On 07/26/2012 04:17 PM, Peter Zijlstra wrote: > On Thu, 2012-07-26 at 13:27 +0800, Alex Shi wrote: >> If find_idlest_cpu() return '-1', and sd->child is NULL. The function >> select_task_rq_fair will return -1. That is not the function's purpose. > > But find_idlest_cpu() will only return -1 if the group mask is fully > excluded by the cpus_allowed mask, right?
Yes. > > In that case aren't we covering up a bug in find_idlest_group(), it > appears to have returned a group that isn't eligible to be idlest. If it is possible happening in sched_domain rebuilding? I didn't meet this bug. Just guess. > > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/