karp @ eecs.harvard.edu We present Greedy Perimeter Stateless Routing (GPSR), a novel routing protocol for wireless datagram networks that uses the po-sitions of touters and a packer's destination to make packet for-warding decisions. GPSR makes greedy forwarding decisions us-ing only information about a router's immediate neighbors in the network topology. When a packet reaches a region where greedy forwarding is impossible, the algorithm recovers by routing around the perimeter of the region. By keeping state only about the local topology, GPSR scales better in per-router state than shortest-path and ad-hoc routing protocols as the number of network destinations increases. Under mobility's frequent topology changes, GPSR can use local topology information to find correct new routes quickly. We describe the GPSR protocol, and use extensive simulation of mobile wireless networks to compare its performance with that of Dynamic Source Routing. Our simulations demonstrate GPSR's scalability on densely deployed wireless networks.

Abstract—This paper examines the latency in Internet path failure, failover, and repair due to the convergence properties of interdomain routing. Unlike circuit-switched paths which exhibit failover on the order of milliseconds, our experimental measurements show that interdomain routers in the packet-switched Internet may take tens of minutes to reach a consistent view of the network topology after a fault. These delays stem from temporary routing table fluctuations formed during the operation of the Border Gateway Protocol (BGP) path selection process on Internet backbone routers. During these periods of delayed convergence,we show that end-to-end Internet paths will experience intermittent loss of connectivity, as well as increased packet loss and latency. We present a two-year study of Internet routing convergence through the experimental instrumentation of key portions of the Internet infrastructure, including both passive data collection and fault-injection machines at major Internet exchange points. Based on data from the injection and measurement of several hundred thousand interdomain routing faults, we describe several unexpected properties of convergence and show that the measured upper bound on Internet interdomain routing convergence delay is an order of magnitude slower than previously thought. Our analysis also shows that the upper theoretic computational bound on the number of router states and control messages exchanged during the process of BGP convergence is factorial with respect to the number of autonomous systems in the Internet. Finally, we demonstrate that much of the observed convergence delay stems from specific router vendor implementation decisions and ambiguity in the BGP specification. Index Terms—Failure analysis, Internet, network reliability, routing.

und the perimeter of the region. By keeping state only about the local topology, GPSR scales better in per-router state than shortest-path and ad-hoc routing protocols as the number of network destinations increases. Under mobility's frequent topology changes, GPSR can use local topology information to find correct new routes quickly. We describe the GPSR protocol, and use extensive simulation of mobile wireless networks to compare its performance with that of Dynamic Source Routing. Our simulations demonstrate GPSR's iii scalability on densely deployed wireless networks. iv Contents 1 Introduction 1 1.1 Metrics for Evaluating Routing Scalability . . . . . . . . . . . . . . . . . . 3 1.2 Traditional Shortest-Path Algorithms . . . . . . . . . . . . . . . . . . . . . 4 1.3 Ad-Hoc Routing Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.4 Techniques for Routing Scalability . . . . . . . . . . . . . . . . . . . . . . 7 1.5 Applica

We compare the performance of two recently proposed distance--vector algorithms (Merlin-- Segall and Extended Bellman--Ford) with a link--state algorithm (SPF), under varying file transfer workload. (Unlike the traditional distance--vector algorithms, these new distance-- vector algorithms do not suffer from long--lived loops.) Our comparison is done using a recently developed network simulator, MaRS. We consider both dynamic and static file transfer connections, and both uniform and hotspot distributions of source--sink pairs. Our conclusion is that Extended Bellman--Ford performs as well as SPF in terms of delay and throughput. This suggests that distance--vector algorithms are appropriate for very large wide--area networks, since their space requirements are less than that of link-state algorithms. 1 Introduction In wide--area store--and--forward computer networks, routing protocols are responsible for forwarding data packets over good routes which optimize real--time performance ...

We examine two approaches to adaptive routing protocols for wide-area store-and-forward networks, namely, distance-vector and link-state. Distance-vector algorithms have less storage requirements than link-state algorithms. The ARPANET started with a distance-vector algorithm (Distributed Bellman-Ford), but because of long-lived loops, changed to a link-state algorithm (SPF). We evaluate, using a recently developed network simulator, MaRS, the transient and steady-state performance of SPF and two newly proposed distance-vector algorithms (ExBF and MS). Overall, SPF and ExBF have comparable performance and MS is worse.

A new family of routing algorithms for the distributed maintenance of routing information in large networks and internets is introduced. This family is called link vector algorithms (LVA), and is based on the selective diffusion of link-state information based on the distributed computation of preferred paths, rather than on the flooding of complete link-state information to all routers. According to LVA, each router maintains a subset of the topology that corresponds to the links used by its neighbor routers in their preferred paths to known destinations. Based on that subset of topology information, the router derives its own preferred paths and communicates the corresponding link-state information to its neighbors. An update message contains a vector of updates; each such update specifies a link and its parameters. LVAs can be used for different types of routing. The correctness of LVA is verified for arbitrary types of routing when correct and deterministic algorithms are used to s...

Internet measurements have shown that network failures happen frequently, and that existing routing protocols can take multiple seconds, or even minutes, to converge after a failure. During these routing convergence periods, some packets may already be en-route to their destinations and new packets may be sent. These in-flight packets can encounter routing loops, delays, and losses. However, little is known about how many packets are delivered (or not delivered) during routing convergence periods.

The Internet is a collection of packet based, hop-by-hop routed networks. Internet traffic engineering is the process of allocating resources to meet the performance requirements of users and operators for their traffic. Current mechanisms for doing so, exemplified by TCP’s congestion control, or the variety of packet marking disciplines, concentrate on allocating resources on a per-packet basis, or at data timescales. This article motivates the need for traffic engineering in the Internet at other timescales, namely control and management timescales, and presents three mechanisms for this. It also presents a scenario to show how these mechanisms increase the flexibility of operators ’ service offerings and potentially also ease problems of Internet management.

:With the new rise of applications such as multimedia, the networking environment has to provide more and more bandwidth and should be able to meet the user requirement . The deployment of optical fibers with the emergence of the ATM technology which relies on a Virtual Call (VC) model is the necessary infrastructure to support these applications.. However, we believe that the QoS routeing for VC model has received little attention from the researcher community. In this paper, we propose to extend the classical method for packet switching, namely the distance vector and the link state method to cover these new user requirements. We present routeing architectures using route recording and source routeing which are based on "pre-computed" and "on-demand" routes. Simulation results are provided for the on-demand DV algorithm we propose. 1 Introduction With the new rise of applications such as multimedia, the networking environment has to provide more and more bandwidth and should be ab...

We present an architecture for inter-domain policy routing (IDPR). The objective of IDPR is to construct and maintain routes, between source and destination administrative domains, that provide user traffic with the requested services within the constraints stipulated for the domains transited. The IDPR architecture is designed to accommodate an internetwork containing tens of thousands of administrative domains with heterogeneous service requirements and restrictions.