* Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
*/
+#include <linux/latencytop.h>
+
/*
* Targeted preemption latency for CPU-bound tasks:
- * (default: 20ms * ilog(ncpus), units: nanoseconds)
+ * (default: 20ms * (1 + ilog(ncpus)), units: nanoseconds)
*
* NOTE: this latency value is not the same as the concept of
* 'timeslice length' - timeslices in CFS are of variable length
/*
* Minimal preemption granularity for CPU-bound tasks:
- * (default: 1 msec * ilog(ncpus), units: nanoseconds)
+ * (default: 4 msec * (1 + ilog(ncpus)), units: nanoseconds)
*/
-unsigned int sysctl_sched_min_granularity = 1000000ULL;
+unsigned int sysctl_sched_min_granularity = 4000000ULL;
/*
* is kept at sysctl_sched_latency / sysctl_sched_min_granularity
*/
-unsigned int sched_nr_latency = 20;
+static unsigned int sched_nr_latency = 5;
/*
* After fork, child runs first. (default) If set to 0 then
unsigned int __read_mostly sysctl_sched_compat_yield;
/*
- * SCHED_BATCH wake-up granularity.
- * (default: 10 msec * 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_batch_wakeup_granularity = 10000000UL;
-
-/*
* SCHED_OTHER wake-up granularity.
- * (default: 10 msec * 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;
* CFS operations on generic schedulable entities:
*/
+static inline struct task_struct *task_of(struct sched_entity *se)
+{
+ return container_of(se, struct task_struct, se);
+}
+
#ifdef CONFIG_FAIR_GROUP_SCHED
/* cpu runqueue to which this cfs_rq is attached */
/* An entity is a task if it doesn't "own" a runqueue */
#define entity_is_task(se) (!se->my_q)
+/* Walk up scheduling entities hierarchy */
+#define for_each_sched_entity(se) \
+ for (; se; se = se->parent)
+
+static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
+{
+ return p->se.cfs_rq;
+}
+
+/* runqueue on which this entity is (to be) queued */
+static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
+{
+ return se->cfs_rq;
+}
+
+/* runqueue "owned" by this group */
+static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
+{
+ return grp->my_q;
+}
+
+/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
+ * another cpu ('this_cpu')
+ */
+static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
+{
+ return cfs_rq->tg->cfs_rq[this_cpu];
+}
+
+/* Iterate thr' all leaf cfs_rq's on a runqueue */
+#define for_each_leaf_cfs_rq(rq, cfs_rq) \
+ 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
+is_same_group(struct sched_entity *se, struct sched_entity *pse)
+{
+ if (se->cfs_rq == pse->cfs_rq)
+ return 1;
+
+ return 0;
+}
+
+static inline struct sched_entity *parent_entity(struct sched_entity *se)
+{
+ return se->parent;
+}
+
#else /* CONFIG_FAIR_GROUP_SCHED */
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
#define entity_is_task(se) 1
-#endif /* CONFIG_FAIR_GROUP_SCHED */
+#define for_each_sched_entity(se) \
+ for (; se; se = NULL)
-static inline struct task_struct *task_of(struct sched_entity *se)
+static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
- return container_of(se, struct task_struct, se);
+ return &task_rq(p)->cfs;
+}
+
+static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
+{
+ struct task_struct *p = task_of(se);
+ struct rq *rq = task_rq(p);
+
+ return &rq->cfs;
+}
+
+/* runqueue "owned" by this group */
+static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
+{
+ return NULL;
+}
+
+static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
+{
+ return &cpu_rq(this_cpu)->cfs;
+}
+
+#define for_each_leaf_cfs_rq(rq, cfs_rq) \
+ for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
+
+static inline int
+is_same_group(struct sched_entity *se, struct sched_entity *pse)
+{
+ return 1;
+}
+
+static inline struct sched_entity *parent_entity(struct sched_entity *se)
+{
+ return NULL;
}
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
/**************************************************************
* Scheduling class tree data structure manipulation methods:
* 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);
}
/**************************************************************
#endif
/*
+ * delta *= w / rw
+ */
+static inline unsigned long
+calc_delta_weight(unsigned long delta, struct sched_entity *se)
+{
+ for_each_sched_entity(se) {
+ delta = calc_delta_mine(delta,
+ se->load.weight, &cfs_rq_of(se)->load);
+ }
+
+ return delta;
+}
+
+/*
+ * delta *= rw / w
+ */
+static inline unsigned long
+calc_delta_fair(unsigned long delta, struct sched_entity *se)
+{
+ for_each_sched_entity(se) {
+ delta = calc_delta_mine(delta,
+ cfs_rq_of(se)->load.weight, &se->load);
+ }
+
+ return delta;
+}
+
+/*
* The idea is to set a period in which each task runs once.
