On the analysis of overlay failure detection and recovery

Application-layer overlay networks have been proposed as an alternative method to overcome IP-layer path anomalies and provide users with improved routing services. Running at the application layer, overlay networks usually rely on probing mechanisms for IP-path performance monitoring and failure detection. Their service performance is jointly determined by their topology, parameters of probing mechanism and failure restoration methods. In this paper, we first define metrics to evaluate the performance of overlay networks in terms of failure detection and recovery, network stability and overhead. Second, we model the overlay-based failure detection and recovery process. Through extensive simulations, we investigate how different IP-layer path failure characteristics and overlay topologies, detection and restoration parameters affect service performance of overlay networks. In particular, we examine the tradeoffs among different overlay performance metrics and the optimal performance conditions. Our study helps to understand overlay-based failure recovery and provides practical guidance to overlay network designers and administrators.