Topology Discovery Research Articles

Large-scale fault isolation

Of the many distributed applications designed for the Internet, the successful ones are those that have paid careful attention to scale and robustness. These applications share several design principles. In this paper, we illustrate the application of these principles to common network monitoring tasks. Specifically, we describe and evaluate 1) a robust distributed topology discovery mechanism and 2) a mechanism for scalable fault isolation in multicast distribution trees. Our mechanisms reveal a different design methodology for network monitoring-one that carefully trades off monitoring fidelity (where necessary) for more graceful degradation in the presence of different kinds of network dynamics.

Direct queries for discovering network resource properties in a distributed environment

The development and performance of network-aware applications depends on the availability of accurate predictions of network resource properties. Obtaining this information directly from the network is a scalable solution that provides the accurate performance predictions and topology information needed for planning and adapting application behavior across a variety of networks. The performance predictions obtained directly from the network are as accurate as application-level benchmarks, but the network-based technique provides the added advantages of scalability and topology discovery. We describe how to determine network properties directly from the network using SNMP. We provide an overview of SNMP and describe the features it provides that make it possible to extract both available bandwidth and network topology information from network devices. The available bandwidth predictions based on network queries using SNMP are compared with traditional predictions based on application history to demonstrate that they are equally useful. To demonstrate the feasibility of topology discovery, we present results for a large Ethernet LAN.

IP-centric control and management of optical transport networks

Previous techniques for the management and control of optical transport networks are proving inadequate in today's rapidly evolving multivendor environments. This article examines the issues and challenges involved in developing a standardized optical network control plane. The control of optical transport networks is decomposed into provisioning models, a circuit provisioning process based on signaling, a neighbor and service discovery process, and a topology and resource discovery process. Unique properties and challenges of optical transport networks are explained in the context of these functions.

An improved topology discovery algorithm for networks with wormhole routing and directed links

We propose a new parallel topology discovery algorithm for irregular, mesh-connected networks with unidirectional links and wormhole routing. An algorithm of this type was developed for the ATOMIC high speed local area network to avoid the need for manually updating routing tables. Similar needs may arise in wireless networks where channels may be unidirectional because of limited transmission power, multipath, and similar effects. Like the ATOMIC topology discovery algorithm, our algorithm accumulates a map of the network at a distinguished node called the Address Consultant. However, our algorithm is much faster. In addition, our algorithm is more general, because it can correctly resolve topologies that contain multiple links between the same nodes. We implemented both algorithms in a concurrent simulation environment, and tested them on a variety of topologies.

A management architecture based on network topology information

This paper describes the development of a formalism to represent Network Topology Information that provides hierarchical views of the network elements distribution, usable with advantage by management applications. It reviews some topology discovery tools and emphasizes the lack of a common methodology to represent the network cabling and organize the agent distribution information. The formalism, consisting on a descriptive language and on an object-oriented topology base, is described and some application areas, where this information can be used, are pointed. Finally it presents a Management API, as part of the overall architecture, that helps to show the usability of the Topology Information Base.