Two-side data deduplication mechanism for non-center cloud storage systems

Unnecessarily redundant data wastes lots of storage resource of cloud storage system. In this paper, we focus on the data deduplication for the non-center cloud storage system and propose a novel two-side data deduplication mechanism. First, duplicated data is detected in client side and prevented to be uploaded to cloud data center, and then new-generated duplicated data is detected and deleted in cloud server side. The Chord algorithm is optimized through the compressed finger table and the search optimization of finger table and used to construct the logical network, which makes searching the fingerprint much faster in storage nodes. The experimental results show that the improved Chord algorithm has the better performance than the original one in the number of fingerprint values and the cost of searching time, and the proposed two-side data deduplication mechanism has the higher rate of deduplication than the traditional data deduplication mechanism.