sched: Set group_imb only a task can be pulled from the busiest cpu
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@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286996978-7007-3-git-send-email-ncrao@google.com>
[ small code readability edits ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index bf87192e..3656480 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2378,7 +2378,7 @@
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 @@
/* 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 @@
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;
}
@@ -2447,11 +2450,10 @@
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 =
- DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
+ sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
if (!sgs->group_capacity)
sgs->group_capacity = fix_small_capacity(sd, group);
}