Most current multiprocessor file systems are designed to use multiple
disks in parallel, using the high aggregate bandwidth to meet the grow
ing I/O requirements of parallel scientific applications, Many multipr
ocessor file systems provide applications with a conventional Unix-lik
e interface, allowing the application to access multiple disks transpa
rently. This interface conceals the parallelism within the file system
, increasing the ease of programmability, but making it difficult or i
mpossible for sophisticated programmers and libraries to use knowledge
about their I/O needs to exploit that parallelism. In addition to pro
viding an insufficient interface, most current multiprocessor file sys
tems are optimized for a different workload than they are being asked
to support. We introduce Galley, a new parallel file system that is in
tended to efficiently support realistic scientific multiprocessor work
loads. We discuss Galley's file structure and application interface, a
s well as the performance advantages offered by that interface.