Maintaining Predictable Traffic Engineering Performance Under Controller Failures for Software-Defined WANs

Abstract

Many new cloud services and applications have emerged recently. They account for a large share of traffic in Wide Area Networks (WANs) and provide traffic with various Quality of Service (QoS) requirements. Software-Defined Wide Area Network (SD-WAN) offers a promising opportunity for improving the performance of these applications with flexible network management. Nevertheless, SD-WANs are managed by controllers, and unpredictable controller failures may degrade flexible network management. Switches previously controlled by the failed controllers become offline, and flows traversing these offline switches lose the path programmability to route flows on available forwarding paths. Thus, these offline flows cannot be routed/rerouted on available paths to accommodate potential traffic variations, leading to severe performance degradation. Traffic Engineering (TE) is a prevalent network application, which aims to enable differentiable QoS for these numerous cloud services and applications. However, TE performance cannot be guaranteed when controller failures happen due to the loss of flexible network management. Existing recovery solutions reassign offline switches to other active controllers to recover the degraded path programmability but may not promise good TE performance since higher path programmability does not necessarily guarantee satisfactory TE performance. In this paper, we propose Ares to provide predictable TE performance under controller failures. We formulate an optimization problem, which aims to maintain predictable TE performance by jointly considering fine-grained flow-controller reassignment and flow rerouting. Given that the proposed problem is proven to be NP-hard, we further propose a heuristic algorithm to efficiently solve this problem. Specifically, when controller failures occur, Ares updates real-time network information with traffic traces and failure status to calculate optimal flow-controller reassignment and flow rerouting policies. Ares then reassigns and reroutes offline flows to maintain predictable TE performance. Extensive simulation results under two real-world topologies with traffic traces demonstrate that our problem formulation exhibits comparable load balancing performance to optimal TE solution without controller failures, and the proposed Ares can significantly improve average load balancing performance by up to 35.79% with low computation time compared with the state-of-the-art solution.