On 28/02/17 22:09, Byungchul Park wrote:
> On Tue, Feb 28, 2017 at 11:35:15AM +0000, Juri Lelli wrote:
> > Hi,
> >
> > On 23/02/17 15:14, Byungchul Park wrote:
> > > Let's consider the following example.
> > >
> > > timeline : o...................o.........o.......o..o
> > > ^ ^ ^ ^ ^
> > > | | | | |
> > > start | | | |
> > > original runtime | | |
> > > sleep with (-)runtime | |
> > > original deadline |
> > > wake up
> > >
> > > When this task is woken up, a negative runtime should be considered,
> > > which means that the task should get penalized when assigning runtime,
> > > becasue it already spent more than expected. Current code handles this
> > > by replenishing a runtime in hrtimer callback for deadline. But this
> > > approach has room for improvement:
> > >
> > > It will be replenished twice unnecessarily if the task sleeps for
> > > long time so that the deadline, assigned in the hrtimer callback,
> > > also passed. In other words, one happens in the callback and the
> > > other happens in update_dl_entiry() when waking it up.
> > >
> > > So force to replenish it for sleep tasks when waking it up.
> > >
> > > Signed-off-by: Byungchul Park <byungchul.p...@lge.com>
> > > ---
> > > kernel/sched/deadline.c | 13 ++++++-------
> > > 1 file changed, 6 insertions(+), 7 deletions(-)
> > >
> > > diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> > > index 27737f3..cb43ce9 100644
> > > --- a/kernel/sched/deadline.c
> > > +++ b/kernel/sched/deadline.c
> > > @@ -498,8 +498,9 @@ static void update_dl_entity(struct sched_dl_entity
> > > *dl_se,
> > > struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
> > > struct rq *rq = rq_of_dl_rq(dl_rq);
> > >
> > > - if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
> > > - dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
> > > + if (dl_time_before(dl_se->deadline, rq_clock(rq)))
> > > + replenish_dl_entity(dl_se, pi_se);
> > > + else if (dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
> > > dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
> > > dl_se->runtime = pi_se->dl_runtime;
> > > }
> > > @@ -621,13 +622,11 @@ static enum hrtimer_restart dl_task_timer(struct
> > > hrtimer *timer)
> > > * __dequeue_task_dl()
> > > * prev->on_rq = 0;
> > > *
> > > - * We can be both throttled and !queued. Replenish the counter
> > > - * but do not enqueue -- wait for our wakeup to do that.
> > > + * We can be both throttled and !queued. Wait for our wakeup to
> > > + * replenish runtime and enqueue p.
> > > */
> > > - if (!task_on_rq_queued(p)) {
> > > - replenish_dl_entity(dl_se, dl_se);
> >
> > Hasn't this patch the same problem we discussed a couple of weeks ago?
>
> No. This patch solves the problem by calling replenish_dl_entity() when
> a dl task is woken up.
>
So, if the task was throttled in the "going to sleep" path we set the
replenishment timer to fire at your "original deadline" instant of time
above. Now, 3 things can happen I guess:
- task wakes up before the replenishment timer ("original deadline")
-> it is throttled, so we do nothing
- task wakes up after the replenishment timer
-> we replenished it in the timer callback (which considers negative
runtime from previous execution)
+ deadline should be in the future
+ dl_entity shouldn't overflow
+ we don't touch its parameters, but we simply enqueue it back on dl_rq
- task wakes up even after the deadline it has got from previous
replenishment expired
-> we assign to him completely new parameters, but since he didn't
use the previous runtime at all, this should be fine I guess
What am I still missing? :)
> The problem was that it cannot consider negative runtime if we replenish
> the task when it's woken up. So I made replenish_dl_entity() called even
> on wake-up path, instead of simple assignment.
>
> IMHO, this patch avoids double-replenishing properly, but adds additional
> condition on wake-up path to acheive it. To be honest, I don't think it's
> worth as I expected.
>
> Thank you,
> Byungchul
>
> >
> > https://marc.info/?l=linux-kernel&m=148699950802995
> >
> > Thanks,
> >
> > - Juri
