Delegating Data Plane With Cloud-Assisted Routing

Abstract

Data centers are embracing the software-defined networking (SDN) as it is evident that this technology of completely separating the data plane from the control plane gives more flexibility for their internal routing management and provides better Quality-of-Service (QoS) to the users. Implementing a similar solution to serve the purpose of software-defined wide-area networking using public Internet routing is also gaining popularity. Although, instead of having a complete separation, a hybrid approach to keep most of the control plane along with the least of the data plane in the remote and vice-versa for the local platform may be more fitting. To this end, we propose a new hybrid SDN approach, Cloud-Assisted Routing (CAR), that utilizes the high computational services that cloud offers at a lower price by splitting both control and data plane functions between a local router and a remote cloud computing platform. Such delegation of data plane to a third-party authority requires proper control plane management policies and handling or avoiding possible loops and failures. We detail the architectural view of CAR, address its associated challenges, and present prototype-based evaluations of it for reducing routing table sizes.