SpinTrap: Catching Speeding QUIC Flows
Ike Kunze, Constantin Sander, Lars Tissen, Benedikt Bode, Klaus Wehrle · 2024
The resilience of the Internet to high traffic loads fundamentally relies on hosts responding to congestion, i.e., that they back off when the network is overloaded. Despite the corresponding wide-spread deployment of congestion control, unresponsive hosts still represent a danger and can wipe out all benefits of modern congestion management approaches, such as L4S. Hence, identifying (and isolating) unresponsive flows can contribute to improving the Internet’s resilience. Yet, existing approaches only provide broad or probabilistic solutions which become inapplicable with QUIC or also harm benign traffic.In this paper, we propose SpinTrap, a speed trap for Internet flows designed to identify unresponsive traffic. Leveraging the QUIC spin bit, SpinTrap first monitors the sending behavior of QUIC flows before assessing their congestion responsiveness by checking for reduced sending rates as reaction to congestion signals (packet loss and ECN markings). Evaluating our eBPF prototype, we show that SpinTrap can accurately track the sending rates and assess the responsiveness of QUIC traffic, singling out flows that do not react to congestion. As such, SpinTrap provides a novel building block for Internet congestion management that can help in improving the Internet’s resilience.