After poking at them a little more I feel somewhat more confident. I found one more bug, but this one was my own fault, we should also clear sds->busiest_stat.avg_load because update_sd_pick_busiest() reads that before we set it.
Moved the memset optimization and the fix for that into a separate patch. Other than that, there's a sched_domain degenerate fix; and a new way to detect group_imb (which relies on the sched_domain fix). -- 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/