Le 21 janv. 2014 19:39, <bsegall@google.com> a écrit :
>
> Vincent Guittot <vincent.guittot@linaro.org> writes:
>
> > With the current implementation, the load average statistics of a sched entity
> > change according to other activity on the CPU even if this activity is done
> > between the running window of the sched entity and have no influence on the
> > running duration of the task.
> >
> > When a task wakes up on the same CPU, we currently update last_runnable_update
> > with the return  of __synchronize_entity_decay without updating the
> > runnable_avg_sum and runnable_avg_period accordingly. In fact, we have to sync
> > the load_contrib of the se with the rq's blocked_load_contrib before removing
> > it from the latter (with __synchronize_entity_decay) but we must keep
> > last_runnable_update unchanged for updating runnable_avg_sum/period during the
> > next update_entity_load_avg.
>
> ... Gah, that's correct, we had this right the first time. Could you do
> this as a full revert of 282cf499f03ec1754b6c8c945c9674b02631fb0f (ie
> remove the now inaccurate comment, or maybe replace it with a correct one).

Ok i'm going to remove comment as well and replace it with a new description

Vincent

> >
> > Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
> > ---
> >  kernel/sched/fair.c |    3 +--
> >  1 file changed, 1 insertion(+), 2 deletions(-)
> >
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index e64b079..5b0ef90 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@ -2370,8 +2370,7 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
> >                * would have made count negative); we must be careful to avoid
> >                * double-accounting blocked time after synchronizing decays.
> >                */
> > -             se->avg.last_runnable_update += __synchronize_entity_decay(se)
> > -                                                     << 20;
> > +             __synchronize_entity_decay(se);
> >       }
> >
> >       /* migrated tasks did not contribute to our blocked load */