DataCube: a P2P persistent Storage Architecture based on Hybrid Redundancy Schema

This paper presents the design of DataCube, a P2P data persistent platform. This platform exploits the properties of cluster-based peer-to-peer structured overlays altogether with a hybrid redundancy schema (a compound of light replication and rateless erasure coding) to guarantee durable access and integrity of data despite adversarial attacks. In particular, the recovery of damaged data is achieved through the retrieval of the minimum number of coded blocks: coded blocks are selectively retrieved and their integrity is checked on the y. An analysis validates DataCube principles design. Specically, the triptych "availability - storage overhead - bandwidth usage" is evaluated, and results show that despite massive attacks and high churn, DataCube performs remarkably well