Explanation: The queue length is the number of pending I/O requests for a device. The optimal average queue length will vary for every customer workload, and this value depends on a particular application’s sensitivity to IOPS and latency. If the workload is not delivering enough I/O requests to maintain the optimal average queue length, then the EBS volume might not consistently deliver the IOPS that have been provisioned. However, if the workload maintains an average queue length that is higher than the optimal value, then the per-request I/O latency will increase; in this case, the user should provision more IOPS for his volume. AWS recommends that the user should target an optimal average queue length of 1 for every 200 provisioned IOPS and tune that value based on his application requirements.
Reference:
http://docs.aws.amazon.com/AWSEC2/latest/UserGuide/ebs-workload-dem…