A Heuristic for Selecting the Cycle Length for FAIRIO

FAIRIO is a cycle-based I/O scheduling algorithm that provides differentiated service to workloads concurrently accessing a consolidated RAID storage system. FAIRIO enforces proportional sharing of I/O service through fair scheduling of disk time. During each cycle of the algorithm, I/O requests are scheduled according to workload weights and disk-time utilization history. There are several parameters in the FAIRIO scheduler that can affect its behavior. One parameter in particular, the length of a scheduling cycle, can affect the scheduler’s ability to react to and compensate for changes in workload access characteristics. Unfortunately, there is no cycle length that is optimal for all workloads and, thus, it must be chosen according to the workload environment. This technical report describes a heuristic that can be used to choose a favorable cycle length that promotes performance differentiation given a priori knowledge of workload access behavior. The heuristic is validated using simulations driven by several real and synthetic workload scenarios that represent a broad range of request types, sizes, and access characteristics. We show that when workload weights properly map to workload requirements, cycle lengths deduced by our heuristic promote differentiated disk-time sharing within 3.9% of perfect proportionality to workload weights.