An efficient flow cache algorithm with improved fairness in Software-Defined Data Center Networks

Abstract

The use of Software-Defined Networking (SDN) with OpenFlow-enabled switches in Data Centers has received much attention from researchers and industries. One of the major issues in OpenFlow switch is the limited size of the flow table resulting in evictions of flows from the flow table. From Data Center traffic characteristics, we observe that elephant flows are very large in size (data volume) but few in numbers when compared to mice flows. Thus, Elephant flows are more likely to be evicted, due to the limited size of the switch flow table causing additional traffic to the controller. We propose a differential flow cache framework that achieves fairness and efficient cache maintenance with fast lookup and reduced cache miss ratio. The framework uses a hash-based placement and localized Least Recently Used (LRU)-based replacement mechanisms.