Abstract: After doing research on Google File System, we find out some methods to improve the performance of Google file system. Google File System is a scalable distributed file system for large size distributed data-intensive applications. It provides high fault tolerance while running on inexpensive commodity hardware and it delivers high aggregate performance to a large number of clients. But there are some limitations in it such as it uses same chunk size to append and write data. Fixed chunk size decreases its performance for append data. So we will explain some methods to increase its performance by changing some attributes of typical Google File System. This paper is divided into five parts. First part presents the basic introduction of Google File System, second part provides the performance of GFS cluster for a 64 MB chunk size, third part shows the performance of real time GFS clusters, fourth part presents a method to increase the performance of GFS, and finally part fifth concludes the effect of variable size chunk on GFS.
Keywords: Availability, chunk, performance, reliability, scalability