Storage QoS control with adaptive I/O deadline assignment and slack-stealing EDF

Abstract

Storage QoS control enforces a given storage QoS requirement for each I/O request from different storage clients that share an underlying storage system. This paper proposes an efficient storage QoS control scheme that features adaptive I/O deadline assignment and slack-stealing EDF scheduling. Simulation results with various I/O workloads show that the proposed scheme outperforms previous approaches in terms of response time variation, average response times, and miss ratio of the target response time.