A method and apparatus for hierarchical redundancy for a distributed control plane. In one embodiment of the invention, control plane processes are distributed among a plurality of processing entities including an active primary control processing entity and multiple secondary processing entities. Each of the secondary processing entities performs a dual role; an active role and a standby role. An application redundancy manager (ARM) instantiated on the active primary control processing entity manages the redundancy services for the secondary processing entities. For each secondary processing entity, the ARM selects one of the secondary processing entities to act as a backup for another one of the secondary processing entities. Upon a failure of one of the secondary processing entities, the ARM causes the secondary processing entity backing up the failed secondary processing entity to transition its standby role to an active role regarding the services provided by the failed secondary processing entity.

Hierarchical Redundancy for a Distributed Control Plane

Infrastructure as a Service (IaaS) is considered a prominent model for IP based service delivery. As grid and cloud computing have become a stringent demand for today's Internet services, IaaS is required for providing services, particularly "private cloud," regardless of physical infrastructure locations. However, enabling IaaS on traditional Internet Service Provider (ISP) network infrastructures is challenging because IaaS requires a high abstraction level of network architectures, protocols, and devices. Network control plane architecture plays therefore an essential role in this transition, particularly with respect to new requirements of scalability, reliability, and flexibility. In this article we review the evolutionary trend of network element control planes from monolithic to distributed architectures according to network growth, and then present a new virtualization oriented architecture that allows infrastructure providers and service providers to achieve service delivery independently and transparently to end users based on virtualized network control planes. As a result, current ISP infrastructures will be able to support new services, such as heavy resource consuming data center applications. We also show how to use network virtualization for providing cloud computing and data center services in a flexible manner on the nationwide CANARIE network infrastructure.

/pdf/enabling-infrastructure-as-a-service-iaas-on-ip-networks-4n9olintue.pdf

Enabling infrastructure as a service (IaaS) on IP networks: from distributed to virtualized control plane

In recent years, the exponential growth of Internet users with increased bandwidth requirements has led to the emergence of the next generation of IP routers. Distributed architecture is one of the promising trends providing petabit routers with a large switching capacity and high-speed interfaces. Distributed routers are designed with an optical switch fabric interconnecting line and control cards. Computing and memory resources are available on both control and line cards to perform routing and forwarding tasks. This new hardware architecture is not efficiently utilized by the traditional software models where a single control card is responsible for all routing and management operations. The routing table manager plays an extremely critical role by managing routing information and in particular, a forwarding information table. This article presents a distributed architecture set up around a distributed and scalable routing table manager. This architecture also comes provides improvements in robustness and resiliency. The proposed architecture is based on a sharing mechanism between control and line cards and is able to meet the scalability requirements for route computations, notifications, and advertisements. A comparative scalability evaluation is made between distributed and centralized architectures in terms of required memory and computing resources.

A distributed and scalable routing table manager for the next generation of IP routers

A method and apparatus of updating a forwarding plane of a network element in response to receiving a mobility event is described. The network element receives a mobility message indicating a mobile node has coupled to a new access port associated with the network element. The message further indicates that the mobile node moved from an old access port to a new access port. The network element adds an entry in a forwarding table of the old egress engine to redirect a set of packets destined to the mobile node to a new egress engine, where the new egress engine is associated with the new access port. Furthermore, the network element redirects the set of packet from the old egress engine to the new egress engine.

Forwarding data path optimization in a distributed environment for achieving micro-mobility

In this paper, we present our research aiming at building a petabit router model for next generation networks. Considering the increasing traffic requirements on the Internet, current gigabit and terabit speed routers will soon not be able to meet user demand. One of the promising trends of router evolution is to build next generation routers with enhanced memory capacity and computing resources, distributed across a very high speed switching fabric. The main limitation of the current routing and signaling software modules, traditionally designed in a centralized manner, is that they do not scale in order to fully exploit such an advanced distributed hardware architecture. This paper discusses an implementation for an control plane for next generation routers integrating several protocol dedicated distributed architectures, aiming at increasing the scalability and resiliency. The proposed architecture distributes the processing functions on router cards, i.e., on both control and line cards. Therefore, it reduces the bottlenecks and improves both the overall performance and the resiliency in the presence of faults. Scalability is estimated with respect to the CPU utilization and memory requirements.

Distributed control plane architecture of next generation IP routers

As networks become more and more pervasive and broadband access technologies evolve to provide affordable broadband solutions for both homes and offices, one needs to rethink the architecture design for next generation routers in order to be able to deliver multiple services over high-speed interfaces and perform fast switching capabilities (e.g., multipetabit). The size and complexity of next generation networks requires a protocol transition from its classical centralized approach to a fully distributed and scalable paradigm. In this paper, we propose a new control plane architecture that is resilient and scalable where we distribute the OSPF/IS-IS, MPLS and BGP protocols using IETF-approved inter-protocol interfaces. In such architecture, forwarding tables will be updated by OSPF, IS-IS, RTM, BGP and MPLS routing protocols distributed onto multiple processors, in the interface cards themselves. We therefore revisit each of these protocols and redraw their implementation within an efficient, scalable, distributed, resilient, and fault tolerant scheme. As a proof of concept, we present the hyperchip router (PBR1280) that has been built on these grounds and discuss the performance of the proposed distributed architecture. Although some features (e.g., resiliency) still need further development, it is shown that the proposed distributed routing protocol scheme already offers a new generation of routers with significant higher switching capacity

M. Lanoue

Papers

Toward a Distributed Control Plane Architecture for Next Generation Routers