From: Scott Wood <swood@redhat.com>
To: Juri Lelli <juri.lelli@redhat.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
Thomas Gleixner <tglx@linutronix.de>,
Steven Rostedt <rostedt@goodmis.org>,
Peter Zijlstra <peterz@infradead.org>,
Daniel Bristot de Oliveira <bristot@redhat.com>,
Clark Williams <williams@redhat.com>,
linux-kernel@vger.kernel.org, linux-rt-users@vger.kernel.org
Subject: Re: [PATCH RT 5/8] sched/deadline: Reclaim cpuset bandwidth in .migrate_task_rq()
Date: Mon, 30 Sep 2019 11:24:00 -0500 [thread overview]
Message-ID: <9acc5f1bd0fe06acb2b7b518c5ef1f082e89ad63.camel@redhat.com> (raw)
In-Reply-To: <20190930071233.GE31660@localhost.localdomain>
On Mon, 2019-09-30 at 09:12 +0200, Juri Lelli wrote:
> On 27/09/19 11:40, Scott Wood wrote:
> > On Fri, 2019-09-27 at 10:11 +0200, Juri Lelli wrote:
> > > Hi Scott,
> > >
> > > On 27/07/19 00:56, Scott Wood wrote:
> > > > With the changes to migrate disabling, ->set_cpus_allowed() no
> > > > longer
> > > > gets deferred until migrate_enable(). To avoid releasing the
> > > > bandwidth
> > > > while the task may still be executing on the old CPU, move the
> > > > subtraction
> > > > to ->migrate_task_rq().
> > > >
> > > > Signed-off-by: Scott Wood <swood@redhat.com>
> > > > ---
> > > > kernel/sched/deadline.c | 67 +++++++++++++++++++++++---------------
> > > > ----
> > > > -------
> > > > 1 file changed, 31 insertions(+), 36 deletions(-)
> > > >
> > > > diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> > > > index c18be51f7608..2f18d0cf1b56 100644
> > > > --- a/kernel/sched/deadline.c
> > > > +++ b/kernel/sched/deadline.c
> > > > @@ -1606,14 +1606,42 @@ static void yield_task_dl(struct rq *rq)
> > > > return cpu;
> > > > }
> > > >
> > > > +static void free_old_cpuset_bw_dl(struct rq *rq, struct task_struct
> > > > *p)
> > > > +{
> > > > + struct root_domain *src_rd = rq->rd;
> > > > +
> > > > + /*
> > > > + * Migrating a SCHED_DEADLINE task between exclusive
> > > > + * cpusets (different root_domains) entails a bandwidth
> > > > + * update. We already made space for us in the destination
> > > > + * domain (see cpuset_can_attach()).
> > > > + */
> > > > + if (!cpumask_intersects(src_rd->span, p->cpus_ptr)) {
> > > > + struct dl_bw *src_dl_b;
> > > > +
> > > > + src_dl_b = dl_bw_of(cpu_of(rq));
> > > > + /*
> > > > + * We now free resources of the root_domain we are
> > > > migrating
> > > > + * off. In the worst case, sched_setattr() may
> > > > temporary
> > > > fail
> > > > + * until we complete the update.
> > > > + */
> > > > + raw_spin_lock(&src_dl_b->lock);
> > > > + __dl_sub(src_dl_b, p->dl.dl_bw,
> > > > dl_bw_cpus(task_cpu(p)));
> > > > + raw_spin_unlock(&src_dl_b->lock);
> > > > + }
> > > > +}
> > > > +
> > > > static void migrate_task_rq_dl(struct task_struct *p, int new_cpu
> > > > __maybe_unused)
> > > > {
> > > > struct rq *rq;
> > > >
> > > > - if (p->state != TASK_WAKING)
> > > > + rq = task_rq(p);
> > > > +
> > > > + if (p->state != TASK_WAKING) {
> > > > + free_old_cpuset_bw_dl(rq, p);
> > >
> > > What happens if a DEADLINE task is moved between cpusets while it was
> > > sleeping? Don't we miss removing from the old cpuset if the task gets
> > > migrated on wakeup?
