Reliable sender-based one-to-many protocols do not scale well due mainly to implosion caused by excessive rate of feedback packets arriving from receivers. We show that this problem can be circumvented by making the sender poll the receivers at carefully planned timing instants, so that the arrival rate of feedback packets is not large enough to cause implosion. We describe a generic end-to-end protocol which incorporates this polling mechanism together with error and ow control mechanisms, and an architecture that implements it. We analyse the behaviour of our protocol using simulations which indicate that our scheme can be e ective in minimising losses due to implosion, and achieve high throughput with low network cost.
Marinho P. Barcellos, Paul D. Ezhilchelvan