Highly available fault tolerant distributed computing using reflection and replication

Abstract

High availability is a desired feature of a good distributed system. Replication is a well-known technique to achieve fault tolerance in distributed systems, thereby enhancing availability. Distributed computing for partitionable system presents a challenge in that there is a trade-off between availability and consistency. Changes in one partition are not visible in another. Therefore strict consistency is required, which reduces availability. Proposed algorithm uses trade-off between consistency and availability. We have proposed an algorithm using combination of replication and reflection techniques to be applied in distributed system for fault tolerance. Algorithm uses both active and passive strategies to implement optimistic replication protocol. We incorporate reflection technique to achieve roll forward mechanism.