sched: fix buddie group latency

Similar to the previous patch, by not clearing buddies we can select entities
past their run quota, which can increase latency. This means we have to clear
group buddies as well.

Do not use the group clear for pick_next_task(), otherwise that'll get O(n^2).

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 75248b9ff4c19902b4ba1cbc8b44c98b899fb8e3..a7e50ba185ac0a843ac16604e13a721ca8e4cb8e 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -719,7 +719,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
                __enqueue_entity(cfs_rq, se);
 }
 
-static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
        if (cfs_rq->last == se)
                cfs_rq->last = NULL;
@@ -728,6 +728,12 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
                cfs_rq->next = NULL;
 }
 
+static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+       for_each_sched_entity(se)
+               __clear_buddies(cfs_rq_of(se), se);
+}
+
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
@@ -1455,7 +1461,7 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
                 * If se was a buddy, clear it so that it will have to earn
                 * the favour again.
                 */
-               clear_buddies(cfs_rq, se);
+               __clear_buddies(cfs_rq, se);
                set_next_entity(cfs_rq, se);
                cfs_rq = group_cfs_rq(se);
        } while (cfs_rq);