Fleet

Abstract

We present the malicious administrator problem, in which one or more network administrators attempt to damage routing, forwarding, or network availability by misconfiguring controllers. While this threat vector has been acknowledged in previous work, most solutions have focused on enforcing specific policies for forwarding rules. We present a definition of this problem and a controller design called Fleet that makes a first step towards addressing this problem. We present two protocols that can be used with the Fleet controller, and argue that its lower layer deployed on top of switches eliminates many problems of using multiple controllers in SDNs. We then present a prototype simulation and show that as long as a majority of non-malicious administrators exists, we can usually recover from link failures within several seconds (a time dominated by failure detection speed and inter-administrator latency).