Accelerating Packet Classification with Counting Bloom Filters for Virtual OpenFlow Switching

摘要

The growing trend of network vir-tualization results in a widespread adoption of virtual switches in virtualized environments. However, virtual switching is confronted with great performance challenges regarding packet classification especially in OpenFlow-based software defined networks. This paper first takes an insight into packet classification in virtual OpenFlow switching, and points out that its performance bottleneck is dominat-ed by flow table traversals of multiple failed mask probing for each arrived packet. Then we are motivated to propose an efficient pack-et classification algorithm based on counting bloom filters. In particular, counting bloom fil-ters are applied to predict the failures of flow table lookups with great possibilities, and by-pass flow table traversals for failed mask prob-ing. Finally, our proposed packet classification algorithm is evaluated with real network traf-fic traces by experiments. The experimental results indicate that our proposed algorithm outperforms the classical one in Open vSwitch in terms of average search length, and contrib-utes to promote virtual OpenFlow switching performance.