Distributed File System: Efficiency Experiments for Data Access and Communication

In a distributed file system, operations such as read, write, send and receive should be efficient and must increase the overall performance of the system. Especially every remote read and write operation we encounter network and secondary storage latencies. In order to reduce this latency time and improve the performance of distributed file system, we analyze the problem of selecting application-level buffer size for the network communication and disk input/output operations. A number of experiments were carried out to identify the optimal size for our application-level buffer.