diff options
| -rw-r--r-- | kernel/sched/fair.c | 38 |
1 files changed, 22 insertions, 16 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1b56d63c5322..047fd1c78a94 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4862,33 +4862,39 @@ next: done: return target; } + /* * cpu_util returns the amount of capacity of a CPU that is used by CFS * tasks. The unit of the return value must be the one of capacity so we can * compare the utilization with the capacity of the CPU that is available for * CFS task (ie cpu_capacity). - * cfs.avg.util_avg is the sum of running time of runnable tasks on a - * CPU. It represents the amount of utilization of a CPU in the range - * [0..SCHED_LOAD_SCALE]. The utilization of a CPU can't be higher than the - * full capacity of the CPU because it's about the running time on this CPU. - * Nevertheless, cfs.avg.util_avg can be higher than SCHED_LOAD_SCALE - * because of unfortunate rounding in util_avg or just - * after migrating tasks until the average stabilizes with the new running - * time. So we need to check that the utilization stays into the range - * [0..cpu_capacity_orig] and cap if necessary. - * Without capping the utilization, a group could be seen as overloaded (CPU0 - * utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of - * available capacity. + * + * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the + * recent utilization of currently non-runnable tasks on a CPU. It represents + * the amount of utilization of a CPU in the range [0..capacity_orig] where + * capacity_orig is the cpu_capacity available at the highest frequency + * (arch_scale_freq_capacity()). + * The utilization of a CPU converges towards a sum equal to or less than the + * current capacity (capacity_curr <= capacity_orig) of the CPU because it is + * the running time on this CPU scaled by capacity_curr. + * + * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even + * higher than capacity_orig because of unfortunate rounding in + * cfs.avg.util_avg or just after migrating tasks and new task wakeups until + * the average stabilizes with the new running time. We need to check that the + * utilization stays within the range of [0..capacity_orig] and cap it if + * necessary. Without utilization capping, a group could be seen as overloaded + * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of + * available capacity. We allow utilization to overshoot capacity_curr (but not + * capacity_orig) as it useful for predicting the capacity required after task + * migrations (scheduler-driven DVFS). */ static int cpu_util(int cpu) { unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg; unsigned long capacity = capacity_orig_of(cpu); - if (util >= SCHED_LOAD_SCALE) - return capacity; - - return (util * capacity) >> SCHED_LOAD_SHIFT; + return (util >= capacity) ? capacity : util; } /* |