Abstract

Retransmission based error control for large scale multicast applications is difficult because of two main problems: request implosion and lack of local recovery. Existing schemes (SRM, RMTP, TMTP, LBRRM) have good solutions to request implosion, but only approximate solutions (e.g., based on scoped multicast) for the local recovery problem. Our scheme achieves finer grain fault recovery by exploiting new forwarding services that allow us to create a dynamic hierarchy of receivers. We use a new paradigm, where routers provide a more refined form of multicasting (that may be useful to other applications), that enables local recovery. The new services, however, are simple to implement and do not require routers to examine or store application packets; hence, they do not violate layering. Besides providing good local recovery, our scheme integrates well with the current IP model, has small recovery latencies (it requires no back-off delays), produces fewer duplicates than other schemes, a...

Citations