Cost-effective replica management in fault-tolerant cloud environments

Cloud providers rely on fault-tolerance mechanisms to realize high-availability services on best-effort infrastructure. Service replication limits the data-loss caused by failure, at the expense of additional operational costs. Recently, with the advent of Mobile Edge Computing, cloud environments are becoming increasingly heterogeneous and dynamic, by the incorporation of (very) unreliable and resource-constrained devices. In this paper, we investigate how to devise an economically viable replication strategy, for a given service on a particular cloud environment. Previous work either focused on finding replication strategies for stateless services, ignoring recovery processes and correlated failures, or considered system dynamics, while lacking Service Level Agreement (SLA)-awareness. We approach the replica management problem as a run-time revenue maximization problem. Our proposed Dynamic Programming (DP) algorithm can generate the optimal replication strategy over the application lifetime. Through extensive simulations, we show that our algorithm significantly improves provider revenue over a wide range of cloud- and SLA-conditions, and adapt its strategy to evolving operating conditions. The results show that coupling dynamic failure models with SLA-awareness can lead to profitable replication strategies, even in cases where providers currently turn a loss.