Failure Insensitive Routing for Ensuring Service Availability

Abstract

Intra-domain routing protocols employed in the Internet route around failed links by having routers detect adjacent link failures, exchange link state changes, and recompute their routing tables. Due to several delays in detection, propagation and recomputation, it may take tens of seconds to minutes after a link failure to resume forwarding of packets to the affected destinations. This discontinuity in destination reachability adversely affects the quality of continuous media applications such as Voice over IP. Moreover, the resulting service unavailability for even a short duration could be catastrophic in the world of e-commerce. Though careful tuning of the various parameters of the routing protocols can accelerate convergence, it may cause instability when the majority of the failures are transient. To improve the failure resiliency without jeopardizing the routing stability, we propose a local rerouting based approach called failure insensitive routing. Under this approach, upon a link failure, adjacent router suppresses global updating and instead initiates local rerouting. All other routers infer potential link failures from the packet’s incoming interface, precompute interface specific forwarding tables and route around failed links without explicit link state updates. We demonstrate that the proposed approach provides higher service availability than the existing routing schemes.

This work is partly supported by National Science Foundation Grants CAREER Award ANI- 9734428, ANI-0073819, and ITR ANI-0085824. Any opinions, findings, and conclusions or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of the National Science Foundation.