Abstract

Recent literature has proved that stable dynamic routing algorithms have solid theoretical foundation that makes them suitable to be implemented in a real protocol, and used in practice in many different operational network contexts. Such algorithms inherit much of the properties of congestion controllers implementing one of the possible combination of AQM/ECN schemes at nodes and flow control at sources. In this paper we propose a linear program formulation of the multi-commodity flow problem with congestion control, under max-min fairness, comprising demands with or without exogenous peak rates. Our evaluations of the gain, using path diversity, in scenarios as intra-domain traffic engineering and wireless mesh networks encourages real implementations, especially in presence of hot spots demands and non uniform traffic matrices. We propose a flow aware perspective of the subject by using a natural multi-path extension to current congestion controllers and show its performance with respect to current proposals. Since flow aware architectures exploiting path diversity are feasible, scalable, robust and nearly optimal in presence of flows with exogenous peak rates, we claim that our solution rethinked in the context of realistic traffic assumptions performs as better as an optimal approach with all the additional benefits of the flow aware paradigm. Document type: Report

Abstract

In this paper, we propose an AIMD-based TCP load balancing architecture in a backbone network where TCP flows are split between two explicitly routed paths, namely the primary and the secondary paths. We propose that primary paths have strict priority over the secondary paths with respect to packet forwarding and both paths are rate-controlled using ECN marking in the core and AIMD rate adjustment at the ingress nodes. We call this technique "prioritized AIMD". The buffers maintained at the ingress nodes for the two alternative paths help us predict the delay difference between the two paths which forms the basis for deciding on which path to forward a new-coming flow. We provide a simulation study for a large mesh network to demonstrate the efficiency of the proposed approach in terms of the average per-flow goodput and byte blocking rates. © Springer-Verlag Berlin Heidelberg 2004.

Abstract

Cataloged from PDF version of article. In this thesis, we propose a multi-path TCP load balancing traffic engineering methodology in IP networks. In this architecture, TCP traffic is split at the flow level between the primary and secondary paths in order to prevent the adverse effect of packet reordering on TCP performance occuring in packet-based load balancing schemes. Traffic splitting is done by using a random early rerouting algorithm that controls the queuing delay difference between the two alternative paths. We apply strict priority queuing in order to prevent the knock-on effect that arises when primary and secondary path queues have equal priority. Probe packets are used for getting congestion information from the output queues of links along the paths and AIMD (Additive Increase/Multiplicative Decrease) based rate control using this congestion information is applied to the traffic routed over these paths. We compare two queuing architectures, namely first-in-first-out (FIFO) and strict priority. We show through simulations that strict priority queuing has higher performance, it is relatively more robust than FIFO queuing and it eliminates the knock-on effect. We show that avoiding packet reordering by flow level splitting significantly improves the performance of long flows. The capabilities of ns-2 simulator is improved bu using optimizations in order to apply the simulator to relatively large networks. We show that incorporating a-priori knowledge of the traffic demand matrix into the proposed architecture can further improve its performance in terms of load balancing and byte rejection ratio. Alparslan, Onur M.S.