The Dispatch Time Aligning I/O Scheduling for Parallel File Systems

TitleThe Dispatch Time Aligning I/O Scheduling for Parallel File Systems
Publication TypeJournal Article
Year of Publication2015
AuthorsLiu, Y, Qin, J, Figueiredo, R
JournalCluster Computing
Keywordsearliest deadline first, I/O scheduling, parallel file system, workload imbalance
AbstractIn Parallel File Systems (PFS’s), a data file I/O request may be divided into multiple I/O sub-requests across the storage system. The latency of the original I/O request depends on the finish time of the last sub-request. Due to application multiplexing and various file data layouts employed by the PFS’s, data servers may have very different workloads. Thus, the performance penalty caused by the finish time of different sub-requests can be significant. The Dispatch Time Aligning (DTA) I/O scheduling algorithm focuses on improving system performance by prioritizing lagged sub-requests in PFS I/O requests. The DTA algorithm associates sub-requests from the same I/O request, de- tects and prioritizes the lagged-behind sub-requests. The dual-queue scheduling scheme in DTA provides I/O request latency control while promoting system throughput. Simulation results show that the DTA algorithm can provide up to 83% higher total system throughput than EDF, while offering similar latency guarantees.