The case for separating routing from routers

Abstract

Over the past decade, the complexity of the Internet's routing infrastructure has increased dramatically. This complexity and the problems it causes stem not just from various new demands made of the routing infrastructure, but also from fundamental limitations in the ability of today's distributed infrastructure to scalably cope with new requirements.The limitations in today's routing system arise in large part from the fully distributed path-selection computation that the IP routers in an autonomous system (AS) must perform. To overcome this weakness, interdomain routing should be separated from today's IP routers, which should simply forward packets (for the most part). Instead, a separate Routing Control Platform (RCP) should select routes on behalf of the IP routers in each AS and exchange reachability information with other domains.Our position is that an approach like RCP is a good way of coping with complexity while being responsive to new demands and can lead to a routing system that is substantially easier to manage than today. We present a design overview of RCP based on three architectural principles-path computation based on a consistent view of network state, controlled interactions between routing protocol layers, and expressive specification of routing policies-and discuss the architectural strengths and weaknesses of our proposal.

Lcast: Software-defined inter-domain multicast

“…Note that we are not the first to propose such split. This ideas has been previously recommended to aid routing scalability [37] and is nowadays central to current SDN research [38].…”

Virtual Area Routing: a Scalable Intra-Domain Routing Scheme

“…We are not the first to claim that control and data separation can enhance routing performance. RCP [7] is proposed to improve the flexibility of routing selection as well as facilitate configuration. 4D [8] is an innovative routing architecture which is consisted of Decision plane, Dissemination plane, Discovery plane, Data plane.…”

“…Large network may occasionally experience LSA Storm which can probably result in congestion when the underlying network is overloaded by data traffic, or even worsen the congestion situation. Other abnormal interactions between control and data plane are beyond this paper's scope, but yet undeniable [7].…”

Resilience support in software-defined networking: A survey

“…The growth in number and variety of end-to-end services that networks must support has led to a great deal of heterogeneity in the way networks are implemented, resulting in (i) complex protocols to handle the communication between network devices [1], (ii) difficult deployment of network policies by network administrators [2] and (iii) limited routing scalability [3,4,5]. Additionally, challenges to normal network operation, such as malicious attacks and prohibitive communication delay, demonstrate that computer networks have long-standing resilience requirements [6].…”