A Fast and Load-aware Controller Failover Mechanism for Software-Defined Networks

Abstract

We propose a Fast and Load-aware Controller Failover (FLCF) for software-defined networks to resolve the single point of failure problem. The FLCF utilizes one detecting controller to collect all the other controllers\' failure notifications about a failed controller so as to help the detecting controller to make the final decision. Each controller pre-computes its recovery plan and synchronizes the plan with other controllers that will take over the switches if the controller is determined failed. Using Estinet, experiment results show that the proposed FLCF has better performance in terms of failover time and controller load standard deviation than related works.