Data replication in p2p environments
André Brinkmann, Sascha Effert · 2008
Current p2p environments are often based on Consistent Hashing as underlying distributed hash table (DHT). The drawback of Consistent Hashing for small or mid-sized environments is that it is not able to efficiently use the available storage capacity, if the environment consists of heterogeneous peers. Inside this paper, we investigate the Redundant Share strategy and introduce the peer-Replication strategy, which are able to ensure an optimal capacity efficiency, even in case of data replication. While Redundant Share is not always able to retrieve all copies inside the view of a client, peer-Replication achieves this property by introducing a small number of additional communication rounds. The trade-off between the proposed peer-Replication strategy and Consistent Hashing is the number of required communication rounds vs. the quality of the data distribution. Inside this paper we show that a very small number of additional communication rounds enables us to significantly increase the capacity efficiency.