On Tue, Dec 05, 2017 at 05:10:16PM +0000, Patrick Bellasi wrote:
> +static inline void util_est_dequeue(struct task_struct *p, int flags)
> +{
> + struct cfs_rq *cfs_rq = &task_rq(p)->cfs;
> + unsigned long util_last = task_util(p);
> + bool sleep = flags & DEQUEUE_SLEEP;
> + unsigned long ewma;
> + long util_est;
> +
> + if (!sched_feat(UTIL_EST))
> + return;
> +
> + /*
> + * Update root cfs_rq's estimated utilization
> + *
> + * If *p is the last task then the root cfs_rq's estimated utilization
> + * of a CPU is 0 by definition.
> + *
> + * Otherwise, in removing *p's util_est from its cfs_rq's
> + * util_est_runnable we should account for cases where this last
> + * activation of *p was longer then the previous ones.
> + * Also in these cases we need to set 0 the estimated utilization for
> + * the CPU.
> + */
> + if (cfs_rq->nr_running > 0) {
> + util_est = cfs_rq->util_est_runnable;
> + util_est -= task_util_est(p);
> + if (util_est < 0)
> + util_est = 0;
> + cfs_rq->util_est_runnable = util_est;
> + } else {
> + cfs_rq->util_est_runnable = 0;
> + }
> +
> + /*
> + * Skip update of task's estimated utilization when the task has not
> + * yet completed an activation, e.g. being migrated.
> + */
> + if (!sleep)
> + return;
> +
> + /*
> + * Skip update of task's estimated utilization when its EWMA is already
> + * ~1% close to its last activation value.
> + */
> + util_est = p->util_est.ewma;
> + if (abs(util_est - util_last) <= (SCHED_CAPACITY_SCALE / 100))
> + return;
Isn't that computation almost as expensive as the stuff you're trying to
avoid?
> + /*
> + * Update Task's estimated utilization
> + *
> + * When *p completes an activation we can consolidate another sample
> + * about the task size. This is done by storing the last PELT value
> + * for this task and using this value to load another sample in the
> + * exponential weighted moving average:
> + *
> + * ewma(t) = w * task_util(p) + (1 - w) ewma(t-1)
> + * = w * task_util(p) + ewma(t-1) - w * ewma(t-1)
> + * = w * (task_util(p) + ewma(t-1) / w - ewma(t-1))
> + *
> + * Where 'w' is the weight of new samples, which is configured to be
> + * 0.25, thus making w=1/4
> + */
> + p->util_est.last = util_last;
> + ewma = p->util_est.ewma;
> + if (likely(ewma != 0)) {
Why special case 0? Yes it helps with the initial ramp-on, but would not
an asymmetric IIR (with a consistent upward bias) be better?
> + ewma = util_last + (ewma << UTIL_EST_WEIGHT_SHIFT) - ewma;
> + ewma >>= UTIL_EST_WEIGHT_SHIFT;
> + } else {
> + ewma = util_last;
> + }
> + p->util_est.ewma = ewma;
> +}
