Toward a practical approach for BGP stability with root cause check

Abstract

The instability issues of the Border Gateway Protocol (BGP), such as route oscillations and path explorations, can decrease the performance of packet forwarding and place heavy workload on routers. While BGP instability has been extensively studied, existing solutions mainly solve individual instances of BGP instability. Thus, with the existing solutions, the route selection processes of ASes or routers may not realize the actual root cause of BGP instability and hence cannot effectively solve the BGP instability problem. In this paper, we propose a simple, integrated solution called stable BGP <i>(stableBGP)</i> that practically solve a general class of BGP instability issues, including route oscillations and path explorations. stableBGP seeks to adapt the route selection process to best address the root cause of route changes so that the route selection process can quickly stabilize. We formally prove that stableBGP can achieve BGP stability. Extensive simulation results show that in the link failure scenario, stableBGP significantly reduces the number of route changes, the convergence time, and the number of route update messages when compared to prior solutions. We also analyze the performance of stableBGP when it is partially deployed. Our work provides insights into developing a practical solution that addresses the BGP instability problem.