Distributed Snapshot for Rollback-Recovery with One-Sided Communications

Traditional interprocess communication requires cooperation and synchronization between sender and receiver. The One-sided communication model is a new way and very promising model: processes can directly read or write in the memory of another process. In such a model, fault tolerance is a challenging problem. In this paper, we present algorithms to be able to do rollback-recovery based on global snapshot in a distributed system with one-sided communications.