A Novel Fault Tolerance Mechanism for Software Defined Networking

Software Defined Networking (SDN) is a new network design paradigm. SDNs depend on decoupling thecontrol plane from the forwarding plane atthe network switches. SDNs use logically centralized controllers that are responsible for directing the forwarding decisions to the connected switches. In this paper, we design a new model to provide fault tolerance using feedback control to SDNs based on load balancing schemes. The model is called load balancing to support fault tolerance using feedback control for SDNs (LBFTFB). LBFTFB improves the resistance to cascaded failures. Cascading failures cause an enormous increase in the load of the surrounding controllers as a subsequence of the failure of a certain controller. On SDN controller failures, the LBFTFB distributes the load on the failed controller among thesurrounding controllers based on a defined feedback control policy. The LBFTFB model reduces the cascading failure problem when compared to HyperFlow model which is considered as a reference model. The HyperFlow model is a distributed control plane for OpenFlow. HyperFlow model suffers from a dramatic increase in the load of the surrounding controllers as a consequence of the failure of a certain controller. This is an ongoing research. Tentative emulation results are promising and show that the LBFTFB model outperforms the reference model for cascading failures by 14% in terms of packet loss and 17% in terms of packet delays

I. Introduction

Software Defined Networking (SDN) decouples the control plane and the forwarding plane of network devices. Controllers at the network edge are responsible for the complex control plane functionality while the network switches are responsible for the forwarding plane functionality[2]. Figure 1 shows the data and control planes for traditional network and Figure 2 shows data and control planes for SDN networks. In this paper, SDNs use OpenFlow protocol [2] [15] [16] which is a communication protocol that enables a controller to interact with OpenFlow switches [1]. Initial SDN designs assumed a single controller design [1]. Single controller designs suffer from single point of failure problem. Multi-controller designs improve the SDN networks scalability and reliability[3]. In the multi-controller SDN designs, switches are assigned to multiple controllers to avoid overloading of the controller. While multi-controller designsprevent single point of failures, failing of one of the controllers might lead to subsequent failures of the other surrounding available controllers. That is, when a controller fails, switches associated with that controller get re-assigned to the available controllers. This problem is referred to as cascading controller failure problem.