} __attribute__((__aligned__(sizeof(u64))));
/*
- * The load_avg/util_avg accumulates an infinite geometric series
+ * The load/runnable/util_avg accumulates an infinite geometric series
* (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c).
*
* [load_avg definition]
*
* load_avg = runnable% * scale_load_down(load)
*
- * where runnable% is the time ratio that a sched_entity is runnable.
- * For cfs_rq, it is the aggregated load_avg of all runnable and
- * blocked sched_entities.
+ * [runnable_avg definition]
+ *
+ * runnable_avg = runnable% * SCHED_CAPACITY_SCALE
*
* [util_avg definition]
*
* util_avg = running% * SCHED_CAPACITY_SCALE
*
- * where running% is the time ratio that a sched_entity is running on
- * a CPU. For cfs_rq, it is the aggregated util_avg of all runnable
- * and blocked sched_entities.
+ * where runnable% is the time ratio that a sched_entity is runnable and
+ * running% the time ratio that a sched_entity is running.
+ *
+ * For cfs_rq, they are the aggregated values of all runnable and blocked
+ * sched_entities.
*
- * load_avg and util_avg don't direcly factor frequency scaling and CPU
- * capacity scaling. The scaling is done through the rq_clock_pelt that
- * is used for computing those signals (see update_rq_clock_pelt())
+ * The load/runnable/util_avg doesn't direcly factor frequency scaling and CPU
+ * capacity scaling. The scaling is done through the rq_clock_pelt that is used
+ * for computing those signals (see update_rq_clock_pelt())
*
* N.B., the above ratios (runnable% and running%) themselves are in the
* range of [0, 1]. To do fixed point arithmetics, we therefore scale them
struct sched_avg {
u64 last_update_time;
u64 load_sum;
+ u64 runnable_sum;
u32 util_sum;
u32 period_contrib;
unsigned long load_avg;
+ unsigned long runnable_avg;
unsigned long util_avg;
struct util_est util_est;
} ____cacheline_aligned;
struct cfs_rq *cfs_rq;
/* rq "owned" by this entity/group: */
struct cfs_rq *my_q;
+ /* cached value of my_q->h_nr_running */
+ unsigned long runnable_weight;
#endif
#ifdef CONFIG_SMP
#ifdef CONFIG_SMP
P(se->avg.load_avg);
P(se->avg.util_avg);
+ P(se->avg.runnable_avg);
#endif
#undef PN_SCHEDSTAT
#ifdef CONFIG_SMP
SEQ_printf(m, " .%-30s: %lu\n", "load_avg",
cfs_rq->avg.load_avg);
+ SEQ_printf(m, " .%-30s: %lu\n", "runnable_avg",
+ cfs_rq->avg.runnable_avg);
SEQ_printf(m, " .%-30s: %lu\n", "util_avg",
cfs_rq->avg.util_avg);
SEQ_printf(m, " .%-30s: %u\n", "util_est_enqueued",
cfs_rq->removed.load_avg);
SEQ_printf(m, " .%-30s: %ld\n", "removed.util_avg",
cfs_rq->removed.util_avg);
- SEQ_printf(m, " .%-30s: %ld\n", "removed.runnable_sum",
- cfs_rq->removed.runnable_sum);
+ SEQ_printf(m, " .%-30s: %ld\n", "removed.runnable_avg",
+ cfs_rq->removed.runnable_avg);
#ifdef CONFIG_FAIR_GROUP_SCHED
SEQ_printf(m, " .%-30s: %lu\n", "tg_load_avg_contrib",
cfs_rq->tg_load_avg_contrib);
P(se.load.weight);
#ifdef CONFIG_SMP
P(se.avg.load_sum);
+ P(se.avg.runnable_sum);
P(se.avg.util_sum);
P(se.avg.load_avg);
+ P(se.avg.runnable_avg);
P(se.avg.util_avg);
P(se.avg.last_update_time);
P(se.avg.util_est.ewma);
}
}
+ sa->runnable_avg = cpu_scale;
+
if (p->sched_class != &fair_sched_class) {
/*
* For !fair tasks do:
* _IFF_ we look at the pure running and runnable sums. Because they
* represent the very same entity, just at different points in the hierarchy.
