Since for max_load and this_load, they are the value that already be
scaled. It is not reasonble to get a minimum value between the scaled
and non-scaled value, like below example.
min(sds->busiest_load_per_task, sds->max_load);
Also add comment over in what condition, there would be cpu power gain
in move the load.
Signed-off-by: Lei Wen <lei...@marvell.com>
---
kernel/sched/fair.c | 38 +++++++++++++++++++++++++-------------
1 file changed, 25 insertions(+), 13 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 28052fa..6173095 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4692,10 +4692,14 @@ void fix_small_imbalance(struct lb_env *env, struct
sd_lb_stats *sds)
{
unsigned long tmp, pwr_now = 0, pwr_move = 0;
unsigned int imbn = 2;
- unsigned long scaled_busy_load_per_task;
if (sds->this_nr_running) {
sds->this_load_per_task /= sds->this_nr_running;
+
+ /* Scale this_load_per_task to local power not related */
+ sds->this_load_per_task <<= SCHED_POWER_SHIFT;
+ sds->this_load_per_task /= sds->this->sgp->power;
+
if (sds->busiest_load_per_task >
sds->this_load_per_task)
imbn = 1;
@@ -4704,12 +4708,8 @@ void fix_small_imbalance(struct lb_env *env, struct
sd_lb_stats *sds)
cpu_avg_load_per_task(env->dst_cpu);
}
- scaled_busy_load_per_task = sds->busiest_load_per_task
- * SCHED_POWER_SCALE;
- scaled_busy_load_per_task /= sds->busiest->sgp->power;
-
- if (sds->max_load - sds->this_load + scaled_busy_load_per_task >=
- (scaled_busy_load_per_task * imbn)) {
+ if (sds->max_load - sds->this_load + sds->busiest_load_per_task >=
+ (sds->busiest_load_per_task * imbn)) {
env->imbalance = sds->busiest_load_per_task;
return;
}
@@ -4727,22 +4727,29 @@ void fix_small_imbalance(struct lb_env *env, struct
sd_lb_stats *sds)
pwr_now /= SCHED_POWER_SCALE;
/* Amount of load we'd subtract */
- if (sds->max_load > scaled_busy_load_per_task) {
+ if (sds->max_load > sds->busiest_load_per_task) {
pwr_move += sds->busiest->sgp->power *
min(sds->busiest_load_per_task,
- sds->max_load - scaled_busy_load_per_task);
- tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) /
- sds->this->sgp->power;
+ sds->max_load - sds->busiest_load_per_task);
+ tmp = sds->busiest_load_per_task;
} else
- tmp = (sds->max_load * sds->busiest->sgp->power) /
- sds->this->sgp->power;
+ tmp = sds->max_load;
+ /* Scale to this queue from busiest queue */
+ tmp = (tmp * sds->busiest->sgp->power) /
+ sds->this->sgp->power;
/* Amount of load we'd add */
pwr_move += sds->this->sgp->power *
min(sds->this_load_per_task, sds->this_load + tmp);
pwr_move /= SCHED_POWER_SCALE;
/* Move if we gain throughput */
+ /*
+ * The only possibilty for below statement be true, is:
+ * sds->max_load is larger than sds->busiest_load_per_task, while,
+ * sds->busiest_load_per_task is larger than sds->this_load plus by
+ * the scaled sds->busiest_load_per_task moved into this queue
+ */
if (pwr_move > pwr_now)
env->imbalance = sds->busiest_load_per_task;
}
@@ -4758,6 +4765,11 @@ static inline void calculate_imbalance(struct lb_env
*env, struct sd_lb_stats *s
unsigned long max_pull, load_above_capacity = ~0UL;
sds->busiest_load_per_task /= sds->busiest_nr_running;
+
+ /* Scale busiest_load_per_task to local power not related */
+ sds->busiest_load_per_task <<= SCHED_POWER_SHIFT;
+ sds->busiest_load_per_task /= sds->busiest->sgp->power;
+
if (sds->group_imb) {
sds->busiest_load_per_task =
min(sds->busiest_load_per_task, sds->avg_load);
--
1.7.10.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
