STABILITY, AVAILABILITY, AND RESPONSE IN NETWORK FILE SERVICE

Engineering computing environments require file systems capable of supporting applications dependent on realtime processing, where it is crucial for the file system to be responsive, for data to be immediately available, and for the file system to exhibit stable behaviors. This paper describes a network file system called MULTIFILE, meeting response, availability, and stability requirements as primitive functions. MULTIFILE has a high degree of responsiveness because its component parts compete among themselves to service file requests, it has high availability because it maintains multiple copies of files, and it exhibits stable behaviors over a wide range of system parameters. The responsiveness of MULTIFILE to read requests is observed to improve as the number of pages per request rises, implying that read ahead pages can profitably be cached at client sites. The throughput of MULTIFILE improves as the request size increases, and as the number of clients increases. As server load increases the responsiveness of MULTIFILE to read requests is stable in most configurations, provided there is more than one file replicate responding and provided read requests encompass more than one page. The throughput of writes is unstable as the number of pages in the write request rises, implying that write back pages should not be cached at client sites. The scale of events in file service is dominated by disk activity, so lost message exceptions do not occur frequently enough to affect file service, however duplicate message exceptions are a factor in performance.