Topic
Equal-cost multi-path routing
About: Equal-cost multi-path routing is a research topic. Over the lifetime, 10472 publications have been published within this topic receiving 249362 citations.
Papers published on a yearly basis
Papers
More filters
01 May 1996
TL;DR: The purpose of SDRP is to support source-initiated selection of routes to complement the route selection provided by existing routing protocols for both inter-domain and intra-domain routes.
Abstract: The purpose of SDRP is to support source-initiated selection of routes
to complement the route selection provided by existing routing
protocols for both inter-domain and intra-domain routes. This memo
provides information for the Internet community. This memo does not
specify an Internet standard of any kind.
60 citations
02 Jun 2003
TL;DR: Under this approach, upon a link failure, adjacent router suppresses global updating and instead initiates local rerouting, which provides higher service availability than the existing routing schemes.
Abstract: Intra-domain routing protocols employed in the Internet route around failed links by having routers detect adjacent link failures, exchange link state changes, and recompute their routing tables. Due to several delays in detection, propagation and recomputation, it may take tens of seconds to minutes after a link failure to resume forwarding of packets to the affected destinations. This discontinuity in destination reachability adversely affects the quality of continuous media applications such as Voice over IP. Moreover, the resulting service unavailability for even a short duration could be catastrophic in the world of e-commerce. Though careful tuning of the various parameters of the routing protocols can accelerate convergence, it may cause instability when the majority of the failures are transient. To improve the failure resiliency without jeopardizing the routing stability, we propose a local rerouting based approach called failure insensitive routing. Under this approach, upon a link failure, adjacent router suppresses global updating and instead initiates local rerouting. All other routers infer potential link failures from the packet's incoming interface, precompute interface specific forwarding We demonstrate that the proposed approach provides higher service availability than the existing routing schemes.
59 citations
27 Oct 2014
TL;DR: It is argued that future networks can achieve the benefits of both approaches through central control over the distributed route computation through Fibbing, which is to have the controller trick the routers into seeing a fake topology that is carefully constructed to achieve the desired Forwarding Information Base.
Abstract: Link-state routing protocols (e.g., OSPF and IS-IS) are widely used because they are scalable, robust, and based on simple abstractions. Unfortunately, these protocols are also relatively inflexible, since they direct all traffic over shortest paths. In contrast, Software Defined Networking (SDN) offers fine-grained control over routing, at the expense of controller overhead, failover latency, and deployment challenges.We argue that future networks can achieve the benefits of both approaches through central control over the distributed route computation. The key idea, which we call Fibbing, is to have the controller trick the routers into seeing a fake topology that is carefully constructed to achieve the desired Forwarding Information Base (FIB). Given an acyclic forwarding graph for each destination, the controller computes an augmented topology with fake nodes (and destinations to announce there) and fake links (and link weights). The controller injects these "lies" into the link-state routing protocol, and the routers simply compute the paths accordingly. The controller can also select an augmented topology that triggers the use of specific backup paths when real links and routers fail. To reduce router load, our Fibbing algorithms compute augmented topologies of minimal size. Our preliminary evaluation on realistic ISP topologies shows that Fibbing works well in practice.
59 citations
Patent•
07 May 2001
TL;DR: In this article, the authors describe a method for routing communications in a storage system, where the storage system may include multiple nodes interconnected by an interconnection fabric that provides multiple independent paths between a source node and a destination node.
Abstract: Embodiments of a routing system are disclosed, including a method for routing communications in a storage system. The storage system may include multiple nodes interconnected by an interconnection fabric that provides multiple independent paths between a source node and a destination node. Some nodes may be connected to one or more disk drives. The method may include receiving a communication to be sent from a source node to a destination node, selecting a communication path from the multiple independent paths, and sending the communication on the selected communication path. This process may be repeated so that multiple communications may be sent. Each communication path may be selected according to a preference assigned to it, so that a more preferred path is selected more often than a less preferred path.
59 citations