This paper presents the design, implementation and performance of a reliable multicast transport protocol called RMTP. RMTP is based on a hierarchical structure in which receivers are grouped into local regions or domains and in each domain there is a special receiver called a Designated Receiver (DR) which is responsible for sending acknowledgments periodically to the sender, for processing acknowledgements from receivers in its domain and for retransmitting lost packets to the corresponding receivers. Since lost packets are recovered by local retransmissions as opposed to retransmissions from the original sender, end-to-end latency is significantly reduced, and the overall throughput is improved as well. Also, since only the DRs send their acknowledgments to the sender, instead of all receivers sending their acknowledgments to the sender, a single acknowledgement is generated per local region, and this prevents acknowledgement implosion. Receivers in RMTP send their acknowledgments to the DRs periodically, thereby simplifying error recovery. In addition, lost packets are recovered by selective repeat retransmissions, leading to improved throughput at the cost of minimal additional buffering at the receivers. This paper also describes the implementation of RMTP and its performance on the Internet.

Traditional broadcast protocols are inappropriate for the high-speed networks of the future. Such protocols are limited by the speed of software pro-cessing, which becomes a bottleneck as network speeds increase. This paper presents a broadcast protocol that is appropriate for high-speed net-works, and is tolerant of failures involving the loss of messages. The protocol is based primarily on the simple hardware functions present in a high-speed net-work node. This leads to message delivery at hardware speeds. In the unlikely event of a fail-ure, some software intervention may be required to guarantee the timely termination of the pro-tocol. However this software processing does not interfere with message delivery. We show that in the likely cases, the protocol guarantees message delivery within D ~ time, where D is the diameter of the network, and ~ is the maximum link delay.