sched: Remove irq time from available CPU power

The idea was suggested by Peter Zijlstra here:

  http://marc.info/?l=linux-kernel&m=127476934517534&w=2

irq time is technically not available to the tasks running on the CPU.
This patch removes irq time from CPU power piggybacking on
sched_rt_avg_update().

Tested this by keeping CPU X busy with a network intensive task having 75%
oa a single CPU irq processing (hard+soft) on a 4-way system. And start seven
cycle soakers on the system. Without this change, there will be two tasks on
each CPU. With this change, there is a single task on irq busy CPU X and
remaining 7 tasks are spread around among other 3 CPUs.

Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-8-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 30 insertions, 1 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 9e01b7100ef6..bff9ef537df0 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -519,6 +519,10 @@ struct rq {
         u64 avg_idle;
 #endif
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+        u64 prev_irq_time;
+#endif
+
         /* calc_load related fields */
         unsigned long calc_load_update;
         long calc_load_active;
@@ -643,6 +647,7 @@ static inline struct task_group *task_group(struct task_struct *p)
 #endif /* CONFIG_CGROUP_SCHED */
 
 static u64 irq_time_cpu(int cpu);
+static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time);
 
 inline void update_rq_clock(struct rq *rq)
 {
@@ -654,6 +659,8 @@ inline void update_rq_clock(struct rq *rq)
                 irq_time = irq_time_cpu(cpu);
                 if (rq->clock - irq_time > rq->clock_task)
                         rq->clock_task = rq->clock - irq_time;
+
+                sched_irq_time_avg_update(rq, irq_time);
         }
 }
 
@@ -1985,6 +1992,15 @@ void account_system_vtime(struct task_struct *curr)
         local_irq_restore(flags);
 }
 
+static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time)
+{
+        if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) {
+                u64 delta_irq = curr_irq_time - rq->prev_irq_time;
+                rq->prev_irq_time = curr_irq_time;
+                sched_rt_avg_update(rq, delta_irq);
+        }
+}
+
 #else
 
 static u64 irq_time_cpu(int cpu)
@@ -1992,6 +2008,8 @@ static u64 irq_time_cpu(int cpu)
         return 0;
 }
 
+static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { }
+
 #endif
 
 #include "sched_idletask.c"
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index c358d4081b81..74cccfae87a8 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2275,7 +2275,13 @@ unsigned long scale_rt_power(int cpu)
         u64 total, available;
 
         total = sched_avg_period() + (rq->clock - rq->age_stamp);
-        available = total - rq->rt_avg;
+
+        if (unlikely(total < rq->rt_avg)) {
+                /* Ensures that power won't end up being negative */
+                available = 0;
+        } else {
+                available = total - rq->rt_avg;
+        }
 
         if (unlikely((s64)total < SCHED_LOAD_SCALE))
                 total = SCHED_LOAD_SCALE;
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 83c66e8ad3ee..185f920ec1a2 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -61,3 +61,8 @@ SCHED_FEAT(ASYM_EFF_LOAD, 1)
  * release the lock. Decreases scheduling overhead.
  */
 SCHED_FEAT(OWNER_SPIN, 1)
+
+/*
+ * Decrement CPU power based on irq activity
+ */
+SCHED_FEAT(NONIRQ_POWER, 1)