Distributed De-Duplication Storage Systems in Wide Area Networks

The problem of redundancy often occurs in mass data stored in distributed storage systems. Greater efficiency in storage and network bandwidth utilization can be achieved by employing de-duplication techniques to eliminate this problem. This article introduces the design and implementation of redundancy-removal systems in a distributed WAN environment. AegeanStore can eliminate redundancy prior to data being uploaded. This frees up storage space and resource use, and lowers the total cost of storage. Furthermore, disaster recovery features inherent in the distributed system are maintained, storage system scalability is enhanced, and overall performance of the network is improved.