Comparing Atomic Broadcast Algorithms in High Latency Networks

Since the introduction of the concept of failure detectors, several consensus and atomic broadcast algorithms based on these detectors have been published. The performance of these algorithms is often aected by a trade-o between the number of communication steps and the number of messages needed to reach a decision. Some algorithms reach decisions in few communication steps but require more messages to do so. Others save messages at the expense of an additional communication step to diuse the decision to all processes in the system. This trade-o is heavily influenced by the network latency and the message processing times and therefore yields fundamentally dierent results in wide and local area networks. Performance evaluations of these algorithms, both in simulated or in real environments, have been published. These evaluations often consider a symmetrical setup : all processes are on the same network and have identical peer-to-peer latencies. In this paper, we model and evaluate the performance of three consensus and atomic broadcast algorithms using failure detectors in several wide area networks. We specifically focus on the case of a system with three processes, located in two or three dierent locations.