktop.programming.kicks-ass.net>
Date: Wed, 20 Jul 2022 14:50:15 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Nicolas Saenz Julienne <nsaenzju@...hat.com>
Cc: linux-kernel@...r.kernel.org, fweisbec@...il.com,
bristot@...hat.com, vschneid@...hat.com, cmetcalf@...hip.com,
mgorman@...e.de, bsegall@...gle.com, rostedt@...dmis.org,
dietmar.eggemann@....com, vincent.guittot@...aro.org,
juri.lelli@...hat.com, mingo@...hat.com, mtosatti@...hat.com
Subject: Re: [PATCH] nohz/full, sched/rt: Fix missed tick-reenabling bug in
dequeue_task_rt
On Wed, Jul 13, 2022 at 07:18:42PM +0200, Nicolas Saenz Julienne wrote:
> On Tue, 2022-06-28 at 11:22 +0200, Nicolas Saenz Julienne wrote:
> > dequeue_task_rt() only decrements 'rt_rq->rt_nr_running' after having
> > called sched_update_tick_dependency() preventing it from re-enabling the
> > tick on systems that no longer have pending SCHED_RT tasks but have
> > multiple runnable SCHED_OTHER tasks:
> >
> > dequeue_task_rt()
> > dequeue_rt_entity()
> > dequeue_rt_stack()
> > dequeue_top_rt_rq()
> > sub_nr_running() // decrements rq->nr_running
> > sched_update_tick_dependency()
> > sched_can_stop_tick() // checks rq->rt.rt_nr_running,
> > ...
> > __dequeue_rt_entity()
> > dec_rt_tasks() // decrements rq->rt.rt_nr_running
> > ...
> >
> > Every other scheduler class performs the operation in the opposite
> > order, and sched_update_tick_dependency() expects the values to be
> > updated as such. So avoid the misbehaviour by inverting the order in
> > which the above operations are performed in the RT scheduler.
> >
> > Fixes: 76d92ac305f2 ("sched: Migrate sched to use new tick dependency mask model")
> > Signed-off-by: Nicolas Saenz Julienne <nsaenzju@...hat.com>
> > ---
>
> Ping :)
Thanks! got stuck in the retbleed backlog :/
Powered by blists - more mailing lists