论文部分内容阅读
SDN provides an approach to create desired network forwarding plane by programming applications.For a large-scale SDN network comprised of multiple domains and running multiple controller applications, it is difficult to measure and diagnose the problems of flow tables in data plane. Tracing the forwarding path of SDN is one of effective way for data plane state measurement. Previously proposed methods for debugging SDN were applied to a single administrative domain. There is less effort to trace the flow entries of the data plane in large-scale multi-domain SDN networks. In this paper, we propose a method of software defined data plane tracing in large-scale multi-domain SDN networks. Our method can trace forwarding paths, and get the matched flow entries and other customized trace information. We present the designs compatible with Open Flow 1.0 and1.3 switches. The performance and deployment effect are evaluated by simulation test and analysis. It shows that our method has better performance than traditional IP traceroute, and its deployment at about 20% of AS nodes can enable 70% of AS paths to be traceable.
SDN provides an approach to create desired network forwarding plane by programming applications. For a large-scale SDN network comprised of multiple domains and running multiple controller applications, it is difficult to measure and diagnose the problems of flow tables in data plane. Tracing the forwarding path of SDN is one of effective ways for data plane state measurement. Previously proposed methods for debugging SDN were applied to a single administrative domain. There is less effort to trace the flow entries of the data plane in large-scale multi-domain SDN networks . In this paper, we propose a method of software defined data plane tracing in large-scale multi-domain SDN networks. Our method can trace forwarding paths, and get the matched flow entries and other customized trace information. We present the designs compatible with Open flow 1.0 and1.3 switches. The performance and deployment effect are evaluated by simulation test and analysis. It shows that our method has better pe rformance than traditional IP traceroute, and its deployment at about 20% of AS nodes can enable 70% of AS paths to be traceable.