[PATCH 1/3] sched: set group_imb only a task can be pulled from the busiest cpu

From: Nikhil Rao
Date: Mon Sep 27 2010 - 20:30:35 EST


When cycling through sched groups to determine the busiest group, set
group_imb only if the busiest cpu has more than 1 runnable task. This patch
fixes the case where two cpus in a group have one runnable task each, but there
is a large weight differential between these two tasks. The load balancer is
unable to migrate any task from this group, and hence do not consider this
group to be imbalanced.

Signed-off-by: Nikhil Rao <ncrao@xxxxxxxxxx>
---
kernel/sched_fair.c | 10 +++++++---
1 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index a171138..de8a6a0 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2378,7 +2378,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
int local_group, const struct cpumask *cpus,
int *balance, struct sg_lb_stats *sgs)
{
- unsigned long load, max_cpu_load, min_cpu_load;
+ unsigned long load, max_cpu_load, min_cpu_load, max_nr_running;
int i;
unsigned int balance_cpu = -1, first_idle_cpu = 0;
unsigned long avg_load_per_task = 0;
@@ -2389,6 +2389,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
/* Tally up the load of all CPUs in the group */
max_cpu_load = 0;
min_cpu_load = ~0UL;
+ max_nr_running = 0;

for_each_cpu_and(i, sched_group_cpus(group), cpus) {
struct rq *rq = cpu_rq(i);
@@ -2406,8 +2407,10 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
load = target_load(i, load_idx);
} else {
load = source_load(i, load_idx);
- if (load > max_cpu_load)
+ if (load > max_cpu_load) {
max_cpu_load = load;
+ max_nr_running = rq->nr_running;
+ }
if (min_cpu_load > load)
min_cpu_load = load;
}
@@ -2447,7 +2450,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
if (sgs->sum_nr_running)
avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;

- if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
+ if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task &&
+ max_nr_running > 1)
sgs->group_imb = 1;

sgs->group_capacity =
--
1.7.1

--
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/