Active reliable multicast

This paper presents a novel loss recovery scheme, active reliable multicast (ARM), for large scale reliable multicast. ARM is "active" in that routers in the multicast tree play an active role in loss recovery. Additionally, ARM utilizes soft-state storage within the network to improve performance and scalability. In the upstream direction, routers suppress duplicate NACKs from multiple receivers to control the implosion problem. By suppressing duplicate NACKs, ARM also lessens the traffic that propagates back through the network, In the downstream direction, routers limit the delivery of repair packets to receivers experiencing loss, thereby reducing network bandwidth consumption. Finally, to reduce wide-area recovery latency and to distribute the retransmission load, routers cache multicast data on a "best effort" basis. ARM is flexible and robust in that it does not require all nodes to be active, nor does it require any specific router or receiver to perform loss recovery. Analysis and simulation results show that ARM yields significant benefits even when less than half the routers within the multicast tree can perform ARM processing.