* Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
*/
+#include <linux/latencytop.h>
+
/*
* Targeted preemption latency for CPU-bound tasks:
* (default: 20ms * (1 + ilog(ncpus)), units: nanoseconds)
/*
* SCHED_OTHER wake-up granularity.
- * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds)
*
* This option delays the preemption effects of decoupled workloads
* and reduces their over-scheduling. Synchronous workloads will still
* have immediate wakeup/sleep latencies.
*/
-unsigned int sysctl_sched_wakeup_granularity = 10000000UL;
+unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
* Maintain a cache of leftmost tree entries (it is frequently
* used):
*/
- if (leftmost)
+ if (leftmost) {
cfs_rq->rb_leftmost = &se->run_node;
+ /*
+ * maintain cfs_rq->min_vruntime to be a monotonic increasing
+ * value tracking the leftmost vruntime in the tree.
+ */
+ cfs_rq->min_vruntime =
+ max_vruntime(cfs_rq->min_vruntime, se->vruntime);
+ }
rb_link_node(&se->run_node, parent, link);
rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- if (cfs_rq->rb_leftmost == &se->run_node)
- cfs_rq->rb_leftmost = rb_next(&se->run_node);
+ if (cfs_rq->rb_leftmost == &se->run_node) {
+ struct rb_node *next_node;
+ struct sched_entity *next;
+
+ next_node = rb_next(&se->run_node);
+ cfs_rq->rb_leftmost = next_node;
+
+ if (next_node) {
+ next = rb_entry(next_node,
+ struct sched_entity, run_node);
+ cfs_rq->min_vruntime =
+ max_vruntime(cfs_rq->min_vruntime,
+ next->vruntime);
+ }
+ }
+
+ if (cfs_rq->next == se)
+ cfs_rq->next = NULL;
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
}
static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
{
- struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
- struct sched_entity *se = NULL;
- struct rb_node *parent;
+ struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
- while (*link) {
- parent = *link;
- se = rb_entry(parent, struct sched_entity, run_node);
- link = &parent->rb_right;
- }
+ if (!last)
+ return NULL;
- return se;
+ return rb_entry(last, struct sched_entity, run_node);
}
/**************************************************************
unsigned long nr_latency = sched_nr_latency;
if (unlikely(nr_running > nr_latency)) {
+ period = sysctl_sched_min_granularity;
period *= nr_running;
- do_div(period, nr_latency);
}
return period;
*/
static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- u64 slice = __sched_period(cfs_rq->nr_running);
-
- slice *= se->load.weight;
- do_div(slice, cfs_rq->load.weight);
-
- return slice;
+ return calc_delta_mine(__sched_period(cfs_rq->nr_running),
+ se->load.weight, &cfs_rq->load);
}
/*
return vslice;
}
-static u64 sched_vslice(struct cfs_rq *cfs_rq)
-{
- return __sched_vslice(cfs_rq->load.weight, cfs_rq->nr_running);
-}
-
static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
return __sched_vslice(cfs_rq->load.weight + se->load.weight,
unsigned long delta_exec)
{
unsigned long delta_exec_weighted;
- u64 vruntime;
schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
&curr->load);
}
curr->vruntime += delta_exec_weighted;
-
- /*
- * maintain cfs_rq->min_vruntime to be a monotonic increasing
- * value tracking the leftmost vruntime in the tree.
