__enqueue_entity(cfs_rq, se);
}
-static void update_avg(u64 *avg, u64 sample)
-{
- s64 diff = sample - *avg;
- *avg += diff >> 3;
-}
-
-static void update_avg_stats(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
- if (!se->last_wakeup)
- return;
-
- update_avg(&se->avg_overlap, se->sum_exec_runtime - se->last_wakeup);
- se->last_wakeup = 0;
-}
-
static void
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
{
update_stats_dequeue(cfs_rq, se);
if (sleep) {
- update_avg_stats(cfs_rq, se);
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
struct task_struct *tsk = task_of(se);
#ifdef CONFIG_SCHED_HRTICK
static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
- int requeue = rq->curr == p;
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
* Don't schedule slices shorter than 10000ns, that just
* doesn't make sense. Rely on vruntime for fairness.
*/
- if (!requeue)
- delta = max(10000LL, delta);
+ if (rq->curr != p)
+ delta = max_t(s64, 10000LL, delta);
- hrtick_start(rq, delta, requeue);
+ hrtick_start(rq, delta);
}
}
-#else
+#else /* !CONFIG_SCHED_HRTICK */
static inline void
hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
* not idle and an idle cpu is available. The span of cpus to
* search starts with cpus closest then further out as needed,
* so we always favor a closer, idle cpu.
+ * Domains may include CPUs that are not usable for migration,
+ * hence we need to mask them out (cpu_active_map)
*
* Returns the CPU we should wake onto.
*/
|| ((sd->flags & SD_WAKE_IDLE_FAR)
&& !task_hot(p, task_rq(p)->clock, sd))) {
cpus_and(tmp, sd->span, p->cpus_allowed);
- for_each_cpu_mask(i, tmp) {
+ cpus_and(tmp, tmp, cpu_active_map);
+ for_each_cpu_mask_nr(i, tmp) {
if (idle_cpu(i)) {
if (i != task_cpu(p)) {
schedstat_inc(p,
}
return cpu;
}
-#else
+#else /* !ARCH_HAS_SCHED_WAKE_IDLE*/
static inline int wake_idle(int cpu, struct task_struct *p)
{
return cpu;
static const struct sched_class fair_sched_class;
#ifdef CONFIG_FAIR_GROUP_SCHED
-static unsigned long effective_load(struct task_group *tg, int cpu,
- unsigned long wl, unsigned long wg)
+/*
+ * effective_load() calculates the load change as seen from the root_task_group
+ *
+ * Adding load to a group doesn't make a group heavier, but can cause movement
+ * of group shares between cpus. Assuming the shares were perfectly aligned one
+ * can calculate the shift in shares.
+ *
+ * The problem is that perfectly aligning the shares is rather expensive, hence
+ * we try to avoid doing that too often - see update_shares(), which ratelimits
+ * this change.
+ *
+ * We compensate this by not only taking the current delta into account, but
+ * also considering the delta between when the shares were last adjusted and
+ * now.
+ *
+ * We still saw a performance dip, some tracing learned us that between
+ * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
+ * significantly. Therefore try to bias the error in direction of failing
+ * the affine wakeup.
+ *
+ */
+static long effective_load(struct task_group *tg, int cpu,
+ long wl, long wg)
{
struct sched_entity *se = tg->se[cpu];
+ long more_w;
+
+ if (!tg->parent)
+ return wl;
+
+ /*
+ * By not taking the decrease of shares on the other cpu into
+ * account our error leans towards reducing the affine wakeups.
+ */
+ if (!wl && sched_feat(ASYM_EFF_LOAD))
+ return wl;
+
+ /*
+ * Instead of using this increment, also add the difference
+ * between when the shares were last updated and now.
+ */
+ more_w = se->my_q->load.weight - se->my_q->rq_weight;
+ wl += more_w;
+ wg += more_w;
for_each_sched_entity(se) {
#define D(n) (likely(n) ? (n) : 1)
S = se->my_q->tg->shares;
s = se->my_q->shares;
- rw = se->my_q->load.weight;
+ rw = se->my_q->rq_weight;
a = S*(rw + wl);
b = S*rw + s*wg;
* a reasonable amount of time then attract this newly
* woken task:
*/
- if (sync && balanced && curr->sched_class == &fair_sched_class) {
+ if (sync && balanced) {
if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
- p->se.avg_overlap < sysctl_sched_migration_cost)
+ p->se.avg_overlap < sysctl_sched_migration_cost)
return 1;
}
return;
}
- se->last_wakeup = se->sum_exec_runtime;
if (unlikely(se == pse))
return;
struct task_struct *p = NULL;
struct sched_entity *se;
- while (next != &cfs_rq->tasks) {
+ if (next == &cfs_rq->tasks)
+ return NULL;
+
+ /* Skip over entities that are not tasks */
+ do {
se = list_entry(next, struct sched_entity, group_node);
next = next->next;
+ } while (next != &cfs_rq->tasks && !entity_is_task(se));
- /* Skip over entities that are not tasks */
- if (entity_is_task(se)) {
- p = task_of(se);
- break;
- }
- }
+ if (next == &cfs_rq->tasks)
+ return NULL;
cfs_rq->balance_iterator = next;
+
+ if (entity_is_task(se))
+ p = task_of(se);
+
return p;
}
return 0;
}
-#endif
+#endif /* CONFIG_SMP */
/*
* scheduler tick hitting a task of our scheduling class: