When check_asym_packing() is triggered, the imbalance is set to : busiest_stat.avg_load * busiest_stat.group_capacity / SCHED_CAPACITY_SCALE busiest_stat.avg_load also comes from a division and the final rounding can make imbalance slightly lower than the weighted load of the cfs_rq. But this is enough to skip the rq in find_busiest_queue and prevents asym migration to happen.
Add 1 to the avg_load to make sure that the targeted cpu will not be skipped unexpectidly. Signed-off-by: Vincent Guittot <[email protected]> --- kernel/sched/fair.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 309c93f..c376cd0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7780,6 +7780,12 @@ static inline void update_sg_lb_stats(struct lb_env *env, /* Adjust by relative CPU capacity of the group */ sgs->group_capacity = group->sgc->capacity; sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity; + /* + * Prevent division rounding to make the computation of imbalance + * slightly less than original value and to prevent the rq to be then + * selected as busiest queue + */ + sgs->avg_load += 1; if (sgs->sum_nr_running) sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; -- 2.7.4