- */
- if (first_fair(cfs_rq)) {
- vruntime = min_vruntime(curr->vruntime,
- __pick_next_entity(cfs_rq)->vruntime);
- } else
- vruntime = curr->vruntime;
-
- cfs_rq->min_vruntime =
- max_vruntime(cfs_rq->min_vruntime, vruntime);
}
static void update_curr(struct cfs_rq *cfs_rq)
__update_curr(cfs_rq, curr, delta_exec);
curr->exec_start = now;
+
+ if (entity_is_task(curr)) {
+ struct task_struct *curtask = task_of(curr);
+
+ cpuacct_charge(curtask, delta_exec);
+ }
}
static inline void
{
schedstat_set(se->wait_max, max(se->wait_max,
rq_of(cfs_rq)->clock - se->wait_start));
+ schedstat_set(se->wait_count, se->wait_count + 1);
+ schedstat_set(se->wait_sum, se->wait_sum +
+ rq_of(cfs_rq)->clock - se->wait_start);
schedstat_set(se->wait_start, 0);
}
#ifdef CONFIG_SCHEDSTATS
if (se->sleep_start) {
u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
+ struct task_struct *tsk = task_of(se);
if ((s64)delta < 0)
delta = 0;
se->sleep_start = 0;
se->sum_sleep_runtime += delta;
+
+ account_scheduler_latency(tsk, delta >> 10, 1);
}
if (se->block_start) {
u64 delta = rq_of(cfs_rq)->clock - se->block_start;
+ struct task_struct *tsk = task_of(se);
if ((s64)delta < 0)
delta = 0;
* time that the task spent sleeping:
*/
if (unlikely(prof_on == SLEEP_PROFILING)) {
- struct task_struct *tsk = task_of(se);
profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
delta >> 20);
}
+ account_scheduler_latency(tsk, delta >> 10, 0);
}
#endif
}
{
u64 vruntime;
- vruntime = cfs_rq->min_vruntime;
-
- if (sched_feat(TREE_AVG)) {
- struct sched_entity *last = __pick_last_entity(cfs_rq);
- if (last) {
- vruntime += last->vruntime;
- vruntime >>= 1;
- }
- } else if (sched_feat(APPROX_AVG) && cfs_rq->nr_running)
- vruntime += sched_vslice(cfs_rq)/2;
+ if (first_fair(cfs_rq)) {
+ vruntime = min_vruntime(cfs_rq->min_vruntime,
+ __pick_next_entity(cfs_rq)->vruntime);
+ } else
+ vruntime = cfs_rq->min_vruntime;
/*
* The 'current' period is already promised to the current tasks,
if (!initial) {
/* sleeps upto a single latency don't count. */
- if (sched_feat(NEW_FAIR_SLEEPERS) && entity_is_task(se) &&
- task_of(se)->policy != SCHED_BATCH)
- vruntime -= sysctl_sched_latency;
+ if (sched_feat(NEW_FAIR_SLEEPERS)) {
+ vruntime -= calc_delta_fair(sysctl_sched_latency,
+ &cfs_rq->load);
+ }
/* ensure we never gain time by being placed backwards. */
vruntime = max_vruntime(se->vruntime, vruntime);
account_entity_enqueue(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);
se->prev_sum_exec_runtime = se->sum_exec_runtime;
}
+static struct sched_entity *
+pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ s64 diff, gran;
+
+ if (!cfs_rq->next)
+ return se;
+
+ diff = cfs_rq->next->vruntime - se->vruntime;
+ if (diff < 0)
+ return se;
+
+ gran = calc_delta_fair(sysctl_sched_wakeup_granularity, &cfs_rq->load);
+ if (diff > gran)
+ return se;
+
+ return cfs_rq->next;
+}
+
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
struct sched_entity *se = NULL;
if (first_fair(cfs_rq)) {
se = __pick_next_entity(cfs_rq);
+ se = pick_next(cfs_rq, se);
set_next_entity(cfs_rq, se);
}
cfs_rq->curr = NULL;
}
-static void entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
+static void
+entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
{
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
+#ifdef CONFIG_SCHED_HRTICK
+ /*
+ * queued ticks are scheduled to match the slice, so don't bother
+ * validating it and just reschedule.
+ */
+ if (queued)
+ return resched_task(rq_of(cfs_rq)->curr);
+ /*
+ * don't let the period tick interfere with the hrtick preemption
+ */
+ if (!sched_feat(DOUBLE_TICK) &&
+ hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
+ return;
+#endif
+
if (cfs_rq->nr_running > 1 || !sched_feat(WAKEUP_PREEMPT))
check_preempt_tick(cfs_rq, curr);
}
/* Iterate thr' all leaf cfs_rq's on a runqueue */
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
- list_for_each_entry(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
+ list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
/* Do the two (enqueued) entities belong to the same group ? */
static inline int
#endif /* CONFIG_FAIR_GROUP_SCHED */
+#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);
+
+ WARN_ON(task_rq(p) != rq);
+
+ if (hrtick_enabled(rq) && cfs_rq->nr_running > 1) {
+ u64 slice = sched_slice(cfs_rq, se);
+ u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+ s64 delta = slice - ran;
+
+ if (delta < 0) {
+ if (rq->curr == p)
+ resched_task(p);
+ return;
+ }
+
+ /*
+ * Don't schedule slices shorter than 10000ns, that just
+ * doesn't make sense. Rely on vruntime for fairness.
