Experience in black-box OSPF measurement

  • Authors:
  • Aman Shaikh;Albert Greenberg

  • Affiliations:
  • University of California, Santa Cruz, CA;AT&T Research, Florham Park, NJ

  • Venue:
  • IMW '01 Proceedings of the 1st ACM SIGCOMM Workshop on Internet Measurement
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

OSPF (Open Shortest Path First) is a widely used intra-domain routing protocol in IP networks. Internal processing delays in OSPF implementations impact the speed at which updates propagate in the network, the load on individual routers, and the time needed for both intra-domain and inter-domain routing to reconverge following an internal topology or a configuration change. An OSPF user, such as an Internet Service Provider, typically has no access to the software implementation, and no way to estimate these delays directly. In this paper, we present black-box methods (i.e., measurements that rely only on external observations) for estimating and trending delays for key internal tasks in OSPF: processing Link State Advertisements (LSAs), performing Shortest Path First calculations, updating the Forwarding Information Base, and flooding LSAs. Corresponding measurements are reported for production routers from Cisco Systems. To help validate the methodology, black-box and white-box (i.e., measurements that rely on internal instrumentation) are reported for a open source OSPF implementation, GateD.