The introduction of Network Function Virtualisation (NFV) represents a significant change in networking technology, which may create new opportunities in terms of cost efficiency, operations, and service provisioning. Although not explicitly stated as an objective, the dependability of the services provided using this technology should be at least as good as conventional solutions. Logical centralisation, off-the-shelf computing platforms, and increased system complexity represent new dependability challenges relative to the state of the art. The core function of the network, with respect to failure and service management, is orchestration. The failure and misoperation of the NFV Orchestrator (NFVO) will have huge network-wide consequences. At the same time, NFVO is vulnerable to overload and design faults.Thus, the objective of this paper is to give a tutorial on the dependability challenges of the NFVO, and to give insight into the required future research. This paper provides necessary background information, reviews the available literature, outlines the proposed solutions, and identifies some design and research problems that must be addressed.

To provide high availability despite link failures, many modern communication networks feature fast failover mechanisms in the data plane, which operates orders of magnitude faster than the control plane. While the configuration of highly resilient data planes using the shortest possible backup routes is known to be a difficult combinatorial problem, over the last years, much progress has been made in the design of algorithms which provably guarantee connectivity even under many concurrent link failures. However, while these algorithms provide connectivity, the resulting routes after failures can be very long, which in turn can harm performance. In this paper, we propose, analyze, and evaluate methods for fast failover algorithms which account for the quality of the routes after failures, in addition to connectivity. In particular, we revisit the existing approach to cover the to-be-protected network with arc-disjoint spanning arborescences to define alternative routes to the destination, aiming to keep the stretch imposed by these trees low (hence the name of our method: Bonsai). We show that the underlying problem is NP-hard on general topologies and present lower bound results that are tight for various topologies, for any class of fast failover algorithms. We also present heuristics for general networks and demonstrate their performance benefits in extensive simulations. Finally, we show that failover algorithms using low-stretch arborescences, as a side effect, can provide connectivity under more general failure models than usually considered in the literature.

In order to meet their stringent dependability requirements, most modern packet-switched communication networks support fast-recovery mechanisms in the data plane. While reactions to failures in the data plane can be significantly faster compared to control plane mechanisms, implementing fast recovery in the data plane is challenging, and has recently received much attention in the literature. This survey presents a systematic, tutorial-like overview of packet-based fast-recovery mechanisms in the data plane, focusing on concepts but structured around different networking technologies, from traditional link-layer and IP-based mechanisms, over BGP and MPLS to emerging software-defined networks and programmable data planes. We examine the evolution of fast-recovery standards and mechanisms over time, and identify and discuss the fundamental principles and algorithms underlying different mechanisms. We then present a taxonomy of the state of the art, summarize the main lessons learned, and propose a few concrete future directions.

No abstract

Abstract-Software-Defined Networking (SDN) promises to improve the programmability and flexibility of networks, but it may also bring new challenges that need to be explored. The main objective of this paper is to present a quantitative assessment of the properties of SDN backbone networks to determine whether they can provide similar availability to the traditional IP backbone networks. To achieve this goal, we have completed the following steps: i) we formalized a two-level availability model that is able to capture the global network connectivity without neglecting the essential details; ii) we proposed Markov models for characterizing the single network elements in both SDN and traditional networks; iii) we carried out an extensive sensitivity analysis of a national and a world-wide backbone networks. The results have highlighted the considerable impact of operational and management (O&M) failures on the overall availability of SDN. High O&M failure intensity may reduce the availability of SDN as much as one order of magnitude compared to traditional networks. Moreover, the results show that the impact of software and hardware failures on the overall availability of SDN can be significantly reduced through proper overprovisioning of the SDN controller(s).