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.