Abstract
The blooming of cloud computing leads to the rapid expansion of data center networks (DCN). Conventional link state routing algorithms like OSPF are widely adopted in data center networks, however, those routing algorithms bring great control overheads and long convergence time. Recently, topology-aware routing methods are considered to be efficient especially in data center networks with regular topologies. Lots of topology-aware routing methods (e.g., Fat-Tree and BCube) have been proposed for specific data center network topologies. This paper first proposes a formalized method to describe regular topologies and a regular Topology Description Language (TPDL) based on this method. TPDL is well designed to accurately define regular network topologies in a clear way leveraging their regularities. Based on the Software-Defined Networking (SDN) technology, this paper also proposes a novel topology-aware routing scheme: cRetor (controller-side REgular TOpology Routing scheme). Different from other topology-aware routing methods, cRetor is a TPDL-based general routing method, which means it is expected to work on different kinds of regular topologies. In this scheme, TDPL files are used as a priori knowledge to build an initial topology in the SDN controllers, which eliminates the process of topology discovery via Link Layer Discovery Protocol (LLDP) and hence relieves the bandwidth and processing burdens on controllers. Besides, we also apply the A-star algorithm to SDN controllers to speed up the routing selection, where TPDL's distance formulas act as the heuristic function. The experimental results show that cRetor outperforms LLDP-based SDN, OSPF and DCell in routing calculation performance, convergence speed, routing overheads and fault tolerance.
Highlights
With the wide application of cloud computing and big data technologies, the scale of data centers has increased rapidly, which leads to a higher demand for both communication and management capabilities of data center networks
WORK In this paper, an Software-Defined Networking (SDN)-based topology-aware routing scheme cRetor for regular network topologies is proposed, which leverages the regularities of topology in the data center networks to achieve efficient topology description and distance calculation
We designed and implemented a routing scheme based on Topology Description Language (TPDL) and SDN technology, as well as an efficient routing calculation method and fault handling mechanism based on the A-star algorithm and TPDL
Summary
With the wide application of cloud computing and big data technologies, the scale of data centers has increased rapidly, which leads to a higher demand for both communication and management capabilities of data center networks. We propose an SDN-based topology-aware routing approach for large-scale data center networks: cRetor. This scheme takes advantage of the structure character for efficient topology discovery and path calculation in a regular network topology. As a more general topology-aware routing algorithm, cRetor’s performance in convergence, routing protocol overhead, and scalability are slightly lower than dedicated routing algorithms like Fat-Tree two level routing and BCube source routing algorithms and DCell It has more advantages than general routing algorithms such as SDN and OSPF. The experimental results show that cRetor has obvious advantages compared with the traditional OSPF algorithm and the existing SDN routing method as well as a DCell implementation in terms of path computation performance, network convergence speed, routing overheads and fault recovery capability. The rest of this paper is structured as follows: section II presents the formal description method and TPDL; section III elaborates the architecture and algorithms in cRetor; section IV focuses on the experiments and results about cRetor compared with OSPF, Floodlight and DCell; section V explores related work; section VI concludes the paper and mentions directions for future work
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
