Multi-VPN Optimization for Scalable Routing via Relaying

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 involves a very high memory footprint and is causing associated routing tables in the service provider´s routers to grow very large. The concept of relaying was proposed earlier [6] to separately minimize the routing table memory footprint of individual VPNs, and involves selecting a small number of hub routers to maintain complete reachability information for that VPN, and enabling non-hub spoke routers with reduced routing tables to achieve any-to-any reachability by routing traffic via a hub. A large service provider network typically hosts many 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 solve this NP-complete problem. Evaluations using traces and configurations from a large provider and many real-world VPNs indicate that the resulting Relaying solution substantially 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.