Early-delivery atomic broadcast

Abstract

This paper presents early-delivery atomic broadcast protocols for systems in which processors are subject to arbitrary failures, but have access to a message authentication facility. Informally, atomic broadcast requires that all the non-faulty processors deliver the same set of messages in the same order. Atomic broadcast has no solution in asynchronous systems. If it did, the agreement on message delivery order could be used to contradict the impossibility of fault-tolerant agreement in an asynchronous system. Thus, we only consider synchronous systems. However, we avoid the traditional 'round' model of synchronous computation, as many issues can be hidden in the implicit synchronization of that model. We use time explicitly in our protocols.