}
/*
- * The goal of calc_delta_asym() is to be asymmetrically around NICE_0_LOAD, in
- * that it favours >=0 over <0.
- *
- * -20 |
- * |
- * 0 --------+-------
- * .'
- * 19 .'
- *
- */
-static unsigned long
-calc_delta_asym(unsigned long delta, struct sched_entity *se)
-{
- struct load_weight lw = {
- .weight = NICE_0_LOAD,
- .inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT)
- };
-
- for_each_sched_entity(se) {
- struct load_weight *se_lw = &se->load;
- unsigned long rw = cfs_rq_of(se)->load.weight;
-
-#ifdef CONFIG_FAIR_SCHED_GROUP
- struct cfs_rq *cfs_rq = se->my_q;
- struct task_group *tg = NULL
-
- if (cfs_rq)
- tg = cfs_rq->tg;
-
- if (tg && tg->shares < NICE_0_LOAD) {
- /*
- * scale shares to what it would have been had
- * tg->weight been NICE_0_LOAD:
- *
- * weight = 1024 * shares / tg->weight
- */
- lw.weight *= se->load.weight;
- lw.weight /= tg->shares;
-
- lw.inv_weight = 0;
-
- se_lw = &lw;
- rw += lw.weight - se->load.weight;
- } else
-#endif
-
- if (se->load.weight < NICE_0_LOAD) {
- se_lw = &lw;
- rw += NICE_0_LOAD - se->load.weight;
- }
-
- delta = calc_delta_mine(delta, rw, se_lw);
- }
-
- return delta;
-}
-
-/*
* Update the current task's runtime statistics. Skip current tasks that
* are not in our scheduling class.
*/
update_load_add(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
inc_cpu_load(rq_of(cfs_rq), se->load.weight);
- if (entity_is_task(se))
+ if (entity_is_task(se)) {
add_cfs_task_weight(cfs_rq, se->load.weight);
+ list_add(&se->group_node, &cfs_rq->tasks);
+ }
cfs_rq->nr_running++;
se->on_rq = 1;
- list_add(&se->group_node, &cfs_rq->tasks);
}
static void
update_load_sub(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
dec_cpu_load(rq_of(cfs_rq), se->load.weight);
- if (entity_is_task(se))
+ if (entity_is_task(se)) {
add_cfs_task_weight(cfs_rq, -se->load.weight);
+ list_del_init(&se->group_node);
+ }
cfs_rq->nr_running--;
se->on_rq = 0;
- list_del_init(&se->group_node);
}
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
__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, long wl, int cpu)
+/*
+ * 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 wg = wl;
- for_each_sched_entity(se) {
-#define D(n) (likely(n) ? (n) : 1)
+ 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;
+ for_each_sched_entity(se) {
long S, rw, s, a, b;
+ long more_w;
+
+ /*
+ * 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;
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;
- wl = s*(a-b)/D(b);
+ wl = s*(a-b);
+
+ if (likely(b))
+ wl /= b;
+
+ /*
+ * Assume the group is already running and will
+ * thus already be accounted for in the weight.
+ *
+ * That is, moving shares between CPUs, does not
+ * alter the group weight.