*
* When there are too many tasks (sysctl_sched_nr_latency) we have to stretch
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_weight(__sched_period(cfs_rq->nr_running), se);
}
/*
- * We calculate the vruntime slice.
+ * We calculate the vruntime slice of a to be inserted task
*
- * vs = s/w = p/rw
+ * vs = s*rw/w = p
*/
-static u64 __sched_vslice(unsigned long rq_weight, unsigned long nr_running)
+static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- u64 vslice = __sched_period(nr_running);
+ unsigned long nr_running = cfs_rq->nr_running;
- vslice *= NICE_0_LOAD;
- do_div(vslice, rq_weight);
+ if (!se->on_rq)
+ nr_running++;
- return vslice;
+ return __sched_period(nr_running);
}
-static u64 sched_vslice(struct cfs_rq *cfs_rq)
+/*
+ * 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)
{
- return __sched_vslice(cfs_rq->load.weight, cfs_rq->nr_running);
-}
+ struct load_weight lw = {
+ .weight = NICE_0_LOAD,
+ .inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT)
+ };
-static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
- return __sched_vslice(cfs_rq->load.weight + se->load.weight,
- cfs_rq->nr_running + 1);
+ 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;
}
/*
unsigned long delta_exec)
{
unsigned long delta_exec_weighted;
- u64 vruntime;
schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
curr->sum_exec_runtime += delta_exec;
schedstat_add(cfs_rq, exec_clock, delta_exec);
- delta_exec_weighted = delta_exec;
- if (unlikely(curr->load.weight != NICE_0_LOAD)) {
- delta_exec_weighted = calc_delta_fair(delta_exec_weighted,
- &curr->load);
- }
+ delta_exec_weighted = calc_delta_fair(delta_exec, curr);
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);
}
* Scheduling class queueing methods:
*/
+#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
+static void
+add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
+{
+ cfs_rq->task_weight += weight;
+}
+#else
+static inline void
+add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
+{
+}
+#endif
+
static void
account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
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))
+ add_cfs_task_weight(cfs_rq, se->load.weight);
cfs_rq->nr_running++;
se->on_rq = 1;
+ list_add(&se->group_node, &cfs_rq->tasks);
}
static void
account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
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))
+ add_cfs_task_weight(cfs_rq, -se->load.weight);
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)
#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)) {
+ unsigned long thresh = sysctl_sched_latency;
+
+ /*
+ * convert the sleeper threshold into virtual time
+ */
+ if (sched_feat(NORMALIZED_SLEEPER))
+ thresh = calc_delta_fair(thresh, se);
+
+ vruntime -= thresh;
+ }
/* ensure we never gain time by being placed backwards. */
vruntime = max_vruntime(se->vruntime, vruntime);
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
+ account_entity_enqueue(cfs_rq, se);
if (wakeup) {
place_entity(cfs_rq, se, 0);
check_spread(cfs_rq, se);
if (se != cfs_rq->curr)
__enqueue_entity(cfs_rq, se);
- account_entity_enqueue(cfs_rq, se);
}
static void
update_stats_dequeue(cfs_rq, se);
if (sleep) {
- se->peer_preempt = 0;
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
struct task_struct *tsk = task_of(se);
ideal_runtime = sched_slice(cfs_rq, curr);
delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
- if (delta_exec > ideal_runtime ||
- (sched_feat(PREEMPT_RESTRICT) && curr->peer_preempt))
+ if (delta_exec > ideal_runtime)
resched_task(rq_of(cfs_rq)->curr);
- curr->peer_preempt = 0;
}
static void
se->prev_sum_exec_runtime = se->sum_exec_runtime;
}
+static struct sched_entity *
+pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ struct rq *rq = rq_of(cfs_rq);
+ u64 pair_slice = rq->clock - cfs_rq->pair_start;
+
+ if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) {
+ cfs_rq->pair_start = rq->clock;
+ 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) {
+ resched_task(rq_of(cfs_rq)->curr);
+ return;
+ }
+ /*
+ * 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);
}
* CFS operations on tasks:
*/
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_SCHED_HRTICK
+static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
+{
+ struct sched_entity *se = &p->se;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
-/* Walk up scheduling entities hierarchy */
-#define for_each_sched_entity(se) \
- for (; se; se = se->parent)
+ WARN_ON(task_rq(p) != rq);
-static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
-{
- return p->se.cfs_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;
-/* runqueue on which this entity is (to be) queued */
-static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
-{
- return se->cfs_rq;
-}
+ if (delta < 0) {
+ if (rq->curr == p)
+ resched_task(p);
+ return;
+ }
-/* runqueue "owned" by this group */
-static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
+ /*
+ * Don't schedule slices shorter than 10000ns, that just
+ * doesn't make sense. Rely on vruntime for fairness.