> >
> > In that case set_task_cpu() is called by ttwu after setting state to
> > TASK_WAKING.
>
> Right.
>
> > I guess it could be annoying if the task doesn't wake up for a
> > long time and therefore doesn't release the bandwidth until then.
>
> Hummm, I was actually more worried about the fact that we call free_old_
> cpuset_bw_dl() only if p->state != TASK_WAKING.
Oh, right. :-P Not sure what I had in mind there; we want to call it
regardless.
I assume we need rq->lock in free_old_cpuset_bw_dl()? So something like
this:
if (p->state == TASK_WAITING)
raw_spin_lock(&rq->lock);
free_old_cpuset_bw_dl(rq, p);
if (p->state != TASK_WAITING)
return;
if (p->dl.dl_non_contending) {
....
BTW, is the full cpumask_intersects() necessary or would it suffice to see
that the new cpu is not in the old span?
-Scott
next prev parent reply other threads:[~2019-09-30 16:24 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-27 5:56 [RT PATCH 0/8] migrate disable fixes and performance Scott Wood
2019-07-27 5:56 ` [PATCH RT 1/8] sched: migrate_enable: Use sleeping_lock to indicate involuntary sleep Scott Wood
2019-07-29 13:26 ` Steven Rostedt
2019-07-27 5:56 ` [PATCH RT 2/8] sched: __set_cpus_allowed_ptr: Check cpus_mask, not cpus_ptr Scott Wood
2019-09-17 14:57 ` Sebastian Andrzej Siewior
2019-09-17 15:23 ` Scott Wood
2019-07-27 5:56 ` [PATCH RT 3/8] sched: Remove dead __migrate_disabled() check Scott Wood
2019-07-27 5:56 ` [PATCH RT 4/8] sched: migrate disable: Protect cpus_ptr with lock Scott Wood
2019-09-26 16:39 ` Sebastian Andrzej Siewior
2019-09-26 16:52 ` Scott Wood
2019-09-27 12:19 ` Sebastian Andrzej Siewior
2019-09-27 20:02 ` Scott Wood
2019-07-27 5:56 ` [PATCH RT 5/8] sched/deadline: Reclaim cpuset bandwidth in .migrate_task_rq() Scott Wood
2019-09-17 15:10 ` Sebastian Andrzej Siewior
2019-09-27 8:11 ` Juri Lelli
2019-09-27 16:40 ` Scott Wood
2019-09-30 7:12 ` Juri Lelli
2019-09-30 16:24 ` Scott Wood [this message]
2019-10-01 8:52 ` Juri Lelli
2019-10-09 6:25 ` Scott Wood
2019-10-09 7:27 ` Juri Lelli
2019-10-09 19:12 ` Scott Wood
2019-10-10 8:18 ` Juri Lelli
2019-07-27 5:56 ` [PATCH RT 6/8] sched: migrate_enable: Set state to TASK_RUNNING Scott Wood
2019-09-17 15:31 ` Sebastian Andrzej Siewior
2019-09-17 17:54 ` Scott Wood
2019-07-27 5:56 ` [PATCH RT 7/8] sched: migrate_enable: Use select_fallback_rq() Scott Wood
2019-09-17 16:00 ` Sebastian Andrzej Siewior
2019-09-24 18:05 ` Scott Wood
2019-07-27 5:56 ` [PATCH RT 8/8] sched: Lazy migrate_disable processing Scott Wood
2019-09-17 16:50 ` Sebastian Andrzej Siewior
2019-09-17 17:06 ` Scott Wood
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=9acc5f1bd0fe06acb2b7b518c5ef1f082e89ad63.camel@redhat.com \
--to=swood@redhat.com \
--cc=bigeasy@linutronix.de \
--cc=bristot@redhat.com \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rt-users@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--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;
as well as URLs for NNTP newsgroup(s).