Reducing Storage for Quorum Consensus Algorithms

Abetrae t In this paper, we first develop a fragmentation method that reduces the storage overhead of replicated objects. We then present a data management protocol for these fragmented objects, and show that this protocol is a generalisation of quorum consensus algorithms for replicated data in which objects are not fragmented. Although this protocol reduces storage requirements, it does not achieve the same level of resiliency for both read and write operations. By integating a log-based propagation mechanism with our protocol, we are able to achieve the same level of resiliency for both read and write operations as other quorum consensus protocob, while reducing the storage cost.