+ */
+ if (rq->curr != p)
+ delta = max(10000LL, delta);
+
+ hrtick_start(rq, delta);
+ }
+}
+#else /* !CONFIG_SCHED_HRTICK */
+static inline void
+hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
- return grp->my_q;
}
+#endif
-/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
- * another cpu ('this_cpu')
+/*
+ * The enqueue_task method is called before nr_running is
+ * increased. Here we update the fair scheduling stats and
+ * then put the task into the rbtree:
*/
-static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
+static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
{
- return cfs_rq->tg->cfs_rq[this_cpu];
-}
-
-/* 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)
+ struct cfs_rq *cfs_rq;
+ struct sched_entity *se = &p->se;
-/* Do the two (enqueued) entities belong to the same group ? */
-static inline int
-is_same_group(struct sched_entity *se, struct sched_entity *pse)
-{
- if (se->cfs_rq == pse->cfs_rq)
- return 1;
+ for_each_sched_entity(se) {
+ if (se->on_rq)
+ break;
+ cfs_rq = cfs_rq_of(se);
+ enqueue_entity(cfs_rq, se, wakeup);
+ wakeup = 1;
+ }
- return 0;
-}
-
-static inline struct sched_entity *parent_entity(struct sched_entity *se)
-{
- return se->parent;
-}
-
-#else /* CONFIG_FAIR_GROUP_SCHED */
-
-#define for_each_sched_entity(se) \
- for (; se; se = NULL)
-
-static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
-{
- return &task_rq(p)->cfs;
-}
-
-static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
-{
- struct task_struct *p = task_of(se);
- struct rq *rq = task_rq(p);
-
- return &rq->cfs;
-}
-
-/* runqueue "owned" by this group */
-static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
-{
- return NULL;
-}
-
-static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
-{
- return &cpu_rq(this_cpu)->cfs;
-}
-
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
- for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
-
-static inline int
-is_same_group(struct sched_entity *se, struct sched_entity *pse)
-{
- return 1;
-}
-
-static inline struct sched_entity *parent_entity(struct sched_entity *se)
-{
- return NULL;
-}
-
-#endif /* CONFIG_FAIR_GROUP_SCHED */
-
-/*
- * The enqueue_task method is called before nr_running is
- * increased. Here we update the fair scheduling stats and
- * then put the task into the rbtree:
- */
-static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
-{
- struct cfs_rq *cfs_rq;
- struct sched_entity *se = &p->se;
-
- for_each_sched_entity(se) {
- if (se->on_rq)
- break;
- cfs_rq = cfs_rq_of(se);
- 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)) {
- __update_rq_clock(rq);
+ if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
+ update_rq_clock(rq);
/*
* Update run-time statistics of the 'current'.
*/
/*
* Already in the rightmost position?
*/
- if (unlikely(rightmost->vruntime < se->vruntime))
+ if (unlikely(!rightmost || rightmost->vruntime < se->vruntime))
return;
/*
}
/*
+ * 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.
+ * 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.
