A monitoring framework at layer4–7 granularity using network service headers

Abstract

Traffic measurement and network monitoring needs have always daunted operators and recent trends of virtualization and programmable networks put a higher stress on this topic. The reality is that today's monitoring toolsets are viable for legacy network operations and traffic. With recent industry trends such as network function virtualization (NFV), software-defined networking (SDN) and everything as a service (XaaS), will follow higher network dynamicity and traffic change patterns. Network monitoring and measurement schemes need to evolve to accommodate these upcoming trends. The research community has been very active in past years in proposing new or improved mechanisms for various monitoring tasks. In this work however we leverage another recent development in the industry for network function chaining and propose to use the newly defined tunneling headers by IETF's service function chaining (SFC) working group to achieve specific and novel monitoring tasks not possible with existing methods. This paper's contributions are two folds: first it proposes a framework and an architecture able to perform unified monitoring across network, cloud, physical and virtual boundaries. Second, based on layer4–7 information it proposes novel monitoring mechanisms applicable to NFV traffic. The latter distinguishes itself with respect to existing proposals by its flexibility and potential for widespread deployment as it piggybacks on IETF's SFC standardization work. This paper's contributions are the system architecture, the monitoring metadata encodings with their respective use cases, as well performance results for monitoring overhead measured on a testbed implementation of this proposal.