[tip:sched/core] sched/fair: Disable the task group load_avg update for the root_task_group

[tip-bot for Waiman Long]

Commit-ID:  aa0b7ae06387d40a988ce16a189082dee6e570bc
Gitweb:     http://git.kernel.org/tip/aa0b7ae06387d40a988ce16a189082dee6e570bc
Author:     Waiman Long <Waiman.Long@xxxxxxx>
AuthorDate: Wed, 2 Dec 2015 13:41:50 -0500
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Fri, 4 Dec 2015 10:34:49 +0100

sched/fair: Disable the task group load_avg update for the root_task_group

Currently, the update_tg_load_avg() function attempts to update the
tg's load_avg value whenever the load changes even for root_task_group
where the load_avg value will never be used. This patch will disable
the load_avg update when the given task group is the root_task_group.

Running a Java benchmark with noautogroup and a 4.3 kernel on a
16-socket IvyBridge-EX system, the amount of CPU time (as reported by
perf) consumed by task_tick_fair() which includes update_tg_load_avg()
decreased from 0.71% to 0.22%, a more than 3X reduction. The Max-jOPs
results also increased slightly from 983015 to 986449.

Signed-off-by: Waiman Long <Waiman.Long@xxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Douglas Hatch <doug.hatch@xxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Mike Galbraith <efault@xxxxxx>
Cc: Morten Rasmussen <morten.rasmussen@xxxxxxx>
Cc: Paul Turner <pjt@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Scott J Norton <scott.norton@xxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Yuyang Du <yuyang.du@xxxxxxxxx>
Link: http://lkml.kernel.org/r/1449081710-20185-4-git-send-email-Waiman.Long@xxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 kernel/sched/fair.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4b0e8b8..1093873 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2709,6 +2709,12 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 {
 	long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
 
+	/*
+	 * No need to update load_avg for root_task_group as it is not used.
+	 */
+	if (cfs_rq->tg == &root_task_group)
+		return;
+
 	if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
 		atomic_long_add(delta, &cfs_rq->tg->load_avg);
 		cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/