+ */
+#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)->cfs.nr_running > 1)
+ return cpu;
+
+ for_each_domain(cpu, sd) {
+ if ((sd->flags & SD_WAKE_IDLE)
+ || ((sd->flags & SD_WAKE_IDLE_FAR)
+ && !task_hot(p, task_rq(p)->clock, sd))) {
+ cpus_and(tmp, sd->span, p->cpus_allowed);
+ 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,
+ se.nr_wakeups_idle);
+ }
+ return i;
+ }
+ }
+ } else {
+ break;
+ }
+ }
+ return cpu;
+}
+#else /* !ARCH_HAS_SCHED_WAKE_IDLE*/
+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;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/*
+ * 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)
+
+ long S, rw, s, a, b;
+
+ S = se->my_q->tg->shares;
+ s = se->my_q->shares;
+ rw = se->my_q->rq_weight;
+
+ a = S*(rw + wl);
+ b = S*rw + s*wg;
+
+ wl = s*(a-b)/D(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;
+}
+
+#else
+
+static inline unsigned long effective_load(struct task_group *tg, int cpu,
+ unsigned long wl, unsigned long wg)
+{
+ return wl;
+}
+
+#endif
+
+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;
+ 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 wakeup then subtract the (maximum possible)
+ * effect of the currently running task from the load
+ * of the current CPU:
+ */
+ 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);
+ }
+
+ 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) {
+ 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 ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
+ balanced) {
+ /*
+ * 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 */
+
+static unsigned long wakeup_gran(struct sched_entity *se)
+{
+ unsigned long gran = sysctl_sched_wakeup_granularity;
+
+ /*
+ * More easily preempt - nice tasks, while not making it harder for
+ * + 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);
+
+ 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)
struct task_struct *curr = rq->curr;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
struct sched_entity *se = &curr->se, *pse = &p->se;
- s64 delta, gran;
+ int se_depth, pse_depth;
if (unlikely(rt_prio(p->prio))) {
update_rq_clock(rq);
resched_task(curr);
return;
}
+
+ if (unlikely(se == pse))
+ return;
+
+ cfs_rq_of(pse)->next = pse;
+
/*
* Batch tasks do not preempt (their preemption is driven by
* the tick):
if (unlikely(p->policy == SCHED_BATCH))
return;
- if (sched_feat(WAKEUP_PREEMPT)) {
- while (!is_same_group(se, pse)) {
- se = parent_entity(se);
- pse = parent_entity(pse);
- }
+ if (!sched_feat(WAKEUP_PREEMPT))
+ return;
- delta = se->vruntime - pse->vruntime;
- gran = sysctl_sched_wakeup_granularity;
- if (unlikely(se->load.weight != NICE_0_LOAD))
- gran = calc_delta_fair(gran, &se->load);
+ /*
+ * 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.
+ */
- if (delta > gran) {
- int now = !sched_feat(PREEMPT_RESTRICT);
+ /* First walk up until both entities are at same depth */
+ se_depth = depth_se(se);
+ pse_depth = depth_se(pse);
- if (now || p->prio < curr->prio || !se->peer_preempt++)
- resched_task(curr);
- }
+ 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 (wakeup_preempt_entity(se, pse) == 1)
+ resched_task(curr);
}
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;
}
/*
* the current task:
*/
static struct task_struct *
-__load_balance_iterator(struct cfs_rq *cfs_rq, struct rb_node *curr)
+__load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
{
- struct task_struct *p;
+ struct task_struct *p = NULL;
+ struct sched_entity *se;
- if (!curr)
- return NULL;
+ while (next != &cfs_rq->tasks) {
+ se = list_entry(next, struct sched_entity, group_node);
+ next = next->next;
- p = rb_entry(curr, struct task_struct, se.run_node);
- cfs_rq->rb_load_balance_curr = rb_next(curr);
+ /* Skip over entities that are not tasks */
+ if (entity_is_task(se)) {
+ p = task_of(se);
+ break;
+ }
+ }
+ cfs_rq->balance_iterator = next;
return p;
}
{
struct cfs_rq *cfs_rq = arg;
- return __load_balance_iterator(cfs_rq, first_fair(cfs_rq));
+ return __load_balance_iterator(cfs_rq, cfs_rq->tasks.next);
}
static struct task_struct *load_balance_next_fair(void *arg)
{
struct cfs_rq *cfs_rq = arg;