+ */
+ if (!requeue)
+ delta = max(10000LL, delta);
+
+ hrtick_start(rq, delta, requeue);
+ }
+}
+#else
+static inline void
+hrtick_start_fair(struct rq *rq, struct task_struct *p)
+{
+}
+#endif
+
/*
* The enqueue_task method is called before nr_running is
* increased. Here we update the fair scheduling stats and
enqueue_entity(cfs_rq, se, wakeup);
wakeup = 1;
}
+
+ hrtick_start_fair(rq, rq->curr);
}
/*
break;
sleep = 1;
}
+
+ hrtick_start_fair(rq, rq->curr);
}
/*
*/
static void yield_task_fair(struct rq *rq)
{
- struct cfs_rq *cfs_rq = task_cfs_rq(rq->curr);
- struct sched_entity *rightmost, *se = &rq->curr->se;
+ struct task_struct *curr = rq->curr;
+ struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+ struct sched_entity *rightmost, *se = &curr->se;
/*
* Are we the only task in the tree?
if (unlikely(cfs_rq->nr_running == 1))
return;
- if (likely(!sysctl_sched_compat_yield)) {
+ if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
__update_rq_clock(rq);
/*
* Update run-time statistics of the 'current'.
se->vruntime = rightmost->vruntime + 1;
}
+/*
+ * wake_idle() will wake a task on an idle cpu if task->cpu is
+ * 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.
+ *
+ * Returns the CPU we should wake onto.
+ */
+#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
+static int wake_idle(int cpu, struct task_struct *p)
+{
+ cpumask_t tmp;
+ struct sched_domain *sd;
+ int i;
+
+ /*
+ * If it is idle, then it is the best cpu to run this task.
+ *
+ * This cpu is also the best, if it has more than one task already.
+ * Siblings must be also busy(in most cases) as they didn't already
+ * pickup the extra load from this cpu and hence we need not check
+ * sibling runqueue info. This will avoid the checks and cache miss
+ * penalities associated with that.
+ */
+ if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
+ return cpu;
+
+ for_each_domain(cpu, sd) {
+ if (sd->flags & SD_WAKE_IDLE) {
+ cpus_and(tmp, sd->span, p->cpus_allowed);
+ for_each_cpu_mask(i, tmp) {
+ if (idle_cpu(i)) {
+ if (i != task_cpu(p)) {
+ schedstat_inc(p,
+ se.nr_wakeups_idle);
+ }
+ return i;
+ }
+ }
+ } else {
+ break;
+ }
+ }
+ return cpu;
+}
+#else
+static inline int wake_idle(int cpu, struct task_struct *p)
+{
+ return cpu;
+}
+#endif
+
+#ifdef CONFIG_SMP
+
+static const struct sched_class fair_sched_class;
+
+static int
+wake_affine(struct rq *rq, 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;
+ unsigned long tl = this_load;
+ unsigned long tl_per_task;
+
+ if (!(this_sd->flags & SD_WAKE_AFFINE))
+ return 0;
+
+ /*
+ * If the currently running task will sleep within
+ * a reasonable amount of time then attract this newly
+ * woken task:
+ */
+ if (sync && 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;
+ }
+
+ schedstat_inc(p, se.nr_wakeups_affine_attempts);
+ tl_per_task = cpu_avg_load_per_task(this_cpu);
+
+ /*
+ * If sync wakeup then subtract the (maximum possible)
+ * effect of the currently running task from the load
+ * of the current CPU:
+ */
+ if (sync)
+ tl -= current->se.load.weight;
+
+ if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
+ 100*(tl + p->se.load.weight) <= imbalance*load) {
+ /*
+ * This domain has SD_WAKE_AFFINE and
+ * p is cache cold in this domain, and
+ * there is no bad imbalance.
+ */
+ schedstat_inc(this_sd, ttwu_move_affine);
+ schedstat_inc(p, se.nr_wakeups_affine);
+
+ return 1;
+ }
+ return 0;
+}
+
+static int select_task_rq_fair(struct task_struct *p, int sync)
+{
+ struct sched_domain *sd, *this_sd = NULL;
+ int prev_cpu, this_cpu, new_cpu;
+ unsigned long load, this_load;
+ struct rq *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;
+
+ /*
+ * 'this_sd' is the first domain that both
+ * this_cpu and prev_cpu are present in:
+ */
+ for_each_domain(this_cpu, sd) {
+ if (cpu_isset(prev_cpu, sd->span)) {
+ this_sd = sd;
+ break;
+ }
+ }
+
+ if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
+ goto out;
+
+ /*
+ * Check for affine wakeup and passive balancing possibilities.
+ */
+ if (!this_sd)
+ goto out;
+
+ idx = this_sd->wake_idx;
+
+ imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
+
+ 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,
+ 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.
