Load-Balanced IP Fast Failure Recovery

Abstract

Abstract. As a promising approach to improve network reliability, Proactive Failure Recovery (PFR) re-routes data traffic to backup paths without waiting for the completion of routing convergence after a local link failure. However, the diverted traffic may cause congestion on the backup paths if it is not carefully split over multiple paths according to their available capacity. Existing approach assigns new link weights based on links' load and re-calculates the routing paths, which incurs significant computation overhead and is susceptible to route oscillations. In this paper, we propose an efficient scheme for load balancing in PFR. We choose an adequate number of different types of loop-free backup paths for potential failures, and once a failure happens, the affected traffic is diverted to multiple paths in a well balanced manner. We formulate the traffic allocation problem as a tractable linear programming optimization problem, which can be solved iteratively and incrementally. As a result, only the flows affected by the failures are re-allocated to backup paths incrementally without disturbing flows not directly affected by the failures. Simulation results show that our scheme is computationally efficient, can effectively balance link utilization in the network, and can avoid route oscillations.

A New Backup Topology Design Method for Congestion Avoidance in IP Fast Reroute

“…IP Fast Reroute keeps additional routing information in the routers, thus allowing packet forwarding to continue on alternative lin ks immediately after the detection of a failure [1][2][3][4][5], [10][11], [14][15][16][17][18][19][20][21]. IP Fast Reroute routers therefore have mult iple forwarding information bases (FIBs) based on the original topology and backup topologies.…”

“…IP Fast Reroute techniques have been studied for fast failure recovery achieving traffic in just a few milliseconds [1][2][3][4][5], [10][11], [14][15][16][17][18][19][20][21]. For scalability, a backup topology design method for reducing the number of backup topologies is necessary for reducing the router memo ry load [3][4].…”

“…It reroutes data traffic to backup routes without wait ing for the co mp let ion of the routing convergence after a net work failu re [1][2][3][4]. Ho wev er, the rerouted traffic is likely to cause congestion on the backup routes if it is not carefully split among the alternative routes acco rd ing to th eir availab le cap acity [1]. M RC method proposed in [2], computes multip le backup topologies for all possible network failures.…”

A Non-Weighted Load Balanced Fast Local Protection Scheme for IP Networks

“…To our best knowledge, [11] is the first one to consider load balance in IP fast failure recovery. Once a failure occurs, the routers adjacent to a failure divert the affected traffic over multiple backup paths through solving a linear programming problem incrementally.…”

RESISTING: Um Novo Mecanismo de Fast-Reroute com Distribuição de Pacotes em Switches Programáveis P4

“…No entanto, esses trabalhos adotaram uma estratégia primária de recuperac ¸ão que não leva em considerac ¸ão a quantidade de links operacionais no data center. Como resultado, todos os fluxos de pacotes afetados pela falha são redirecionados para um único link backup, o que pode causar uma sobrecarga adicional de tráfego [Zhang et al 2008] e, consequentemente, reduzir a largura de banda efetiva entre servidores. O presente artigo propõe o RESISTING (datacenteR Equally coSt multIpath faSt re-rouTING): um novo mecanismo de FRR integrado com ECMP para switches programáveis em P4 com o propósito de oferecer resiliência, robustez e distribuic ¸ão dos fluxos de pacotes no data center durante os eventos de falhas.…”