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 bf87192e97fe24bd6b1d3d0d1bff4ff7da8e950d..3656480e0f792c3274ff6d9e872fce7240a4142f 100644 (file)
--- 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;
                }
@@ -2447,11 +2450,10 @@ 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 =
-               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);
 }