Performance evaluation for SDN deployment: an approach based on stochastic network calculus

摘要

The OpenFlow implementations (SDNs) have been deployed increasingly on varieties of networks in research institutions as well as commercial institutions. To develop an OpenFlow implementation, it is required to understand the performance of the network. A few benchmark tools (e.g., Cbench and OFlops) can be used to measure the network performance, while these tools take considerable time to simulate traffic behaviors and generate the required results, therefore extending the development time. In this paper, we present an analytical model, which is based on stochastic network calculus theory, for evaluating the performance of switch to controller. The previous studies show that stochastic network calculus can provide realistic emulation of real network traffic behaviors. Our model is evaluated by using both simulation tool and realistic testbed. The results show the stochastic network calculus based analysis model can realistically measure the network performance of the end-to-end properties between controller and switch.