ARES: Predictable Traffic Engineering under Controller Failures in SD-WANs

Emerging web applications (e.g., video streaming and Web of Things applications) 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 Networks (SD-WANs) offer a promising opportunity to enhance the performance of Traffic Engineering (TE), which aims to enable differentiable QoS for numerous web applications. Nevertheless, SD-WANs are managed by controllers, and unpredictable controller failures may undermine flexible network management. Switches previously controlled by the failed controllers may 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 previous paths to accommodate potential traffic variations, leading to severe TE performance degradation. Existing recovery solutions reassign offline switches to other active controllers to recover the degraded path programmability but fail to 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 to maintain predictable TE performance by jointly considering fine-grained flow-controller reassignment using P4 Runtime and flow rerouting and propose ARES to efficiently solve this problem. Extensive simulation results demonstrate that our problem formulation exhibits comparable load balancing performance to optimal TE solution without controller failures, and the proposed ARES significantly improves average load balancing performance by up to 43.36% with low computation time compared with existing solutions.