A Small File Performance Optimization Algorithm on P2P Distributed File System

With the further development of the Internet, the amount of data on the network grows exponentially in recent years. While the fastest increasing objects are the mass small files from blogs, forums, etc. Master/Slave structure distributed file systems have some shortcomings, such as the poor access performance with small files, single-point bottlenecks, etc. Although these problems have been solved in the P2P structure distributed file system to some extent, there is still some improvement room of accessing performance for small files in the P2P structure distributed file system, so a small file merging strategy(SFMS) is proposed in this paper. The throughput rate of reading small files is increased significantly. Experiments show that the throughput rate of reading small files is increased by 90% compared with the original system, and 25 times higher than the TFS which is based on Master/Slave structure.