*
- * Per the above update_tg_cfs_util() is trivial * and simply copies the
- * running sum over (but still wrong, because the group entity and group rq do
- * not have their PELT windows aligned).
+ * Per the above update_tg_cfs_util() and update_tg_cfs_runnable() are trivial
+ * and simply copies the running/runnable sum over (but still wrong, because
+ * the group entity and group rq do not have their PELT windows aligned).
*
* However, update_tg_cfs_load() is more complex. So we have:
*
}
static inline void
+update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
+{
+ long delta = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg;
+
+ /* Nothing to update */
+ if (!delta)
+ return;
+
+ /*
+ * The relation between sum and avg is:
+ *
+ * LOAD_AVG_MAX - 1024 + sa->period_contrib
+ *
+ * however, the PELT windows are not aligned between grq and gse.
+ */
+
+ /* Set new sched_entity's runnable */
+ se->avg.runnable_avg = gcfs_rq->avg.runnable_avg;
+ se->avg.runnable_sum = se->avg.runnable_avg * LOAD_AVG_MAX;
+
+ /* Update parent cfs_rq runnable */
+ add_positive(&cfs_rq->avg.runnable_avg, delta);
+ cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * LOAD_AVG_MAX;
+}
+
+static inline void
update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
{
long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum;
add_tg_cfs_propagate(cfs_rq, gcfs_rq->prop_runnable_sum);
update_tg_cfs_util(cfs_rq, se, gcfs_rq);
+ update_tg_cfs_runnable(cfs_rq, se, gcfs_rq);
update_tg_cfs_load(cfs_rq, se, gcfs_rq);
trace_pelt_cfs_tp(cfs_rq);
static inline int
update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
- unsigned long removed_load = 0, removed_util = 0, removed_runnable_sum = 0;
+ unsigned long removed_load = 0, removed_util = 0, removed_runnable = 0;
struct sched_avg *sa = &cfs_rq->avg;
int decayed = 0;
raw_spin_lock(&cfs_rq->removed.lock);
swap(cfs_rq->removed.util_avg, removed_util);
swap(cfs_rq->removed.load_avg, removed_load);
- swap(cfs_rq->removed.runnable_sum, removed_runnable_sum);
+ swap(cfs_rq->removed.runnable_avg, removed_runnable);
cfs_rq->removed.nr = 0;
raw_spin_unlock(&cfs_rq->removed.lock);
sub_positive(&sa->util_avg, r);
sub_positive(&sa->util_sum, r * divider);
- add_tg_cfs_propagate(cfs_rq, -(long)removed_runnable_sum);
+ r = removed_runnable;
+ sub_positive(&sa->runnable_avg, r);
+ sub_positive(&sa->runnable_sum, r * divider);
+
+ /*
+ * removed_runnable is the unweighted version of removed_load so we
+ * can use it to estimate removed_load_sum.
