Messages in this thread | | | Date | Fri, 18 Nov 2016 16:06:10 +0100 | From | luca abeni <> | Subject | Re: [RFC v3 1/6] Track the active utilisation |
| |
Hi Peter,
On Fri, 18 Nov 2016 14:55:54 +0100 Peter Zijlstra <peterz@infradead.org> wrote:
> On Mon, Oct 24, 2016 at 04:06:33PM +0200, Luca Abeni wrote: > > > @@ -498,6 +514,8 @@ 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); > > > > + add_running_bw(dl_se, dl_rq); > > + > > if (dl_time_before(dl_se->deadline, rq_clock(rq)) || > > dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { > > dl_se->deadline = rq_clock(rq) + > > pi_se->dl_deadline; @@ -947,14 +965,19 @@ static void > > enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) > > return; } > > > > + if (p->on_rq == TASK_ON_RQ_MIGRATING) > > + add_running_bw(&p->dl, &rq->dl); > > + > > /* > > * If p is throttled, we do nothing. In fact, if it > > exhausted > > * its budget it needs a replenishment and, since it now > > is on > > * its rq, the bandwidth timer callback (which clearly has > > not > > * run yet) will take care of this. > > */ > > - if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) > > + if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) { > > + add_running_bw(&p->dl, &rq->dl); > > return; > > + } > > > > enqueue_dl_entity(&p->dl, pi_se, flags); > > > > I realize the enqueue path is a bit of a maze, but this hurts my head. > > Isn't there anything we can do to streamline this a bit? > > Maybe move the add_running_bw() from update_dl_entity() to the > ENQUEUE_WAKEUP branch in enqueue_dl_entity()? Because that's what you > really want, isn't it? Its not actually related to recomputing the > absolute deadline.
Right... I'll change the code in this way. I am currently modifying this code (because after Juri's review I realized that there is an issue - see last email exchange with Juri); I'll make this change as soon as the code stabilizes.
Thanks, Luca
| |