*/
unsigned int sysctl_sched_min_granularity __read_mostly = 2000000ULL;
+/*
+ * sys_sched_yield() compat mode
+ *
+ * This option switches the agressive yield implementation of the
+ * old scheduler back on.
+ */
+unsigned int __read_mostly sysctl_sched_compat_yield;
+
/*
* SCHED_BATCH wake-up granularity.
* (default: 25 msec, units: nanoseconds)
update_load_add(&cfs_rq->load, se->load.weight);
cfs_rq->nr_running++;
se->on_rq = 1;
+
+ schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
}
static inline void
update_load_sub(&cfs_rq->load, se->load.weight);
cfs_rq->nr_running--;
se->on_rq = 0;
+
+ schedstat_add(cfs_rq, wait_runtime, -se->wait_runtime);
}
static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq)
/*
* It will always fit into 'long':
*/
- return (long) (tmp >> WMULT_SHIFT);
+ return (long) (tmp >> (WMULT_SHIFT-NICE_0_SHIFT));
}
static inline void
prev_runtime = se->wait_runtime;
__add_wait_runtime(cfs_rq, se, delta_fair);
- schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
delta_fair = se->wait_runtime - prev_runtime;
/*
if (tsk->state & TASK_UNINTERRUPTIBLE)
se->block_start = rq_of(cfs_rq)->clock;
}
- cfs_rq->wait_runtime -= se->wait_runtime;
#endif
}
__dequeue_entity(cfs_rq, se);
/*
* Preempt the current task with a newly woken task if needed:
*/
-static int
+static void
__check_preempt_curr_fair(struct cfs_rq *cfs_rq, struct sched_entity *se,
struct sched_entity *curr, unsigned long granularity)
{
s64 __delta = curr->fair_key - se->fair_key;
+ unsigned long ideal_runtime, delta_exec;
+
+ /*
+ * ideal_runtime is compared against sum_exec_runtime, which is
+ * walltime, hence do not scale.
+ */
+ ideal_runtime = max(sysctl_sched_latency / cfs_rq->nr_running,
+ (unsigned long)sysctl_sched_min_granularity);
+
+ /*
+ * If we executed more than what the latency constraint suggests,
+ * reduce the rescheduling granularity. This way the total latency
+ * of how much a task is not scheduled converges to
+ * sysctl_sched_latency:
+ */
+ delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
+ if (delta_exec > ideal_runtime)
+ granularity = 0;
/*
* Take scheduling granularity into account - do not
* preempt the current task unless the best task has
* a larger than sched_granularity fairness advantage:
+ *
+ * scale granularity as key space is in fair_clock.
*/
- if (__delta > niced_granularity(curr, granularity)) {
+ if (__delta > niced_granularity(curr, granularity))
resched_task(rq_of(cfs_rq)->curr);
- return 1;
- }
- return 0;
}
static inline void
update_stats_wait_end(cfs_rq, se);
update_stats_curr_start(cfs_rq, se);
set_cfs_rq_curr(cfs_rq, se);
+ se->prev_sum_exec_runtime = se->sum_exec_runtime;
}
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
static void entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
- unsigned long gran, ideal_runtime, delta_exec;
struct sched_entity *next;
/*
if (next == curr)
return;
- gran = sched_granularity(cfs_rq);
- ideal_runtime = niced_granularity(curr,
- max(sysctl_sched_latency / cfs_rq->nr_running,
- (unsigned long)sysctl_sched_min_granularity));
- /*
- * If we executed more than what the latency constraint suggests,
- * reduce the rescheduling granularity. This way the total latency
- * of how much a task is not scheduled converges to
- * sysctl_sched_latency:
- */
- delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
- if (delta_exec > ideal_runtime)
- gran = 0;
-
- if (__check_preempt_curr_fair(cfs_rq, next, curr, gran))
- curr->prev_sum_exec_runtime = curr->sum_exec_runtime;
+ __check_preempt_curr_fair(cfs_rq, next, curr,
+ sched_granularity(cfs_rq));
}
/**************************************************
}
/*
- * sched_yield() support is very simple - we dequeue and enqueue
+ * sched_yield() support is very simple - we dequeue and enqueue.
+ *
+ * If compat_yield is turned on then we requeue to the end of the tree.
*/
static void yield_task_fair(struct rq *rq, struct task_struct *p)
{
struct cfs_rq *cfs_rq = task_cfs_rq(p);
+ struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
+ struct sched_entity *rightmost, *se = &p->se;
+ struct rb_node *parent;
- __update_rq_clock(rq);
/*
- * Dequeue and enqueue the task to update its
- * position within the tree:
+ * 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);
+ /*
+ * Dequeue and enqueue the task to update its
+ * position within the tree:
+ */
+ dequeue_entity(cfs_rq, &p->se, 0);
+ enqueue_entity(cfs_rq, &p->se, 0);
+
+ return;
+ }
+ /*
+ * Find the rightmost entry in the rbtree:
+ */
+ do {
+ parent = *link;
+ link = &parent->rb_right;
+ } while (*link);
+
+ rightmost = rb_entry(parent, struct sched_entity, run_node);
+ /*
+ * Already in the rightmost position?
+ */
+ if (unlikely(rightmost == se))
+ return;
+
+ /*
+ * Minimally necessary key value to be last in the tree:
+ */
+ se->fair_key = rightmost->fair_key + 1;
+
+ if (cfs_rq->rb_leftmost == &se->run_node)
+ cfs_rq->rb_leftmost = rb_next(&se->run_node);
+ /*
+ * Relink the task to the rightmost position:
*/
- dequeue_entity(cfs_rq, &p->se, 0);
- enqueue_entity(cfs_rq, &p->se, 0);
+ rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
+ rb_link_node(&se->run_node, parent, link);
+ rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
}
/*
* The statistical average of wait_runtime is about
* -granularity/2, so initialize the task with that:
*/
- if (sysctl_sched_features & SCHED_FEAT_START_DEBIT) {
+ if (sysctl_sched_features & SCHED_FEAT_START_DEBIT)
se->wait_runtime = -(sched_granularity(cfs_rq) / 2);
- schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
- }
__enqueue_entity(cfs_rq, se);
}