With hierarchical grouping we can't just compare task weight to rq weight - we need to scale the weight appropriately. Signed-off-by: Peter Zijlstra --- kernel/sched_fair.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) Index: linux-2.6/kernel/sched_fair.c =================================================================== --- linux-2.6.orig/kernel/sched_fair.c +++ linux-2.6/kernel/sched_fair.c @@ -1071,6 +1071,25 @@ static inline int wake_idle(int cpu, str static const struct sched_class fair_sched_class; +#ifdef CONFIG_FAIR_GROUP_SCHED +static unsigned long task_h_load(struct task_struct *p) +{ + unsigned long h_load = p->se.load.weight; + struct cfs_rq *cfs_rq = cfs_rq_of(&p->se); + + update_h_load(task_cpu(p)); + + h_load = calc_delta_mine(h_load, cfs_rq->h_load, &cfs_rq->load); + + return h_load; +} +#else +static unsigned long task_h_load(struct task_struct *p) +{ + return p->se.load.weight; +} +#endif + static int wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq, struct task_struct *p, int prev_cpu, int this_cpu, int sync, @@ -1091,9 +1110,9 @@ wake_affine(struct rq *rq, struct sched_ * of the current CPU: */ if (sync) - tl -= current->se.load.weight; + tl -= task_h_load(current); - balanced = 100*(tl + p->se.load.weight) <= imbalance*load; + balanced = 100*(tl + task_h_load(p)) <= imbalance*load; /* * If the currently running task will sleep within -- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/