Multi-VPN optimization for scalable routing via relaying

  • Authors:
  • MohammadHossein Bateni;Alexandre Gerber;MohammadTaghi Hajiaghayi;Subhabrata Sen

  • Affiliations:
  • Department of Computer Science, Princeton University, Princeton, NJ and AT&T Labs-Research, Florham Park, NJ;AT&T Labs-Research, Florham Park, NJ;AT&T Labs-Research, Florham Park, NJ;AT&T Labs-Research, Florham Park, NJ

  • Venue:
  • IEEE/ACM Transactions on Networking (TON)
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Enterprise networks are increasingly adopting Layer-3 multiprotocol label switching (MPLS) virtual private network (VPN) technology to connect geographically disparate locations. The any-to-any direct connectivity model of this technology is causing routing tables in the service provider's routers to grow very large. The concept of relaying was proposed earlier to separately minimize the routing table memory footprint of individual VPNs by selecting a small number of hub routers to maintain complete reachability information for each VPN and enabling nonhub spoke routers with reduced routing tables to reach others by routing traffic via a hub. A large service provider network typically hosts thousands of different VPNs. In this paper, we generalize relaying to the multi-VPN environment and consider new constraints on resources shared across VPNs, such as router uplink bandwidth and memory. The hub selection problem involves complex tradeoffs along multiple dimensions including these shared resources and the additional distance traversed by traffic. We formulate the hub selection as a constraint optimization problem and develop an algorithm with provable guarantees to approximate this NP-complete problem. Evaluations using traces and configurations from a large provider indicate that the resulting relaying solution reduces the total router memory requirement by 85% while smoothing out the utilization on each router and requiring only a small increase in the end-to-end path for the relayed traffic.