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


Groups > linux.kernel > #1581343

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

From Juri Lelli <juri.lelli@arm.com>
Newsgroups linux.kernel
Subject Re: [PATCH 3/2] sched/deadline: Use deadline instead of period when calculating overflow
Date 2017-02-15 15:20 +0100
Message-ID <tb8B4-13z-13@gated-at.bofh.it> (permalink)
References (4 earlier) <tb2vD-5gZ-1@gated-at.bofh.it> <tb50u-78r-17@gated-at.bofh.it> <tb72h-8qp-9@gated-at.bofh.it> <tb7lE-5n-17@gated-at.bofh.it> <tb7Yl-zU-7@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On 15/02/17 14:33, Daniel Bristot de Oliveira wrote:
> On 02/15/2017 01:59 PM, Juri Lelli wrote:
> > Actually, another thing that we noticed, talking on IRC with Peter, is
> > that we seem to be replenishing differently on different occasions:
> 
> When a task is awakened (not by the replenishment timer), it is not
> possible to know if the absolute deadline var stores the absolute
> deadline of activation which took place in the instant
> (current time) - dl_period.
> 
> Therefore, assuming the next deadline is one dl_deadline away from now
> is correct.
> 
> IOW: that is a sporadic activation - the task is activated after at
> least minimum inter-arrival time between activation/replenishment:
> 
> >  - on wakeup (if overflowing) we do
> > 
> >    dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
> >    dl_se->runtime = pi_se->dl_runtime;
> 
> 
> In the replenishment timer, it is known that the absolute deadline
> instant of the previous activation is in the deadline var. So
> putting the absolute deadline one dl_period away is correct [1].
> 
> Another point is that this case avoids creating time drift due
> to latencies. For instance, in the case of a 1 ms delay of the timer
> (interrupts disabled?), the wakeup replenishment would push the
> absolute a relative deadline + 1 ms away from the previous deadline.
> 
> IOW: the replenishment timer makes the periodic case - a fixed time
> offset from the previous activation/replenishment.
> 
> >  - 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;
> 
> So I think it is correct. Am I missing something?
> 

Nope, you are right, no problems here.

Thanks,

- Juri

Back to linux.kernel | Previous | NextPrevious 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