Continuous Flow Measurement with SuperFlow

Zongyi Zhao1; Xingang Shi1; Arpit Gupta2; Qing Li3; Zhiliang Wang1; Bin Xiong1; Xia Yin1

10.1109/IWQOS52092.2021.9521284

2021

1548-615X

978-1-6654-3054-8

2021 IEEE/ACM 29th International Symposium on Quality of Service (IWQOS)

1-6

25-28 June 2021

Tokyo, Japan

Flow-based network measurement enables operators to perform a wide range of network management tasks in a scalable manner. Recently, various algorithms have been proposed for flow record collection at very high speed. However, they all focus on processing traffic in a short time window, but overlook the fact that flow measurements are typically needed continuously for unlimited time. To this end, we propose a new algorithm named SuperFlow to support continuous and accurate flow record collection at very high speed by monitoring the flow activeness and exporting the inactive records from the data plane automatically. Our data structures and the corresponding algorithms are carefully designed and analyzed, so the above goal is achieved with limited memory and bandwidth consumption. We implement SuperFlow on both x86 CPU and state-of-the-art PISA target. Comprehensive experiments show that SuperFlow consistently outperforms its competitors significantly. Especially, compared with the best competitor, it records around 136.7% more flows, reduces the error in flow size estimation by 51.5%, and reduces the memory or bandwidth consumption by up to 71.0%, while bringing only negligible throughput degradation.

Degradation Memory management Estimation Bandwidth Quality of service Data structures Throughput

其他

CPCI-S ; EI

WOS:000709411600024

IEEE

1.Tsinghua University
2.UC Santa Barbara
3.Southern University of Science and Technology

Zongyi Zhao,Xingang Shi,Arpit Gupta,et al. Continuous Flow Measurement with SuperFlow[C],2021:1-6.