Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1581290

Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow

Show all headers | View raw

On 15/02/17 13:31, Luca Abeni wrote:
> Hi Juri,
> 
> On Wed, 15 Feb 2017 10:29:19 +0000
> Juri Lelli <juri.lelli@arm.com> wrote:
> [...]
> > > Ok, thanks; I think I can now see why this can result in a task
> > > consuming more than the reserved utilisation. I still need some
> > > time to convince me that "runtime / (deadline - t) > dl_runtime /
> > > dl_deadline" is the correct check to use (in this case, shouldn't
> > > we also change the admission test to use densities instead of
> > > utilisations?) 
> > 
> > Right, this is what I was wondering as well, as dl_overflow()
> > currently looks at the period. And I also have some recollection of
> > this discussion happening already in the past, unfortunately it was
> > not on the list.
> > 
> > That discussion started with the following patch
> [...]
> > that we then dediced not to propose since (note that these are just my
> > memories of the dicussion, so everything it's up for further
> > discussion, also in light of the problem highlighted by Daniel)
> > 
> >  - SCHED_DEADLINE, as the documentation says, does AC using
> > utilization
> >  - it is however true that a sufficient (but not necessary) test on
> > UP for D_i != P_i cases is the one of my patch above
> >  - we have agreed in the past that the kernel should only check that
> > we don't cause "overload" in the system (which is still the case if we
> >    consider utilizations), not "hard schedulability"
> I remember a similar discussion; I think the decision about what to do
> depends on what are the requirements: hard deadline guarantees (but in
> this case global EDF is just a bad choice) or tardines no overload
> guarantees?
> 
> My understanding was that the kernel guarantees that deadline tasks
> will not starve non-deadline tasks, and that there is an upper bound
> for the tardiness experienced by deadline tasks. If this understanding
> is correct, then the current admission test is ok. But if I
> misunderstood the purpose of the kernel admission test, then maybe your
> patch is ok.
> 
> Then, it is important to keep the admission test consistent with the
> checks performed in dl_entity_overflow() (but whatever we decide to do,
> dl_entity_overflow() should be fixed).
> 

I'm sorry, but I'm a bit lost. :(

Why do you say 'whatever we decide to do'?

In my understanding:

 - if we decide AC shouldn't change (as we care about not-starving
   others and having bounded tardiness), then I'd say dl_entity_overflow
   shouldn't change as well, since it's using dl_runtime/dl_period as
   'static bandwidth' (as AC does)
 
 - if we instead move to use densities when doing AC (dl_runtime/dl_
   deadline), I think we should also change the check in dl_entity_
   overflow, as Steve is proposing

 - in both cases Daniel's fixes look sensible to have

Where am I wrong? :)

Actually, another thing that we noticed, talking on IRC with Peter, is
that we seem to be replenishing differently on different occasions:

 - on wakeup (if overflowing) we do

   dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
   dl_se->runtime = pi_se->dl_runtime;

 - when the replenishment timer fires (un-thottle and with runtime < 0)

   dl_se->deadline += pi_se->dl_period;
   dl_se->runtime += pi_se->dl_runtime;

Isn't this problematic as well?

Thanks,

- Juri

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH V2 0/2] sched/deadline: Fixes for constrained deadline tasks Daniel Bristot de Oliveira <bristot@redhat.com> - 2017-02-13 20:10 +0100
  [PATCH V2 2/2] sched/deadline: Throttle a constrained deadline task activated after the deadline Daniel Bristot de Oliveira <bristot@redhat.com> - 2017-02-13 20:10 +0100
    Re: [PATCH V2 2/2] sched/deadline: Throttle a constrained deadline  task activated after the deadline Tommaso Cucinotta <tommaso.cucinotta@santannapisa.it> - 2017-02-14 18:00 +0100
      Re: [PATCH V2 2/2] sched/deadline: Throttle a constrained deadline  task activated after the deadline Daniel Bristot de Oliveira <bristot@redhat.com> - 2017-02-14 18:40 +0100
    Re: [PATCH V2 2/2] sched/deadline: Throttle a constrained deadline  task activated after the deadline Steven Rostedt <rostedt@goodmis.org> - 2017-02-14 20:40 +0100
  [PATCH V2 1/2] sched/deadline: Replenishment timer should fire in the next period Daniel Bristot de Oliveira <bristot@redhat.com> - 2017-02-13 20:10 +0100
  [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow "Steven Rostedt (VMware)" <rostedt@goodmis.org> - 2017-02-14 20:30 +0100
    Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow luca abeni <luca.abeni@santannapisa.it> - 2017-02-14 23:50 +0100
      Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Steven Rostedt <rostedt@goodmis.org> - 2017-02-15 01:20 +0100
        Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Luca Abeni <luca.abeni@santannapisa.it> - 2017-02-15 08:50 +0100
          Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Juri Lelli <juri.lelli@arm.com> - 2017-02-15 11:30 +0100
            Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Peter Zijlstra <peterz@infradead.org> - 2017-02-15 12:40 +0100
            Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Luca Abeni <luca.abeni@santannapisa.it> - 2017-02-15 13:40 +0100
              Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Juri Lelli <juri.lelli@arm.com> - 2017-02-15 14:00 +0100
                Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Luca Abeni <luca.abeni@santannapisa.it> - 2017-02-15 14:20 +0100
                Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Juri Lelli <juri.lelli@arm.com> - 2017-02-15 15:20 +0100
                Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Daniel Bristot de Oliveira <bristot@redhat.com> - 2017-02-15 14:40 +0100
                Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Daniel Bristot de Oliveira <bristot@redhat.com> - 2017-02-15 14:50 +0100
                Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Steven Rostedt <rostedt@goodmis.org> - 2017-02-15 15:10 +0100
                Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Juri Lelli <juri.lelli@arm.com> - 2017-02-15 15:20 +0100
                Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Tommaso Cucinotta <tommaso.cucinotta@santannapisa.it> - 2017-02-16 17:40 +0100
                Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when  calculating overflow Steven Rostedt <rostedt@goodmis.org> - 2017-02-16 17:50 +0100

csiph-web