An Evaluation of Shared Multicast Trees with Multiple Active Cores
Lecture Notes in Computer Science
Native multicast routing protocols have been built and deployed using two basic types of trees: singlesource, shortest-path trees and shared, core-based trees. Core-based multicast trees use less routing state compared to shortest-path trees, but generally have higher end-to-end delay and poor fault tolerance. In this paper we consider a new type of shared multicast structure that uses multiple, independent, simultaneously-active cores. Our design provides for low end-to-end delay, improved
... t tolerance, and low source discovery delay, while balancing bandwidth cost and routing state. These results indicate that shared trees with multiple active cores are a viable alternative to shortest-path trees. * This work was supported in part by the National Science Foundation under grants ANI-9977524 and NCR-9714680.  uses a hierarchy of cores, in which cores at lower levels join to their parent in the higher level, forming a star. OCBT's use of multiple cores helps to avoid looping problems that were present in initial designs of CBT. However, because each of the cores cooperate to form a single tree, this structure does not behave any differently than a single-core tree with respect to performance metrics such as delay, routing state, and fault tolerance. In this paper we demonstrate the promise of building shared multicast trees with multiple, simultaneouslyactive, independent cores. Each core is the center of a separate multicast tree, and there is no coordination or dependencies among cores. This design improves the fault tolerance of the shared trees and can significantly improve performance. Our results show that using multiple cores can reduce the average delay experienced by group members, while balancing the bandwidth and routing state used by the tree. We also investigate core placement algorithms and show that placing cores using a dominating set or k-center algorithm can moderately improve delay. Finally, we show that multiple-core trees can generally avoid the problem of traffic concentration, although there are cases where it is a factor. Based on these results, we conclude that shared trees using multiple cores are a significant improvement over single-core trees and thus a viable alternative to shortest-path trees. The rest of the paper is organized as follows. Section 1 describes related work in the areas of tree comparisons, core placement, and the use of multiple cores. Section 2 describes several alternative designs for using multiple cores and explains how a multicast routing protocol using these cores can be built. Section 3 presents the results of an extensive simulation study examining the performance of these designs, and Section 4 outlines our conclusions.