File System Benchmarks, Then, Now, and Tomorrow

With the growing popularity of storage area networks (SANs) and clustered, shared file systems, the file system is becoming a distinct and critical part of a system environment. Because the file system mitigates access to data on a mass storage subsystem, it has certain behavioral and functional characteristics that affect I/O performance from an application and/or system point of view. Measuring file system performance is significantly more complicated than that of the underlying disk subsystem because of the many types of higher-level operations that can be performed (allocations, deletions, directory searches, ...etc.). The tasks of measuring and characterizing the performance of a file system is further complicated by SANs and emerging clustering technologies that add a distributed aspect to the file systems themselves. Similarly, as the cluster/SAN grows in size, so does the task of performance measurement. The objective of this study is to identify some of the more significant issues involved with file system benchmarking in a highly scalable clustered environment.