The Need of Multicast Predictive NFS Servers for High-Speed Networks Used as Parallel Multimedia Platforms

In this paper we have carried out an experimental study of the I/O latency of a distributed file system over a parallel multimedia platform. Our experimental platform uses NFS (Network File System) to support an application characterized by its high processing and storage requirements. We evaluate the overall system by varying several NFS parameters as well as the underlying network topology and data access patterns. We have also examined the relevance of two other important file management access mechanisms: caching and prefetching. Our experimental results have allowed us to identify the major system parameters affecting the performance of NFS. We then propose the use of a predictive data access mechanisms. Under this mechanism, the file server should detect the similarities among the most recent I/O requests incoming from a set of cooperating clients. Once having identified the access pattern, the file server will be able to multicast the required data even before receiving explicit I/O data requests from the clients. Under this predictive mechanism, the system performance should improve as the number of explicit I/O requests directed to the file server decreases.