AccuPIPE: Accurate Heavy Flow Detection in the Data Plane Using Programmable Switches

Published

April 19, 2020

Author(s)

Yang Guo, Franklin Liu, An Wang, Hang Liu

Abstract

Identifying heavy flows, i.e., flows with high packet rate (or count), is vital for many network applications such as anomaly detection, network operation, quality of service, etc. The task of real-time heavy flow detection in data plane is challenging due to high switching speed (100 Gbps), a large number of concurrent flows (millions of concurrent flows), and small memory footprint requirement. In this paper, we dissect the key factors that affect the existing detection scheme's accuracy, and propose AccuPipe, a new detection scheme with intelligent flow entry replacement strategies. The experiment results show that the new scheme is able to efficiently utilize all flow entries in the detection pipeline, and detects more than 850 heavy flows (out of top 1,000) using a small amount of memory (1,000 flow entries, roughly equivalently to 18KB memory) in a programmable switch, a 70% improvement over the existing scheme. In addition, we investigate the performance of the proposed scheme with varying flow entry replacement strategies, and report their pros and cons.

Conference Dates

April 20-24, 2020

Conference Location

Budapest, HU

Conference Title

IEEE/IFIP Network Operations and Management

Pub Type

Conferences

Keywords

Heavy Flow Detection, Network Measurement, Programmable Switch, Software Defined Networking

Citation

Guo, Y. , Liu, F. , Wang, A. and Liu, H. (2020), AccuPIPE: Accurate Heavy Flow Detection in the Data Plane Using Programmable Switches, IEEE/IFIP Network Operations and Management, Budapest, HU (Accessed April 28, 2026)

Additional citation formats