OpenFlow based flow slice load balancing

Abstract

Today's data center networks are designed using densely interconnected hosts in the data center. There are multiple paths between source host and destination server. Therefore, how to balance traffic is key issue with the fast growth of network applications. Although lots of load balancing methods have been proposed, the traditional approaches cannot fully satisfy the requirement of load balancing in data center networks. The main reason is the lack of efficient ways to obtain network traffic statistics from each network device. As a solution, the OpenFlow protocol enables monitoring traffic statistics by a centralized controller. However, existing solutions based on OpenFlow present a difficult dilemma between load balancing and packet reordering. To achieve a balance between load balancing and packet reordering, we propose an OpenFlow based flow slice load balancing algorithm. Through introducing the idea of differentiated service, the scheme classifies Internet flows into two categories: the aggressive and the normal, and applies different splitting granularities to the two classes of flows. This scheme improves the performance of load balancing and also reduces the number of reordering packets. Using the trace-driven simulations, we show that the proposed scheme gains over 50% improvement over previous schemes under the path delay estimation errors, and is a practical and efficient algorithm.