A Scalable Architecture for Monitoring and Visualizing Multicast Statistics

Prashant Rajvaidya, Kevin C. Almeroth   k Claffy
Department of Computer Science          CAIDA 
University of California                University of California
Santa Barbara, CA 93106-5110            San Diego, CA 9209
{prash,almeroth}@cs.ucsb.edu            kc@caida.org


An understanding of certain network functions is critical for successful 
network management.  Managers must have insight into network topology, 
protocol performance and fault detection/isolation. The ability to 
obtain such insight is even more critical when trying to support evolving 
technologies.  Multicast is one example of a new network layer technology 
and is the focus of this paper.  For multicast, the pace of change is 
rapid, modifications to routing mechanisms are frequent, and faults are
common. In this paper we describe a tool, called Mantra, we have 
developed to monitor multicast. Mantra collects, analyzes, and visualizes 
network-layer (routing and topology) data about the global multicast 
infrastructure. The two most important functions of Mantra are: (1) 
monitoring multicast networks on a global scale; and (2) presenting 
results in the form of intuitive visualizations. To achieve accurate 
monitoring, Mantra collects data from several topologically and 
geographically diverse networks. For the purpose of presentation, Mantra 
uses several interactive visualization mechanisms to present statistics,
topology maps and geographic properties. Another noteworthy feature of 
Mantra is its flexible and scalable architecture. This architecture helps 
keep our monitoring efforts current with the fast pace of multicast 
developments. It also enables us to expand Mantra's monitoring scope to 
more networks and larger data sets.