A Performance Evaluation of TCP BBRv2 Alpha

A Performance Evaluation of TCP BBRv2 Alpha
复制标题

DOI:
10.1109/tsp49548.2020.9163512
复制
发表时间:
2020-07
期刊:
2020 43rd International Conference on Telecommunications and Signal Processing (TSP)
影响因子:
--
通讯作者:
Jose Gomez;Elie F. Kfoury;J. Crichigno;E. Bou-Harb;Gautam Srivastava
Jose Gomez;Elie F. Kfoury;J. Crichigno;E. Bou-Harb;Gautam Srivastava
中科院分区:
其他
文献类型:
--
作者:
Jose Gomez;Elie F. Kfoury;J. Crichigno;E. Bou-Harb;Gautam Srivastava

文献摘要

被引文献

相似文献

瓶颈带宽和往返时间版本2(BBRv 2)的alpha版本最近已经发布,其目的是减轻其前身BBR版本1(BBRv 1)的缺点。以往的研究表明,BBRv 1提供了一个高的链路利用率和低排队延迟,通过估计可用的瓶颈带宽。然而,当流i)使用不同的拥塞控制算法(诸如CUBIC),以及ii)具有不同的往返时间(RTT)时,其侵略性引起不公平。本文介绍了一个实验评估BBRv 2,使用Mininet。结果表明,BBRv 2-CUBIC之间的共存是增强相对于BBRv 1-CUBIC,作为衡量的公平性指数。他们还表明,BBRv 2减轻了在BBRv 1中观察到的RTT不公平问题。此外,当网络条件(如带宽和延迟)动态变化时,BBRv 2比其前身实现了更好的带宽公平共享。结果还表明,当使用BBRv 2时,并发流的平均流完成时间减少。
The alpha version of Bottleneck Bandwidth and Round-trip Time version 2 (BBRv2) has been recently presented, which aims to mitigate the shortcomings of its predecessor, BBR version 1 (BBRv1). Previous studies show that BBRv1 provides a high link utilization and low queuing delay by estimating the available bottleneck bandwidth. However, its aggressiveness induces unfairness when flows i) use different congestion control algorithms, such as CUBIC, and ii) have distinct round-trip times (RTTs). This paper presents an experimental evaluation of BBRv2, using Mininet. Results show that the coexistence between BBRv2-CUBIC is enhanced with respect to that of BBRv1-CUBIC, as measured by the fairness index. They also show that BBRv2 mitigates the RTT unfairness problem observed in BBRv1. Additionally, BBRv2 achieves a better fair share of the bandwidth than its predecessor when network conditions such as bandwidth and latency dynamically change. Results also indicate that the average flow completion time of concurrent flows is reduced when BBRv2 is used.