+ */
+ add_tg_cfs_propagate(cfs_rq,
+ -(long)(removed_runnable * divider) >> SCHED_CAPACITY_SHIFT);
decayed = 1;
}
*/
se->avg.util_sum = se->avg.util_avg * divider;
+ se->avg.runnable_sum = se->avg.runnable_avg * divider;
+
se->avg.load_sum = divider;
if (se_weight(se)) {
se->avg.load_sum =
enqueue_load_avg(cfs_rq, se);
cfs_rq->avg.util_avg += se->avg.util_avg;
cfs_rq->avg.util_sum += se->avg.util_sum;
+ cfs_rq->avg.runnable_avg += se->avg.runnable_avg;
+ cfs_rq->avg.runnable_sum += se->avg.runnable_sum;
add_tg_cfs_propagate(cfs_rq, se->avg.load_sum);
dequeue_load_avg(cfs_rq, se);
sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+ sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg);
+ sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum);
add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);
++cfs_rq->removed.nr;
cfs_rq->removed.util_avg += se->avg.util_avg;
cfs_rq->removed.load_avg += se->avg.load_avg;
- cfs_rq->removed.runnable_sum += se->avg.load_sum; /* == runnable_sum */
+ cfs_rq->removed.runnable_avg += se->avg.runnable_avg;
raw_spin_unlock_irqrestore(&cfs_rq->removed.lock, flags);
}
+static inline unsigned long cfs_rq_runnable_avg(struct cfs_rq *cfs_rq)
+{
+ return cfs_rq->avg.runnable_avg;
+}
+
static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
{
return cfs_rq->avg.load_avg;
/*
* When enqueuing a sched_entity, we must:
* - Update loads to have both entity and cfs_rq synced with now.
+ * - Add its load to cfs_rq->runnable_avg
* - For group_entity, update its weight to reflect the new share of
* its group cfs_rq
* - Add its new weight to cfs_rq->load.weight
*/
update_load_avg(cfs_rq, se, UPDATE_TG | DO_ATTACH);
+ se_update_runnable(se);
update_cfs_group(se);
account_entity_enqueue(cfs_rq, se);
/*
* When dequeuing a sched_entity, we must:
* - Update loads to have both entity and cfs_rq synced with now.
+ * - Subtract its load from the cfs_rq->runnable_avg.
* - Subtract its previous weight from cfs_rq->load.weight.
* - For group entity, update its weight to reflect the new share
* of its group cfs_rq.
*/
update_load_avg(cfs_rq, se, UPDATE_TG);
+ se_update_runnable(se);
update_stats_dequeue(cfs_rq, se, flags);
goto enqueue_throttle;
update_load_avg(cfs_rq, se, UPDATE_TG);
+ se_update_runnable(se);
update_cfs_group(se);
cfs_rq->h_nr_running++;
goto dequeue_throttle;
update_load_avg(cfs_rq, se, UPDATE_TG);
+ se_update_runnable(se);
update_cfs_group(se);
cfs_rq->h_nr_running--;
return load;
}
+static unsigned long cpu_runnable(struct rq *rq)
+{
+ return cfs_rq_runnable_avg(&rq->cfs);
+}
+
static unsigned long capacity_of(int cpu)
{
return cpu_rq(cpu)->cpu_capacity;
if (cfs_rq->avg.util_sum)
return false;
+ if (cfs_rq->avg.runnable_sum)
+ return false;
+
return true;
}
*/
static __always_inline u32
accumulate_sum(u64 delta, struct sched_avg *sa,
- unsigned long load, int running)
+ unsigned long load, unsigned long runnable, int running)
{
u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
u64 periods;
*/
if (periods) {
sa->load_sum = decay_load(sa->load_sum, periods);
+ sa->runnable_sum =
+ decay_load(sa->runnable_sum, periods);
sa->util_sum = decay_load((u64)(sa->util_sum), periods);
/*
if (load)
sa->load_sum += load * contrib;
+ if (runnable)
+ sa->runnable_sum += runnable * contrib << SCHED_CAPACITY_SHIFT;
if (running)
sa->util_sum += contrib << SCHED_CAPACITY_SHIFT;
*/
static __always_inline int
___update_load_sum(u64 now, struct sched_avg *sa,
- unsigned long load, int running)
+ unsigned long load, unsigned long runnable, int running)
{
u64 delta;
* Also see the comment in accumulate_sum().
*/
if (!load)
- running = 0;
+ runnable = running = 0;
/*
* Now we know we crossed measurement unit boundaries. The *_avg
* Step 1: accumulate *_sum since last_update_time. If we haven't
* crossed period boundaries, finish.
*/
- if (!accumulate_sum(delta, sa, load, running))
+ if (!accumulate_sum(delta, sa, load, runnable, running))
return 0;
return 1;
* Step 2: update *_avg.
