On 12/6/19 2:16 PM, Joseph Qi wrote:
Tested with the following case: fio -name=parallel_dio_reads_test -filename=/mnt/nvme0n1/testfile \ -direct=1 -iodepth=1 -thread -rw=randrw -ioengine=psync -bs=$bs \ -size=20G -numjobs=8 -runtime=600 -group_reporting The performance result is the same as reverting parallel dio reads[1] or even slightly better in both bandwidth and latency, which is as
That's great!!
expected. So, Tested-by: Joseph Qi <joseph.qi@xxxxxxxxxxxxxxxxx>
Thanks :) -ritesh
