Improving the Performance of the Distributed File System through Anticipated Parallel Processing

Abstract

In the emerging Big Data scenario distributed File systems DFSs are used for storing and accessing information in a scalable manner Many cloud computing systems use DFS as the main storage component The Big Data applications de-ployed in cloud computing systems more frequently perform read operations and less frequently the write operations So improving the performance of read access has become an im-portant research issue in DFS In the literature many client side caching with appropriate pre fetching techniques are proposed for improving the performance read access in the DFS A speculation-based approach which uses client side caching is also proposed in the literature for improving the performance of read access in the DFS In this paper we have proposed a new read algorithm for the DFS based on anticipated parallel processing We have evaluated the per- formance of the proposed algorithm using mathematical and simulation methods and the results indicate that the pro-posed algorithm performs better than the speculation-based algorithm proposed in the literature