sched: introduce avg_wakeup

Introduce a new avg_wakeup statistic.

avg_wakeup is a measure of how frequently a task wakes up other tasks, it
represents the average time between wakeups, with a limit of avg_runtime
for when it doesn't wake up anybody.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4cae9b8..daf4e07 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1046,6 +1046,9 @@ struct sched_entity {
        u64                     exec_max;
        u64                     slice_max;
 
+       u64                     start_runtime;
+       u64                     avg_wakeup;
+
        u64                     nr_migrations;
        u64                     nr_migrations_cold;
        u64                     nr_failed_migrations_affine;

diff --git a/kernel/sched.c b/kernel/sched.c
index 8be2c13..86f5a06 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1705,6 +1705,9 @@ static void update_avg(u64 *avg, u64 sample)
 
 static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
 {
+       if (wakeup)
+               p->se.start_runtime = p->se.sum_exec_runtime;
+
        sched_info_queued(p);
        p->sched_class->enqueue_task(rq, p, wakeup);
        p->se.on_rq = 1;
@@ -1712,10 +1715,15 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
 
 static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
 {
-       if (sleep && p->se.last_wakeup) {
-               update_avg(&p->se.avg_overlap,
-                          p->se.sum_exec_runtime - p->se.last_wakeup);
-               p->se.last_wakeup = 0;
+       if (sleep) {
+               if (p->se.last_wakeup) {
+                       update_avg(&p->se.avg_overlap,
+                               p->se.sum_exec_runtime - p->se.last_wakeup);
+                       p->se.last_wakeup = 0;
+               } else {
+                       update_avg(&p->se.avg_wakeup,
+                               sysctl_sched_wakeup_granularity);
+               }
        }
 
        sched_info_dequeued(p);
@@ -2345,6 +2353,22 @@ out_activate:
        activate_task(rq, p, 1);
        success = 1;
 
+       /*
+        * Only attribute actual wakeups done by this task.
+        */
+       if (!in_interrupt()) {
+               struct sched_entity *se = &current->se;
+               u64 sample = se->sum_exec_runtime;
+
+               if (se->last_wakeup)
+                       sample -= se->last_wakeup;
+               else
+                       sample -= se->start_runtime;
+               update_avg(&se->avg_wakeup, sample);
+
+               se->last_wakeup = se->sum_exec_runtime;
+       }
+
 out_running:
        trace_sched_wakeup(rq, p, success);
        check_preempt_curr(rq, p, sync);
@@ -2355,8 +2379,6 @@ out_running:
                p->sched_class->task_wake_up(rq, p);
 #endif
 out:
-       current->se.last_wakeup = current->se.sum_exec_runtime;
-
        task_rq_unlock(rq, &flags);
 
        return success;
@@ -2386,6 +2408,8 @@ static void __sched_fork(struct task_struct *p)
        p->se.prev_sum_exec_runtime     = 0;
        p->se.last_wakeup               = 0;
        p->se.avg_overlap               = 0;
+       p->se.start_runtime             = 0;
+       p->se.avg_wakeup                = sysctl_sched_wakeup_granularity;
 
 #ifdef CONFIG_SCHEDSTATS
        p->se.wait_start                = 0;

diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 16eeba4..2b1260f 100644 (file)
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -397,6 +397,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
        PN(se.vruntime);
        PN(se.sum_exec_runtime);
        PN(se.avg_overlap);
+       PN(se.avg_wakeup);
 
        nr_switches = p->nvcsw + p->nivcsw;