*/
sa->load_avg = div_u64(load * sa->load_sum, divider);
+ sa->runnable_avg = div_u64(sa->runnable_sum, divider);
WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
}
*
* task:
* se_weight() = se->load.weight
+ * se_runnable() = !!on_rq
*
* group: [ see update_cfs_group() ]
* se_weight() = tg->weight * grq->load_avg / tg->load_avg
+ * se_runnable() = grq->h_nr_running
+ *
+ * runnable_sum = se_runnable() * runnable = grq->runnable_sum
+ * runnable_avg = runnable_sum
*
* load_sum := runnable
* load_avg = se_weight(se) * load_sum
*
- * XXX collapse load_sum and runnable_load_sum
- *
* cfq_rq:
*
+ * runnable_sum = \Sum se->avg.runnable_sum
+ * runnable_avg = \Sum se->avg.runnable_avg
+ *
* load_sum = \Sum se_weight(se) * se->avg.load_sum
* load_avg = \Sum se->avg.load_avg
*/
int __update_load_avg_blocked_se(u64 now, struct sched_entity *se)
{
- if (___update_load_sum(now, &se->avg, 0, 0)) {
+ if (___update_load_sum(now, &se->avg, 0, 0, 0)) {
___update_load_avg(&se->avg, se_weight(se));
trace_pelt_se_tp(se);
return 1;
int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- if (___update_load_sum(now, &se->avg, !!se->on_rq, cfs_rq->curr == se)) {
+ if (___update_load_sum(now, &se->avg, !!se->on_rq, se_runnable(se),
+ cfs_rq->curr == se)) {
___update_load_avg(&se->avg, se_weight(se));
cfs_se_util_change(&se->avg);
{
if (___update_load_sum(now, &cfs_rq->avg,
scale_load_down(cfs_rq->load.weight),
+ cfs_rq->h_nr_running,
cfs_rq->curr != NULL)) {
___update_load_avg(&cfs_rq->avg, 1);
* util_sum = cpu_scale * load_sum
* runnable_sum = util_sum
*
- * load_avg is not supported and meaningless.
+ * load_avg and runnable_avg are not supported and meaningless.
*
*/
{
if (___update_load_sum(now, &rq->avg_rt,
running,
+ running,
running)) {
___update_load_avg(&rq->avg_rt, 1);
* util_sum = cpu_scale * load_sum
* runnable_sum = util_sum
*
- * load_avg is not supported and meaningless.
+ * load_avg and runnable_avg are not supported and meaningless.
*
*/
{
if (___update_load_sum(now, &rq->avg_dl,
running,
+ running,
running)) {
___update_load_avg(&rq->avg_dl, 1);
* util_sum = cpu_scale * load_sum
* runnable_sum = util_sum
*
- * load_avg is not supported and meaningless.
+ * load_avg and runnable_avg are not supported and meaningless.
*
*/
*/
ret = ___update_load_sum(rq->clock - running, &rq->avg_irq,
0,
+ 0,
0);
ret += ___update_load_sum(rq->clock, &rq->avg_irq,
1,
+ 1,
1);
if (ret) {
int nr;
unsigned long load_avg;
unsigned long util_avg;
- unsigned long runnable_sum;
+ unsigned long runnable_avg;
} removed;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* An entity is a task if it doesn't "own" a runqueue */
#define entity_is_task(se) (!se->my_q)
+static inline void se_update_runnable(struct sched_entity *se)
+{
+ if (!entity_is_task(se))
+ se->runnable_weight = se->my_q->h_nr_running;
+}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+ if (entity_is_task(se))
+ return !!se->on_rq;
+ else
+ return se->runnable_weight;
+}
+
#else
#define entity_is_task(se) 1
+static inline void se_update_runnable(struct sched_entity *se) {}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+ return !!se->on_rq;
+}
#endif
#ifdef CONFIG_SMP