Implementation and Analysis of the File System Based on Metadata Dynamic Hashing
Metadata management algorithm plays an important role in file system performance and file system is the most common way of data accessing in mass storage systems, so metadata management algorithm is very important for the performance of mass storage system. In this paper we analyze current metadata management algorithms and bring in the metadata dynamic hashing algorithm to solve the problem of poor adaptability of them. We realize the prototype on Lustre. After testing system performance with common tools by adjusting the several parameters’ value of metadata dynamic hashing algorithm, we find that performance of the prototype I/O is superior to Lustre. Furthermore, we analyze impacts of the parameters of dynamic hashing function on I/O performance of prototype