sched: persistent average load per task

Remove the fall-back to SCHED_LOAD_SCALE by remembering the previous value of
cpu_avg_load_per_task() - this is useful because of the hierarchical group
model in which task weight can be much smaller.

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, 12 insertions, 13 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 39d5495540d2..6a6b0139eb32 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -554,6 +554,8 @@ struct rq {
         int cpu;
         int online;
 
+        unsigned long avg_load_per_task;
+
         struct task_struct *migration_thread;
         struct list_head migration_queue;
 #endif
@@ -1427,9 +1429,18 @@ static inline void dec_cpu_load(struct rq *rq, unsigned long load)
 #ifdef CONFIG_SMP
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
-static unsigned long cpu_avg_load_per_task(int cpu);
 static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
 
+static unsigned long cpu_avg_load_per_task(int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+
+        if (rq->nr_running)
+                rq->avg_load_per_task = rq->load.weight / rq->nr_running;
+
+        return rq->avg_load_per_task;
+}
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
 typedef void (*tg_visitor)(struct task_group *, int, struct sched_domain *);
@@ -2011,18 +2022,6 @@ static unsigned long target_load(int cpu, int type)
 }
 
 /*
- * Return the average load per task on the cpu's run queue
- */
-static unsigned long cpu_avg_load_per_task(int cpu)
-{
-        struct rq *rq = cpu_rq(cpu);
-        unsigned long total = weighted_cpuload(cpu);
-        unsigned long n = rq->nr_running;
-
-        return n ? total / n : SCHED_LOAD_SCALE;
-}
-
-/*
  * find_idlest_group finds and returns the least busy CPU group within the
  * domain.
  */