On 7/20/18 6:29 PM, Liu Bo wrote:

When an application's iops has exceeded its cgroup's iops limit, surely it
is throttled and kernel will set a timer for dispatching, thus IO latency
includes the delay.

However, the dispatch delay which is calculated by the limit and the
elapsed jiffies is suboptimal.  As the dispatch delay is only calculated
once the application's iops is (iops limit + 1), it doesn't need to wait
any longer than the remaining time of the current slice.

Looks good to me - can you resend against my for-4.19/block branch, as
it doesn't apply.

-- 
Jens Axboe