This paper describes an approach to IP multicast performance measurement on
the National Science Foundation's very-high-speed Backbone Network Service
(vBNS). Using OC-12c ATM attached workstations that act as either multicas
t senders or receivers distributed throughout the VBNS backbone, we create
arbitrary topologies, generate synthetic IP multicast traffic and measure l
oss encountered. We present packet loss results as a function of time and a
s a function of router hop count (distribution tree depth). We analyze the
multicast join latency incurred end consider both raw results and results w
ith the loss due to the initiation of multicast state removed. We then corr
elate these loss measurements to the multicast distribution tree where resu
lts show less correlation than expected. We attribute various factors inclu
ding unbalanced non-binary distribution trees, loss on the receiver links a
nd the individual characteristics of different wide area links as factors a
ffecting the con elation. (C) 2001 Elsevier Science B.V. All rights reserve
d.