Hanhimnara Choi, Syed Muhammad Raza, Moonseong Kim, Hyunseung Choo, Journal of Internet Computing and Services, Vol. 22, No. 2, pp. 11-17, Apr. 2021
10.7472/jksii.2021.22.2.11, Full Text:  HTML
Keywords: Software-Defined Networking, OpenFlow, Flow table management

Abstract

Software-defined networking provides a programmable and flexible way to manage the network by separating the control plane from data plane. However, the limited switch memory restricts the number of flow entries in the flow table used to forward packets. This leads to flow table overflow and flow entry reinstallation, which severely degrade the network performance. Therefore, this paper proposes a comprehensive policy for timely eviction of inactive flow entries to optimally maintain flow tables usage. In particular, statistics of user datagram protocol flow entries are periodically sampled to enable the inactive entries to be evicted early. Through traffic-based experiments, we found that the proposed system reduces the number of overflow occurrences and flow entries reinstallation compared to the random and FIFO policies.

Statistics
Cite this article