Delayed Internet routing convergence

  • Authors:
  • Craig Labovitz;Abha Ahuja;Abhijit Bose;Farnam Jahanian

  • Affiliations:
  • Arbor Networks, Ann Arbor, MI and Microsoft Research, Redmond, WA;Arbor Networks, Ann Arbor, MI;Center for Parallel Computing, University of Michigan, Ann Arbor, MI;Arbor Networks, Ann Arbor, MI and University of Michigan, Ann Arbor, MI

  • Venue:
  • IEEE/ACM Transactions on Networking (TON)
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

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 temporary routing table fluctuations formed during the operation of the Border Gateway Protocol (BGP) path selection process on Internet backbone routers. During these periods 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 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 upperbound 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 form specific router vendor implementation decisions and ambiguity in the BGP specification.