Achieving near-optimal traffic engineering solutions for current OSPF/IS-IS networks

Abstract

Traffic engineering is aimed at distributing traffic so as to "optimize" a given performance criterion. The ability to carry out such an optimal distribution depends on both the routing protocol and the forwarding mechanisms in use in the network. In IP networks running the OSPF or IS-IS protocols, routing is over shortest paths, and forwarding mechanisms are constrained to distributing traffic uniformly over equal cost shortest paths. These constraints often make achieving an optimal distribution of traffic impossible. In this paper, we propose and evaluate an approach, based on manipulating the set of next hops for routing prefixes, that is capable of realizing near optimal traffic distribution without any change to existing routing protocols and forwarding mechanisms. In addition, we explore the tradeoff that exists between performance and the overhead associated with the additional configuration steps that our solution requires. The paper's contributions are in formulating and evaluating an approach to traffic engineering for existing IP networks that achieves performance levels comparable to that offered when deploying other forwarding technologies such as MPLS. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.This conference paper is available at ScholarlyCommons: http://repository.upenn.edu/ese_papers/26Achieving Near-Optimal Traffic Engineering Solutions for Current OSPF/IS-IS NetworksAbstract-Traffic engineering is aimed at distributing traffic so as to "optimize" a given performance criterion. The ability to carry out such an optimal distribution depends on both the routing protocol and the forwarding mechanisms in use in the network. In IP networks running the OSPF or IS-IS protocols, routing is over shortest paths, and forwarding mechanisms are constrained to distributing traffic uniformly over equal cost shortest paths. These constraints often make achieving an optimal distribution of traffic impossible. In this paper, we propose and evaluate an approach, based on manipulating the set of next hops for routing prefixes, that is capable of realizing near optimal traffic distribution without any change to existing routing protocols and forwarding mechanisms. In addition, we explore the tradeoff that exists between performance and the overhead associated with the additional configuration steps that our solution requires. The paper's contributions are in formulating and evaluating an approach to traffic engineering for existing IP networks that achieves performance levels c...

Link-State Routing with Hop-by-Hop Forwarding Can Achieve Optimal Traffic Engineering

“…Furthermore, while it is true that, from the solution of the COMMODITY problem, a set of link weights can be computed such that all the commodity flow will be forwarded along the shortest paths [3], [5], the flow-splitting ratios among these shortest paths are not related to the link weights, forcing the operator to specify up to O(NE) additional parameters (one parameter on each link for each destination) as the flowsplitting ratios for all the routers.…”

“…However, optimality then comes with a cost for establishing many end-to-end tunnels to forward packets. Second, other studies explored more flexible ways to split traffic over shortest paths [3], [5], but these solutions do not enable routers to independently compute the flow-splitting ratios from link weights. Instead, a central management system must compute and configure the traffic-splitting ratios, and update them when the topology changes, sacrificing the main benefit of running a distributed link-state routing protocol.…”

Traffic distribution over equal-cost-multi-paths

“…Among the four traffic splitting algorithms mentioned above, except Direct Hashing, both equal and unequal traffic splitting can be supported. Based on the assumption that equal traffic splitting is easier to implement (which we tend to disagree), three heuristic algorithms for emulating the unequal traffic splitting by equal traffic splitting algorithms are proposed [5] recently.…”

“…For traffic engineering, the problem of finding the optimal paths for traffic demands is usually solved by formulating it as a linear programming problem [5]. The optimal solution usually requires splitting the traffic demand between two nodes over multiple paths.…”

Cluster-Based Back-Pressure Routing Algorithm

“…Traffic engineering traditionally generates a set of routes between ingress and egress points in the network [8], [22], [19]. However, these are point to point routes and, thus are not always robust to failures or unpredicted changes in traffic loads.…”