+ */
wg = 0;
-#undef D
}
return wl;
}
-static unsigned long task_load_sub(struct task_struct *p)
-{
- return effective_load(task_group(p), -(long)p->se.load.weight, task_cpu(p));
-}
-
-static unsigned long task_load_add(struct task_struct *p, int cpu)
-{
- return effective_load(task_group(p), p->se.load.weight, cpu);
-}
-
#else
-static unsigned long task_load_sub(struct task_struct *p)
+static inline unsigned long effective_load(struct task_group *tg, int cpu,
+ unsigned long wl, unsigned long wg)
{
- return -p->se.load.weight;
-}
-
-static unsigned long task_load_add(struct task_struct *p, int cpu)
-{
- return p->se.load.weight;
+ return wl;
}
#endif
static int
-wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
+wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
struct task_struct *p, int prev_cpu, int this_cpu, int sync,
int idx, unsigned long load, unsigned long this_load,
unsigned int imbalance)
{
struct task_struct *curr = this_rq->curr;
+ struct task_group *tg;
unsigned long tl = this_load;
unsigned long tl_per_task;
+ unsigned long weight;
int balanced;
if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
return 0;
+ if (!sync && sched_feat(SYNC_WAKEUPS) &&
+ curr->se.avg_overlap < sysctl_sched_migration_cost &&
+ p->se.avg_overlap < sysctl_sched_migration_cost)
+ sync = 1;
+
/*
* If sync wakeup then subtract the (maximum possible)
* effect of the currently running task from the load
* of the current CPU:
*/
- if (sync)
- tl += task_load_sub(current);
+ if (sync) {
+ tg = task_group(current);
+ weight = current->se.load.weight;
+
+ tl += effective_load(tg, this_cpu, -weight, -weight);
+ load += effective_load(tg, prev_cpu, 0, -weight);
+ }
- balanced = 100*(tl + task_load_add(p, this_cpu)) <= imbalance*load;
+ tg = task_group(p);
+ weight = p->se.load.weight;
+
+ balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
+ imbalance*(load + effective_load(tg, prev_cpu, 0, weight));
/*
* If the currently running task will sleep within
* a reasonable amount of time then attract this newly
* woken task:
*/
- if (sync && balanced && curr->sched_class == &fair_sched_class) {
- if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
- p->se.avg_overlap < sysctl_sched_migration_cost)
- return 1;
- }
+ if (sync && balanced)
+ return 1;
schedstat_inc(p, se.nr_wakeups_affine_attempts);
tl_per_task = cpu_avg_load_per_task(this_cpu);
- if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
- balanced) {
+ if (balanced || (tl <= load && tl + target_load(prev_cpu, idx) <=
+ tl_per_task)) {
/*
* This domain has SD_WAKE_AFFINE and
* p is cache cold in this domain, and
struct sched_domain *sd, *this_sd = NULL;
int prev_cpu, this_cpu, new_cpu;
unsigned long load, this_load;
- struct rq *rq, *this_rq;
+ struct rq *this_rq;
unsigned int imbalance;
int idx;
prev_cpu = task_cpu(p);
- rq = task_rq(p);
this_cpu = smp_processor_id();
this_rq = cpu_rq(this_cpu);
new_cpu = prev_cpu;
+ if (prev_cpu == this_cpu)
+ goto out;
/*
* 'this_sd' is the first domain that both
* this_cpu and prev_cpu are present in:
load = source_load(prev_cpu, idx);
this_load = target_load(this_cpu, idx);
- if (wake_affine(rq, this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
+ if (wake_affine(this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
load, this_load, imbalance))
return this_cpu;
- if (prev_cpu == this_cpu)
- goto out;
-
/*
* Start passive balancing when half the imbalance_pct
* limit is reached.
* + nice tasks.
*/
if (sched_feat(ASYM_GRAN))
- gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se);
- else
- gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
+ gran = calc_delta_mine(gran, NICE_0_LOAD, &se->load);
return gran;
}
/*
- * Should 'se' preempt 'curr'.
- *
- * |s1
- * |s2
- * |s3
- * g
- * |<--->|c
- *
- * w(c, s1) = -1
- * w(c, s2) = 0
- * w(c, s3) = 1
- *
- */
-static int
-wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
-{
- s64 gran, vdiff = curr->vruntime - se->vruntime;
-
- if (vdiff < 0)
- return -1;
-
- gran = wakeup_gran(curr);
- if (vdiff > gran)
- return 1;
-
- return 0;
-}
-
-/* return depth at which a sched entity is present in the hierarchy */
-static inline int depth_se(struct sched_entity *se)
-{
- int depth = 0;
-
- for_each_sched_entity(se)
- depth++;
-
- return depth;
-}
-
-/*
* Preempt the current task with a newly woken task if needed:
*/
-static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
+static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
{
struct task_struct *curr = rq->curr;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
struct sched_entity *se = &curr->se, *pse = &p->se;
- int se_depth, pse_depth;
+ s64 delta_exec;
if (unlikely(rt_prio(p->prio))) {
update_rq_clock(rq);
return;
}
- se->last_wakeup = se->sum_exec_runtime;
if (unlikely(se == pse))
return;
cfs_rq_of(pse)->next = pse;
/*
+ * We can come here with TIF_NEED_RESCHED already set from new task
+ * wake up path.
