Integrating Mass Storage and File Systems

Abstract

This paper describes current and anticipated work at the University of Michigan's Center for Information Technology Integration (CITI) in developing and integrating mass storage with distributed file systems, specifically with the Andrew File System (AFS). After surveying existing mass storage and associated file systems, this paper presents one approach to integrating AFS with mass storage. We consider the mass store itself to be the file system, not a bag on the side of a disk-based file system. This unifying perspective distinguishes our approach from other large-scale file systems. Instead of developing a back-end server to manage the movement of data files between traditional disk-based storage systems (employed, in our case, by AFS) and magnetic-tape or optical-based mass storage systems (of which AFS has little or no knowledge), we envision the mass store as a first-class data repository. A traditional disk-based file system serves as a (very large) cache of the mass store system. On top of that is another, large, high-speed memory cache. All storage other than the mass store is used exclusively for caching. In this approach, cache management policies are of fundamental importance. Two main requirements for this work are that the AFS name space remain unchanged, and performance seen by users must not suffer. For example, users must not have to pre-stage files explicitly in order to achieve acceptable performance.