Project 28: Distributed Storage Coding Scheme in HDFS-RAID
Contact Information:
Prof. Yuan Luo
Email: yuanluo@sjtu.edu.cn
Project Description and Objectives:
Distributed Storage is widely used in industry. The optimal tradeoff between node storage and repair bandwidth is an important issue for distributed storage systems (DSSs). For realistic DSSs with clusters, while repairing a failed node, downloading more data from intra-cluster nodes than from cross-cluster nodes is effective. Therefore, differentiating the repair bandwidth from intra-cluster and cross-cluster is useful. For cluster DSSs, the tradeoff is considered with special repair assumptions where all alive nodes are used for repairing a failed node. In this project, we investigate the optimal tradeoff for the cluster DSSs under more general storage/repair parameters.
Eligibility Requirements:
Good English communication skills.
Theoretical (Algebra) analysis ability, logical thinking ability, teamwork ability.
Software: Hadoop HDFS.
Interest in Computer Science, Mathematics.
Main Tasks:
MDS code performance analysis.
IO and bandwidth analysis of Hadoop HDFS and RAID.
Program Development.
Website:
Lab: N/A