+ */
+ if (this_sd->flags & SD_WAKE_BALANCE) {
+ if (imbalance*this_load <= 100*load) {
+ schedstat_inc(this_sd, ttwu_move_balance);
+ schedstat_inc(p, se.nr_wakeups_passive);
+ return this_cpu;
+ }
+ }
+
+out:
+ return wake_idle(new_cpu, p);
+}
+#endif /* CONFIG_SMP */
+
+
/*
* Preempt the current task with a newly woken task if needed:
*/
resched_task(curr);
return;
}
+
+ se->last_wakeup = se->sum_exec_runtime;
+ if (unlikely(se == pse))
+ return;
+
+ cfs_rq_of(pse)->next = pse;
+
/*
* Batch tasks do not preempt (their preemption is driven by
* the tick):
}
gran = sysctl_sched_wakeup_granularity;
- if (unlikely(se->load.weight != NICE_0_LOAD))
+ /*
+ * More easily preempt - nice tasks, while not making
+ * it harder for + nice tasks.
+ */
+ if (unlikely(se->load.weight > NICE_0_LOAD))
gran = calc_delta_fair(gran, &se->load);
if (pse->vruntime + gran < se->vruntime)
static struct task_struct *pick_next_task_fair(struct rq *rq)
{
+ struct task_struct *p;
struct cfs_rq *cfs_rq = &rq->cfs;
struct sched_entity *se;
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
- return task_of(se);
+ p = task_of(se);
+ hrtick_start_fair(rq, p);
+
+ return p;
}
/*
struct sched_entity *curr;
struct task_struct *p;
- if (!cfs_rq->nr_running)
+ if (!cfs_rq->nr_running || !first_fair(cfs_rq))
return MAX_PRIO;
curr = cfs_rq->curr;
/*
* scheduler tick hitting a task of our scheduling class:
*/
-static void task_tick_fair(struct rq *rq, struct task_struct *curr)
+static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &curr->se;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
- entity_tick(cfs_rq, se);
+ entity_tick(cfs_rq, se, queued);
}
}
resched_task(rq->curr);
}
+/*
+ * Priority of the task has changed. Check to see if we preempt
+ * the current task.
+ */
+static void prio_changed_fair(struct rq *rq, struct task_struct *p,
+ int oldprio, int running)
+{
+ /*
+ * Reschedule if we are currently running on this runqueue and
+ * our priority decreased, or if we are not currently running on
+ * this runqueue and our priority is higher than the current's
+ */
+ if (running) {
+ if (p->prio > oldprio)
+ resched_task(rq->curr);
+ } else
+ check_preempt_curr(rq, p);
+}
+
+/*
+ * We switched to the sched_fair class.
+ */
+static void switched_to_fair(struct rq *rq, struct task_struct *p,
+ int running)
+{
+ /*
+ * We were most likely switched from sched_rt, so
+ * kick off the schedule if running, otherwise just see
+ * if we can still preempt the current task.
+ */
+ if (running)
+ resched_task(rq->curr);
+ else
+ check_preempt_curr(rq, p);
+}
+
/* Account for a task changing its policy or group.
*
* This routine is mostly called to set cfs_rq->curr field when a task
set_next_entity(cfs_rq_of(se), se);
}
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void moved_group_fair(struct task_struct *p)
+{
+ struct cfs_rq *cfs_rq = task_cfs_rq(p);
+
+ update_curr(cfs_rq);
+ place_entity(cfs_rq, &p->se, 1);
+}
+#endif
+
/*
* All the scheduling class methods:
*/
.enqueue_task = enqueue_task_fair,
.dequeue_task = dequeue_task_fair,
.yield_task = yield_task_fair,
+#ifdef CONFIG_SMP
+ .select_task_rq = select_task_rq_fair,
+#endif /* CONFIG_SMP */
.check_preempt_curr = check_preempt_wakeup,
.set_curr_task = set_curr_task_fair,
.task_tick = task_tick_fair,
.task_new = task_new_fair,
+
+ .prio_changed = prio_changed_fair,
+ .switched_to = switched_to_fair,
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ .moved_group = moved_group_fair,
+#endif
};
#ifdef CONFIG_SCHED_DEBUG
#ifdef CONFIG_FAIR_GROUP_SCHED
print_cfs_rq(m, cpu, &cpu_rq(cpu)->cfs);
#endif
+ rcu_read_lock();
for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
print_cfs_rq(m, cpu, cfs_rq);
+ rcu_read_unlock();
}
#endif