sched: hierarchical load vs affine wakeups

With hierarchical grouping we can't just compare task weight to rq weight - we
need to scale the weight appropriately.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 21 insertions, 2 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 7b8d664d6f22..865cb53a7ccf 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1073,6 +1073,25 @@ static inline int wake_idle(int cpu, struct task_struct *p)
 
 static const struct sched_class fair_sched_class;
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static unsigned long task_h_load(struct task_struct *p)
+{
+        unsigned long h_load = p->se.load.weight;
+        struct cfs_rq *cfs_rq = cfs_rq_of(&p->se);
+
+        update_h_load(task_cpu(p));
+
+        h_load = calc_delta_mine(h_load, cfs_rq->h_load, &cfs_rq->load);
+
+        return h_load;
+}
+#else
+static unsigned long task_h_load(struct task_struct *p)
+{
+        return p->se.load.weight;
+}
+#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,
@@ -1093,9 +1112,9 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
          * of the current CPU:
          */
         if (sync)
-                tl -= current->se.load.weight;
+                tl -= task_h_load(current);
 
-        balanced = 100*(tl + p->se.load.weight) <= imbalance*load;
+        balanced = 100*(tl + task_h_load(p)) <= imbalance*load;
 
         /*
          * If the currently running task will sleep within