An efficient algorithm for group communication

We present an algorithm for reliable group communication that guarantees atomicity and total ordering in message delivery. The algorithm has been designed to operate with general omission failures on top of any datagram subnetwork. It allows one to operate within large groups of processes without loss of efficiency and is suitable for an easy implementation. Processes decide in at most 2fk + 2 protocol rounds after sending O(fkn) messages, where fk is the amount of time required t detect f consecutive coordinator failures, and n is the group cardinality. This paper provides the correctness analysis of the algorithm and discusses the performance of our initial implementation.<
>