Performance study of NFS over Myrinet-based clusters for parallel multimedia applications

The Network File System (NFS) is an open standard that implements a client/server architecture enabling file sharing over heterogeneous computer systems from PCs to mainframes. NFS is currently being upgraded to better meet the performance and reliability requirements of a large variety of applications, ranging from database queries in a LAN cluster to multimedia applications via the Internet. The main objective of our work is to analyze the performance of NFS as the file system support for parallel image processing applications. We undertake the performance study of NFS over a parallel-processing platform used to accelerate the compression process of digital video. The experimental platform consists of eight nodes connected by a high-speed network (Myrinet). We use NFS to allow a set of processors to gain access to the uncompressed video sequences stored in the NFS-based file server. We have carried out a first set of experiments to evaluate the performance of NFS in terms of I/O response time. Our first results have shown the existence of communication bottlenecks and scalability problems in the system. We have identified some critical system parameters and analyzed their impact over the overall system response time. In a second set of experiments, we explored the performance of the system by changing the cluster topology.