[RFC PATCH 3/4] linsched: avoid invoke "tick_nohz_idle_enter" when cpu in idle

[RFC PATCH 3/4] linsched: avoid invoke "tick_nohz_idle_enter" when cpu in idle

[Michael Wang]

From: Michael Wang <wangyun@linux.vnet.ibm.com>

In real world, "tick_nohz_idle_enter" will be invoked by idle thread 
when the cpu change from active to idle, and will only be invoked
again after "tick_nohz_idle_exit" was invoked by idle thread when
cpu going to recover.

Signed-off-by: Michael Wang <wangyun@linux.vnet.ibm.com>
---
 tools/linsched/hrtimer.c |   11 ++++++++++-
 1 files changed, 10 insertions(+), 1 deletions(-)

diff --git a/tools/linsched/hrtimer.c b/tools/linsched/hrtimer.c
index de88b25..1981bc9 100644
--- a/tools/linsched/hrtimer.c
+++ b/tools/linsched/hrtimer.c
@@ -149,6 +149,15 @@ void linsched_check_idle_cpu(void)
 	}
 }

+void linsched_enter_idle_cpu(void)
+{
+	int cpu = smp_processor_id();
+	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+	if (!ts->inidle && idle_cpu(cpu))
+		tick_nohz_idle_enter();
+}
+
 /* Run a simulation for some number of ticks. Each tick,
  * scheduling and load balancing decisions are made. Obviously, we
  * could create tasks, change priorities, etc., at certain ticks
@@ -210,7 +219,7 @@ void linsched_run_sim(int sim_ticks)

 			BUG_ON(irqs_disabled());
 			if (idle_cpu(active_cpu) && !need_resched()) {
-				tick_nohz_idle_enter();
+				linsched_enter_idle_cpu();
 			} else {
 				linsched_current_handler();
 			}
-- 
1.7.1