Reliable Multicast for Publish/Subscribe Systems

Group-based reliable multicast is an important building block for distributed applications. For large systems, however, traditional approaches do not scale well due to centralized recovery mechanisms and excessive message overhead. In this paper, we present a reliable probabilistic multicast, rpbcast, that is a hybrid of the centralized and gossip-based approaches. In particular, rpbcast extends previous work by supporting high packet rates and many active senders. Rpbcast uses gossip as the primary retransmission mechanism and only contacts loggers if gossips fail. Large groups of active senders are supported using negative gossip which describes what a receiver lacks instead of what it has. Moreover, negative gossip allows pull based recovery and converges faster than push based recovery. Rpbcast also applies hashing techniques to reduce message overhead. Garbage collection in rpbcast is stability oriented. The approximate membership protocol in rpbcast exploits some garbage collection flexibilities to avoid expensive join/leave operations. Thesis Supervisor: Nancy Lynch Title: Professor Massachusetts Institute of Technology