Skip to main content
QUICK REVIEW

[论文解读] Leveraging Coupled BBR and Adaptive Packet Scheduling to Boost MPTCP

Jiangping Han, Yitao Xing|arXiv (Cornell University)|Feb 15, 2020
Network Traffic and Congestion Control参考文献 49被引用 6
一句话总结

本文提出耦合BBR与AR&P调度器,以提升在丢包率高且动态变化的无线网络中的MPTCP性能。通过采用基于带宽的拥塞控制与自适应、预测性分组调度,该方案在复杂网络条件下实现了更高的吞吐量、与TCP BBR更优的公平性,以及更少的乱序分组。

ABSTRACT

Quite a few algorithms have been proposed to optimize the transmission performance of Multipath TCP (MPTCP). However, existing MPTCP protocols are still far from satisfactory in lossy and ever-changing networks because of their loss-based congestion control and the difficulty of managing multiple subflows. Recently, a congestion-based congestion control, BBR, is proposed to promote TCP transmission performance through better use of bandwidth. Due to the superior performance of BBR, we try to boost MPTCP with it. For this propose, coupled congestion control should be redesigned for MPTCP, and a functional scheduler able to effectively make use of the characteristics of BBR must also be developed for better performance. In this paper, we first propose Coupled BBR as a coupled congestion control algorithm for MPTCP to achieve high throughput and stable sending rate in lossy network scenarios with guaranteed fairness with TCP BBR flows and balanced congestion. Then, to further improve the performance, we propose an Adaptively Redundant and Packet-by-Packet (AR\&P) scheduler, which includes two scheduling methods to improve adaptability in highly dynamic network scenarios and keep in-order packet delivery in asymmetric networks. Based on Linux kernel implementation and experiments in both testbed and real network scenarios, we show that the proposed scheme not only provides higher throughput, but also improves robustness and reduces out-of-order packets in some harsh circumstances.

研究动机与目标

  • 解决MPTCP在丢包率高且高度动态的无线网络中因基于丢包的拥塞控制与固定调度器而导致的性能低下问题。
  • 通过确保MPTCP聚合吞吐量不超过最佳路径上单路径TCP流的吞吐量,实现MPTCP与单路径TCP BBR流之间的公平性。
  • 通过一种新颖的自适应与预测性分组调度机制,提升在不对称且快速变化的网络条件下的鲁棒性与适应性。
  • 在保持高带宽利用率和低延迟的同时,实现MPTCP子流之间的负载均衡。

提出的方法

  • 提出耦合BBR,一种基于BBR的拥塞控制算法改进版本,通过测量所有子流的聚合带宽来设定各子流的发送速率,确保与单路径TCP BBR的公平性。
  • 引入基于实时带宽测量的数据分配速率,以平衡子流间的拥塞,防止不公平的子流利用。
  • 设计AR&P调度器,包含两个组件:自适应冗余调度(AR-Scheduling),可动态在低带宽子流上发送冗余分组,以提升吞吐量并降低延迟。
  • 集成预测性分组调度(P-Scheduling),根据预期交付顺序和RTT对分组进行优先级排序,最大限度减少在不对称网络中的乱序交付。
  • 通过实时路径状态监控指导冗余决策,确保在动态环境中的适应性。
  • 在Linux内核中实现该方案,并在测试平台与真实无线场景中进行评估。

实验结果

研究问题

  • RQ1基于BBR的拥塞控制机制是否能在丢包率高的无线网络中,相比传统基于丢包的算法,提升MPTCP性能?
  • RQ2MPTCP如何在保持高吞吐量和子流间负载均衡的同时,实现与单路径TCP BBR流的公平性?
  • RQ3自适应且预测性的分组调度器是否能减少在不对称和动态网络条件下的乱序分组交付并改善延迟?
  • RQ4耦合BBR与AR&P调度器的组合在真实无线部署中,能在多大程度上提升MPTCP的鲁棒性与吞吐量?

主要发现

  • 所提出的耦合BBR通过将MPTCP聚合吞吐量限制在最佳路径上单路径TCP流的水平,实现了高带宽利用率,并与单路径TCP BBR流保持公平性。
  • 耦合BBR通过基于实时带宽测量动态调整发送速率,确保子流间拥塞均衡,避免子流利用不公。
  • AR&P调度器通过根据路径条件智能调度冗余与预测性分组,在不对称和动态网络中显著减少了乱序分组的交付。
  • 在真实世界与测试平台实验中,该组合方案相比现有MPTCP变体实现了更高的吞吐量和更低的延迟,尤其在高丢包率与快速链路变化条件下表现更优。
  • 该方案在恶劣网络条件下表现出强大的鲁棒性,即使在个别子流严重退化时也能维持稳定性能。
  • Linux内核实现验证了该方案在真实系统中部署的可行性与实用性。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。