BBRv2+:Towards Balancing Aggressiveness and Fairness with Delay-based Bandwidth Probing

TL;DR

BBRv2+ enhances Google's BBRv2 congestion control by balancing aggressiveness and fairness through delay-based probing, improving throughput and resilience in diverse network conditions.

Contribution

Introduces BBRv2+ with delay-aware mechanisms to improve responsiveness and loss resilience without sacrificing fairness or throughput.

Findings

BBRv2+ achieves 25% higher throughput in high-mobility networks.

BBRv2+ maintains comparable queuing delay to BBRv2.

BBRv2+ effectively balances fairness, responsiveness, and loss resilience.

Abstract

BBRv2, proposed by Google, aims at addressing BBR's shortcomings of unfairness against loss-based congestion control algorithms (CCAs) and excessive retransmissions in shallow-buffered networks. In this paper, we first comprehensively study BBRv2's performance under various network conditions and show that BBRv2 mitigates the shortcomings of BBR. Nevertheless, BBRv2's benefits come with several costs, including the slow responsiveness to bandwidth dynamics as well as the low resilience to random losses. We then propose BBRv2+ to address BBRv2's performance issues without sacrificing its advantages over BBR. To this end, BBRv2+ incorporates delay information into its path model, which cautiously guides the aggressiveness of its bandwidth probing to not reduce its fairness against loss-based CCAs. BBRv2+ also integrates mechanisms for improved resilience to random losses as well as network jitters. Extensive experiments demonstrate the effectiveness of BBRv2+. Especially, it achieves 25% higher throughput and comparable queuing delay in comparison with BBRv2 in high-mobility network scenarios.