Enhanced Flow Table Management Scheme With an LRU-Based Caching Algorithm for SDN

Abstract

We propose a flow table management scheme for OpenFlow switches to minimize table-miss in a flow table. Commercial OpenFlow switches have one or more flow tables that consist of flow entries for processing packets. However, flow entries are managed based only on their timeout parameters, meaning they are expired and deleted by switches regardless of their reusability. The absence of the flow entry then causes table-misses in the future. We propose a solution for the problem of switches disregarding vacancies in the flow table when deleting expired flow entries. When a table-miss occurs, the corresponding switch must perform additional interactions with an OpenFlow controller to insert new flow entries, but this results in additional processing time and communication overhead. Previous studies aimed at solving this limitation have used sophisticated training sets or modified network architectures. In contrast, we propose a simple flow table management scheme with a least recently used-based caching algorithm to keep flow entries in an OpenFlow switch as long as possible. For this purpose, the switch continually adjusts its cache size according to the vacancy of each flow table and the controller determines the packet forwarding path through the switches by referring to the vacancies. We perform an experimental evaluation of the proposed scheme and demonstrate the performance gains in terms of the number of table-missed packets. We also analyze the effectiveness of the flow entry caching scheme using a mathematical model.

Keywords

• Flow table
• OpenFlow
• software-defined networking