+ */
+ if (test_tsk_need_resched(curr))
+ return;
+
+ /*
* Batch tasks do not preempt (their preemption is driven by
* the tick):
*/
if (!sched_feat(WAKEUP_PREEMPT))
return;
- /*
- * preemption test can be made between sibling entities who are in the
- * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
- * both tasks until we find their ancestors who are siblings of common
- * parent.
- */
-
- /* First walk up until both entities are at same depth */
- se_depth = depth_se(se);
- pse_depth = depth_se(pse);
-
- while (se_depth > pse_depth) {
- se_depth--;
- se = parent_entity(se);
- }
-
- while (pse_depth > se_depth) {
- pse_depth--;
- pse = parent_entity(pse);
- }
-
- while (!is_same_group(se, pse)) {
- se = parent_entity(se);
- pse = parent_entity(pse);
+ if (sched_feat(WAKEUP_OVERLAP) && (sync ||
+ (se->avg_overlap < sysctl_sched_migration_cost &&
+ pse->avg_overlap < sysctl_sched_migration_cost))) {
+ resched_task(curr);
+ return;
}
- if (wakeup_preempt_entity(se, pse) == 1)
+ delta_exec = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+ if (delta_exec > wakeup_gran(pse))
resched_task(curr);
}
struct task_struct *p = NULL;
struct sched_entity *se;
- while (next != &cfs_rq->tasks) {
- se = list_entry(next, struct sched_entity, group_node);
- next = next->next;
+ if (next == &cfs_rq->tasks)
+ return NULL;
- /* Skip over entities that are not tasks */
- if (entity_is_task(se)) {
- p = task_of(se);
- break;
- }
- }
+ se = list_entry(next, struct sched_entity, group_node);
+ p = task_of(se);
+ cfs_rq->balance_iterator = next->next;
- cfs_rq->balance_iterator = next;
return p;
}
rcu_read_lock();
update_h_load(busiest_cpu);
- list_for_each_entry(tg, &task_groups, list) {
+ list_for_each_entry_rcu(tg, &task_groups, list) {
struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu];
unsigned long busiest_h_load = busiest_cfs_rq->h_load;
unsigned long busiest_weight = busiest_cfs_rq->load.weight;
- long rem_load, moved_load;
+ u64 rem_load, moved_load;
/*
* empty group
if (!busiest_cfs_rq->task_weight)
continue;
- rem_load = rem_load_move * busiest_weight;
- rem_load /= busiest_h_load + 1;
+ rem_load = (u64)rem_load_move * busiest_weight;
+ rem_load = div_u64(rem_load, busiest_h_load + 1);
moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
rem_load, sd, idle, all_pinned, this_best_prio,
continue;
moved_load *= busiest_h_load;
- moved_load /= busiest_weight + 1;
+ moved_load = div_u64(moved_load, busiest_weight + 1);
rem_load_move -= moved_load;
if (rem_load_move < 0)
return 0;
}
-#endif
+#endif /* CONFIG_SMP */
/*
* scheduler tick hitting a task of our scheduling class:
* 'current' within the tree based on its new key value.
*/
swap(curr->vruntime, se->vruntime);
+ resched_task(rq->curr);
}
enqueue_task_fair(rq, p, 0);
- resched_task(rq->curr);
}
/*
if (p->prio > oldprio)
resched_task(rq->curr);
} else
- check_preempt_curr(rq, p);
+ check_preempt_curr(rq, p, 0);
}
/*
if (running)
resched_task(rq->curr);
else
- check_preempt_curr(rq, p);
+ check_preempt_curr(rq, p, 0);
}
/* Account for a task changing its policy or group.