| Y. Huang, E. Fleury, and P. McKinley. LCM: A multicast core management protocol for link-state routing networks. IEEE International Conference on Communications, 2:1197--1201, June 1998. |
....a shared multicast distribution tree per multicast group. As all the routers connect to the core, the protocol may lead to traffic concentration and a performance bottleneck around the core router. Several core management approaches, e.g. core selection, core failure handling, and core migration [FlH98, HuF98], have been proposed to avoid these problems. Another solution to avoid the performance bottleneck is to use multiple cores. Unfortunately, when multi core architecture is used, the CBT protocol can form loops and thus fail to build a connected multicast tree, even when the underlying routing is ....
Y. Huang, E. Fleury, and P. K. McKinley, "LCM: A Multicast Core Management Protocol for Link-State Routing Networks," Proceedings of the IEEE International Conference on Communications (ICC), Atlanta, Georgia, U.S.A., June 1998.
....all active groups are explicitly stored in the network, for example, at a pre con gured core management server. This approach enables the use of almost any core selection heuristic, at the price of imposing management storage burden on the network. An example of such an approach is described in [13]. 3 Multicast Tree Performance Metrics In order to evaluate the performance of a core selection method, and therefore that of the resultant multicast trees, we consider several di erent metrics. The relative importance of a given metric depends on the type of application using the multicast ....
Y. Huang, E. Fleury, and P. K. McKinley, \LCM: A multicast core management protocol for link-state routing networks," in Proceedings of the
....applications discussed earlier, the mutual consensus property of the NLE protocol enables arbitrary multicast groups to handle network partitions and re unifications. The maintenance of the leader binding of every active group at every switch in a network may raise the concern of scalability. In [13], we describe another coremanagement method that addresses this issue by using the NLE protocol to select a central server to maintain the leader bindings of all active groups. The method presented above, however, has an advantage in groupjoin time, because joining switches do not have to query a ....
Y. Huang and P. K. McKinley, "LCM: A multicast core management protocol for link-state routing networks, " Tech. Rep. MSU-CPS-97-30, Department of Computer Science, Michigan State University, East Lansing, Michigan, August 1997.
No context found.
Y. Huang, E. Fleury, and P. McKinley. LCM: A multicast core management protocol for link-state routing networks. IEEE International Conference on Communications, 2:1197--1201, June 1998.
No context found.
Y. Huang, E. Fleury, and P.K. McKinley. Lcm: A multicast core management protocol for link-state routing networks. IEEE International Conference on Communications, 2:1197--1201, June 1998.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC