Elastic network monitoring with virtual probes

Abstract

The next generation monitoring solutions should evolve as fast as the applications they will support both in terms of functionality (e.g. new protocols, monitoring function, etc.) as well as in terms of scale and performance. We believe the field of network monitoring is yet to experience the same revolutionary transformation as software-defined networking (SDN) and network function visualization (NFV) brought to the telecom world. To this end we present a flexible network monitoring application we use to demonstrate the potential of next generation network monitoring with advanced probe functionality and virtualization. Our demonstration shows a new OVS-based (Open vSwitch) vProbe capable of adding and processing monitoring metadata in IETF's recently proposed network service header (NSH) for service chaining [1], [2]. The monitoring metadata in this work is used for troubleshooting performance issues (i.e. excessive latency) along service function paths (SFPs). Benefits of our approach are the flexibility it offers to create new monitoring solutions as well as the virtualization of monitoring resources in order to benefit from the same economies of scale and elasticity features of NFV. This demonstration is built as part of our proposed monitoring framework presented in [3] which consists of a monitoring platform which, on the northbound, offers a full control as well as a more limiting intent based interface. It can spin new vProbes when and where needed. The data plane used in this demonstration consists of OpenFlow switches (OVS) extended with the NSH header [4]. This work can be described as a troubleshooting use case customized for service chaining. We demonstrate a video traffic performance degradation scenario and pin down where the issue is for a given flow on a service chain.