[patch 1/3] sched: init rt_avg stat whenever rq comes online

[Suresh Siddha]

TSC's get reset after suspend/resume and this leads to a scenario of
rq->clock (sched_clock_cpu()) less than rq->age_stamp. This leads
to a big value returned by scale_rt_power() and the resulting big group
power set by the update_group_power() is causing improper load balancing
between busy and idle cpu's after suspend/resume.

This resulted in multi-threaded workloads (like kernel-compilation) go slower
after suspend/resume cycle on core i5 laptops.

Realign rq->age_stamp to rq->clock and reset rq->rt_avg in rq_online_rt().

Addresses the primary issue reported in the
https://bugzilla.kernel.org/show_bug.cgi?id=15559
(Bad performance after suspend on Intel i7 and i5)

Reported-by: Florian Pritz <flo@xxxxxxx>
Signed-off-by: Suresh Siddha <suresh.b.siddha@xxxxxxxxx>
Cc: stable@xxxxxxxxxx	[2.6.32+]
---

diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index d10c80e..a00af73 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1550,6 +1550,12 @@ static void rq_online_rt(struct rq *rq)
 	__enable_runtime(rq);
 
 	cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
+
+	/*
+ 	 * Reset RT average stat and its time stamp.
+ 	 */
+	rq->age_stamp = rq->clock;
+	rq->rt_avg = 0;
 }
 
 /* Assumes rq->lock is held */


--
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/