- return __load_balance_iterator(cfs_rq, cfs_rq->rb_load_balance_curr);
+ return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
}
-#ifdef CONFIG_FAIR_GROUP_SCHED
-static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
+static unsigned long
+__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ unsigned long max_load_move, struct sched_domain *sd,
+ enum cpu_idle_type idle, int *all_pinned, int *this_best_prio,
+ struct cfs_rq *cfs_rq)
{
- struct sched_entity *curr;
- struct task_struct *p;
-
- if (!cfs_rq->nr_running)
- return MAX_PRIO;
-
- curr = cfs_rq->curr;
- if (!curr)
- curr = __pick_next_entity(cfs_rq);
+ struct rq_iterator cfs_rq_iterator;
- p = task_of(curr);
+ cfs_rq_iterator.start = load_balance_start_fair;
+ cfs_rq_iterator.next = load_balance_next_fair;
+ cfs_rq_iterator.arg = cfs_rq;
- return p->prio;
+ return balance_tasks(this_rq, this_cpu, busiest,
+ max_load_move, sd, idle, all_pinned,
+ this_best_prio, &cfs_rq_iterator);
}
-#endif
+#ifdef CONFIG_FAIR_GROUP_SCHED
static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, int *this_best_prio)
{
- struct cfs_rq *busy_cfs_rq;
long rem_load_move = max_load_move;
- struct rq_iterator cfs_rq_iterator;
+ int busiest_cpu = cpu_of(busiest);
+ struct task_group *tg;
- cfs_rq_iterator.start = load_balance_start_fair;
- cfs_rq_iterator.next = load_balance_next_fair;
+ rcu_read_lock();
+ update_h_load(busiest_cpu);
- for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
-#ifdef CONFIG_FAIR_GROUP_SCHED
- struct cfs_rq *this_cfs_rq;
- long imbalance;
- unsigned long maxload;
-
- this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu);
+ list_for_each_entry(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;
+ u64 rem_load, moved_load;
- imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight;
- /* Don't pull if this_cfs_rq has more load than busy_cfs_rq */
- if (imbalance <= 0)
+ /*
+ * empty group
+ */
+ if (!busiest_cfs_rq->task_weight)
continue;
- /* Don't pull more than imbalance/2 */
- imbalance /= 2;
- maxload = min(rem_load_move, imbalance);
+ rem_load = (u64)rem_load_move * busiest_weight;
+ rem_load = div_u64(rem_load, busiest_h_load + 1);
- *this_best_prio = cfs_rq_best_prio(this_cfs_rq);
-#else
-# define maxload rem_load_move
-#endif
- /*
- * pass busy_cfs_rq argument into
- * load_balance_[start|next]_fair iterators
- */
- cfs_rq_iterator.arg = busy_cfs_rq;
- rem_load_move -= balance_tasks(this_rq, this_cpu, busiest,
- maxload, sd, idle, all_pinned,
- this_best_prio,
- &cfs_rq_iterator);
+ moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
+ rem_load, sd, idle, all_pinned, this_best_prio,
+ tg->cfs_rq[busiest_cpu]);
+
+ if (!moved_load)
+ continue;
- if (rem_load_move <= 0)
+ moved_load *= busiest_h_load;
+ moved_load = div_u64(moved_load, busiest_weight + 1);
+
+ rem_load_move -= moved_load;
+ if (rem_load_move < 0)
break;
}
+ rcu_read_unlock();
return max_load_move - rem_load_move;
}
+#else
+static unsigned long
+load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ unsigned long max_load_move,
+ struct sched_domain *sd, enum cpu_idle_type idle,
+ int *all_pinned, int *this_best_prio)
+{
+ return __load_balance_fair(this_rq, this_cpu, busiest,
+ max_load_move, sd, idle, all_pinned,
+ this_best_prio, &busiest->cfs);
+}
+#endif
static int
move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
return 0;
}
-#endif
+#endif /* CONFIG_SMP */
/*
* 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);
}
}
update_curr(cfs_rq);
place_entity(cfs_rq, se, 1);
+ /* 'curr' will be NULL if the child belongs to a different group */
if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
- curr->vruntime < se->vruntime) {
+ curr && curr->vruntime < se->vruntime) {
/*
* Upon rescheduling, sched_class::put_prev_task() will place
* 'current' within the tree based on its new key value.
swap(curr->vruntime, se->vruntime);
}
- se->peer_preempt = 0;
enqueue_task_fair(rq, p, 0);
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
{
struct cfs_rq *cfs_rq;
-#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
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff