Showing papers by "Jia Wang published in 2005"

On AS-level path inference

Abstract: The ability to discover the AS-level path between two end-points is valuable for network diagnosis, performance optimization, and reliability enhancement. Virtually all existing techniques and tools for path discovery require direct access to the source. However, the uncooperative nature of the Internet makes it difficult to get direct access to any remote end-point. Path inference becomes challenging when we have no access to the source or the destination. Moveover even when we have access to the source and know the forward path, it is nontrivial to infer the reverse path, since the Internet routing is often asymmetric.In this paper, we explore the feasibility of AS-level path inference without direct access to either end-points. We describe RouteScope-a tool for inferring AS-level paths by finding the shortest policy paths in an AS graph obtained from BGP tables collected from multiple vantage points. We identify two main factors that affect the path inference accuracy: the accuracy of AS relationship inference and the ability to determine the first AS hop. To address the issues, we propose two novel techniques: a new AS relation-ship inference algorithm, and a novel scheme to infer the first AS hop by exploiting the TTL information in IP packets. We evaluate the effectiveness of RouteScope using both BGP tables and the AS paths collected from public BGP gateways. Our results show that it achieves 70% - 88% accuracy in path inference.

Finding a needle in a haystack: pinpointing significant BGP routing changes in an IP network

Abstract: The performance of a backbone network is vulnerable to interdomain routing changes that affect how traffic travels to destinations in other Autonomous Systems (ASes) Despite having poor visibility into these routing changes, operators often need to react quickly by tuning the network configuration to alleviate congestion or by notifying other ASes about serious reachability problems Fortunately, operators can improve their visibility by monitoring the Border Gateway Protocol (BGP) decisions of the routers at the periphery of their AS However, the volume of measurement data is very large and extracting the important information is challenging In this paper, we present the design and evaluation of an online system that converts millions of BGP update messages a day into a few dozen actionable reports about significant routing disruptions We apply our tool to two months of BGP and traffic data collected from a Tier-1 ISP backbone and discover several network problems previously unknown to the operators Validation using other data sources confirms the accuracy of our algorithms and the tool's additional value in detecting routing disruptions

A measurement study of Internet bottlenecks

Abstract: Recent advances in Internet measurement tools have made it possible to locate bottleneck links that constrain the available bandwidth of Internet paths. In this paper, we provide a detailed study of Internet path bottlenecks. We focus on the following four aspects: the persistence of bottleneck location, the sharing of bottlenecks among destination clusters, the packet loss and queueing delay of bottleneck links, and the relationship with router and link properties, including router CPU load, router memory load, link traffic load, and link capacity. We find that 20% - 30% of the source-destination pairs in our measurement have a persistent bottleneck; fewer than 10% of the destinations in a prefix cluster share a bottleneck more than half of the time; 60% of the bottlenecks on lossy paths can be correlated with a loss point no more than 2 hops away; and bottlenecks can be clearly correlated with link load, while presenting no strong relationship with link capacity, router CPU and memory load.

On understanding of transient interdomain routing failures

Abstract: The convergence time of the interdomain routing protocol, BGP, can last as long as 30 minutes. Yet, routing behavior during BGP route convergence is poorly understood. BGP can experience transient loss of reachability during route convergence. We refer to this transient loss of reachability during route convergence as transient routing failure. Transient routing failures can lead to end-to-end forwarding failures. Furthermore, the prolonged routing failures can make deploying applications such as voice-over-IP and interactive games infeasible. In this paper, we study the extent to which transient interdomain routing failures occur in the Internet and the duration that these failures can last through both analysis and measurement. We first present a formal model that captures the transient behavior of the interdomain routing protocol. We derive sufficient conditions for and an upper bound for the duration of transient routing failures. Furthermore, we demonstrate the occurrence and duration of transient routing failures in the Internet through measurement. We find that majority of transient failures occur under the commonly applied routing policy setting, and popular and unpopular prefixes can experience transient failures.

Method and apparatus for inferring network paths

Abstract: Disclosed is a method and apparatus for inferring AS paths between two endpoint nodes communicating over a network having a plurality of nodes without having access to the endpoint nodes. The method and apparatus determine routing tables of at least some of the plurality of nodes. A relationship between each node is then inferred from the routing tables. The method and apparatus then determine a path between the two endpoint nodes from the relationship and the routing table determination.

Optimizing network performance in replicated hosting

Abstract: Most important commercial Web sites maintain multiple replicas of their server infrastructure to increase both reliability and performance. In this paper, we study how many replicas should be used and where they should be placed in order to improve client network performance, including both the latency (e.g., round-trip time) between clients and the replicas, and the bandwidth performance between them. This study is based on a large scale measurement study from an 18-node infrastructure, which reveals for the first time the distribution of today's Internet end-user access bandwidth. For example, we find that 50% of end users have access bandwidth less than 4.2Mbps. Using a greedy algorithm, we show that the first five replicas dominate latency optimization in our measurement infrastructure, while the first two replicas dominate bandwidth optimization. We also found that geographic diversity does not help as much for bandwidth optimization as it does for latency. To determine the proper trade-off between latency and bandwidth, we use a simplified TCP model to show that, when content size is less than 10Kb, the deployment should focus on optimizing latency, while for content sizes larger than 1 Mb, the deployment should focus on optimizing bandwidth.