Improving the Performance of Route Control Middleboxes in a Competitive Environment

Abstract

56 0890-8044/08/$25.00 © 2008 IEEE oday, the vast majority of the communications on the Internet are between nodes located in non-transit (i.e., stub) networks. Stub networks are primarily composed of medium and large enterprise customers, universities, public administrations, content service providers (CSPs), and small Internet service providers (ISPs). These networks exploit a widespread practice called multihoming, which consists of using multiple external links to connect to different transit providers. By increasing their connectivity to the Internet, stub networks potentially can obtain several benefits, especially in terms of resilience, cost, and traffic performance [1]. These are described as potential benefits because multihoming per se cannot improve any resilience, cost, and traffic performance. Accordingly, multihomed stub networks require additional mechanisms to achieve these improvements. In particular, when an automatic mechanism actively optimizes the cost and end-to-end performance of the traffic routed among different links connecting a multihomed stub network to the Internet, it is referred to as intelligent route control (IRC).During the last few years, IRC has attracted significant interest in both the research and the commercial fields. Several vendors are developing and offering IRC solutions [2][3][4] that increasingly are being adopted by multihomed stub networks. Most available IRC solutions follow the same principle, that is, they dynamically shift part of the egress traffic of a multihomed subscriber from one of its ISPs to another, using measurement-driven path switching techniques. IRC systems operate in relatively short timescales -even reaching switching frequencies on the order of a few seconds -allowing IRC users to balance cost and performance criteria according to the priority and requirements of their applications.Despite these strengths, IRC practices have one major weakness, that is, they try to achieve a set of local objectives individually without considering the effects of their decisions on the performance of the network. Recently, it was discovered that in a competitive environment, IRC systems actually can cause significant performance degradation rather than improvement. In [5], the authors show that persistent oscillations can occur when independent controllers become synchronized due to a considerable overlap in their measurement time windows. To avoid synchronization issues, the authors propose randomized IRC strategies and empirically show that the oscillations disappear after introducing a random component in the route control decision.It is important to note that although randomization offers a straightforward mechanism to mitigate the oscillations, it cannot guarantee global stability. This issue raises concerns given the proliferation of IRC products because as the number of interfering IRC systems increases, randomization becomes AbstractMultihomed subscribers are increasingly adopting intelligent route control solutions to optimize the cost and end-to-en...

Understanding IPv4 prefix de-aggregation: Challenges for routing scalability

“…In this regard, our basic idea is to benefit from the LISP Map-Server functionality and related protocols, which enable us to build mapping strategies to conceal intra and interdomain traffic engineering objectives, using our previous experience in Intelligent Route Control (IRC) [16] and PCEbased TE [17]. Online computation and provisioning of mappings based on TE policies may be achieved using IRClike techniques, Constraint-Based Routing algorithms and/or classical optimization techniques, such as the IDIPS prototype implementation [18].…”

Bartolomeu: An SDN rebalancing system across multiple interdomain paths

“…Some work deals with fixing the oscillation problems that may arise when multiple MRC devices serving different stub networks operate in parallel [20,41]. As the controllers of each MRC device are selfish, it may occur that all devices coincide in rerouting traffic to the best available path.…”

Managing interdomain traffic in Latin America: a new perspective based on LISP

“…We argue that tools like constraintbased routing (CBR) (for the intradomain part) and an IRM engine borrowing concepts from IRC techniques [6] (for the interdomain part) can work together to accomplish these objectives. At least two appealing solutions can be sketched to drive the intradomain traffic according to the ISP policies.…”

“…The algorithms used to determine the ingress RLOC (RLOC S ) are inherently the same used today by IRC techniques [6]. The E Sto-RLOC S mapping computation is performed by the IRM module of LCB S .…”

“…We outline the strengths of LISP, highlighting a set of important TE opportunities for LA, and we also introduce a novel control plane for LISP that deals with the challenges mentioned above. We discuss the importance of architecting the control plane so as to concurrently provide a highly efficient coupling to the DNS system, the path computation element (PCE) -if present -and an EID-to-RLOC mapping engine that borrows concepts from intelligent route control (IRC) techniques [6]. We conclude with directions for future research, especially in a promising field for LA we refer to here as intelligent route mapping (IRM).…”