sched: fix wakeup granularity for buddies

The wakeup buddy logic didn't use the same wakeup granularity logic as the
wakeup preemption did, this might cause the ->next buddy to be selected past
the point where we would have preempted had the task been a single running
instance.

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

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 86a93376282c2e43773dba5d6a11762e111a5eb6..b01f8e77f2ac022753f526267b6ee8e5d168c37c 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -73,13 +73,13 @@ unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL;
 
 /*
  * SCHED_OTHER wake-up granularity.
- * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 10 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 = 5000000UL;
+unsigned int sysctl_sched_wakeup_granularity = 10000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
@@ -629,20 +629,16 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
        se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
+static int
+wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
+
 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)
+       if (wakeup_preempt_entity(cfs_rq->next, se) != 0)
                return se;
 
        return cfs_rq->next;
@@ -1101,6 +1097,48 @@ out:
 }
 #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 (unlikely(se->load.weight > NICE_0_LOAD))
+               gran = calc_delta_fair(gran, &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;
+}
 
 /*
  * Preempt the current task with a newly woken task if needed:
@@ -1110,7 +1148,6 @@ 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;
-       unsigned long gran;
 
        if (unlikely(rt_prio(p->prio))) {
                update_rq_clock(rq);
@@ -1140,15 +1177,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
                pse = parent_entity(pse);
        }
 
-       gran = sysctl_sched_wakeup_granularity;
-       /*
-        * 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)
+       if (wakeup_preempt_entity(se, pse) == 1)
                resched_task(curr);
 }