[RFC patch v2 2/7] sched: set initial load avg of new forked task

[Alex Shi <alex.shi@intel.com>]

New task has no runnable sum at its first runnable time, so its
runnable load is zero. That makes burst forking balancing just select
few idle cpus to assign tasks if we engage runnable load in balancing.

Set initial load avg of new forked task as its load weight to resolve
this issue.

Signed-off-by: Alex Shi <alex.shi@intel.com>
Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
---
 include/linux/sched.h |  1 +
 kernel/sched/core.c   |  2 +-
 kernel/sched/fair.c   | 11 +++++++++--
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6fc8f45..b8738c0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1069,6 +1069,7 @@ struct sched_domain;
 #else
 #define ENQUEUE_WAKING		0
 #endif
+#define ENQUEUE_NEWTASK		8
 
 #define DEQUEUE_SLEEP		1
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 66c1718..66ce1f1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1705,7 +1705,7 @@ void wake_up_new_task(struct task_struct *p)
 #endif
 
 	rq = __task_rq_lock(p);
-	activate_task(rq, p, 0);
+	activate_task(rq, p, ENQUEUE_NEWTASK);
 	p->on_rq = 1;
 	trace_sched_wakeup_new(p, true);
 	check_preempt_curr(rq, p, WF_FORK);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5eea870..1384297 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1503,8 +1503,9 @@ static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 /* Add the load generated by se into cfs_rq's child load-average */
 static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 						  struct sched_entity *se,
-						  int wakeup)
+						  int flags)
 {
+	int wakeup = flags & ENQUEUE_WAKEUP;
 	/*
 	 * We track migrations using entity decay_count <= 0, on a wake-up
 	 * migration we use a negative decay count to track the remote decays
@@ -1538,6 +1539,12 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 		update_entity_load_avg(se, 0);
 	}
 
+	/*
+	 * set the initial load avg of new task same as its load
+	 * in order to avoid brust fork make few cpu too heavier
+	 */
+	if (flags & ENQUEUE_NEWTASK)
+		se->avg.load_avg_contrib = se->load.weight;
 	cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
 	/* we force update consideration on load-balancer moves */
 	update_cfs_rq_blocked_load(cfs_rq, !wakeup);
@@ -1701,7 +1708,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
-	enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP);
+	enqueue_entity_load_avg(cfs_rq, se, flags);
 	account_entity_enqueue(cfs_rq, se);
 	update_cfs_shares(cfs_rq);
 
-- 
1.7.12