Data distribution for failure correlation management in a Peer to Peer Storage
Abstract: This article presents a dynamic algorithm for data storage in a P2P storage system, named Us. In Us, peers are arranged in groups called meta-peers to take into account failure correlation. When a peer fails, a reconstruction process rebuilds lost data with help from others peers. To minimize end user traffic because of the reconstruction process, distribution must take into account a new measure: the maximum disturbance cost of a peer during the reconstruction process. The disturbance cost is indicated by the number of data communications which are requested from a single peer for rebuilding lost data. The main goal of this article is to define algorithm, that takes into account failure correlation, able to dilute dynamically the reconstruction process in the system.