On 01/02/2021 02:30, Guoqing Jiang wrote: > If user doesn't care about the size and latency of io, and they could > suffer from the additional overhead. So introduce a specific sysfs node > to avoid such mistake. I would make this patch number 1 in the series and then merge patch 4 (the check for blk_queue_io_extra_stat()) into the patches adding blk_additional_latency() and blk_additional_sector().