Heavy-Hitter Detection Entirely in the Data Plane
By Vibhaalakshmi Sivaraman, Srinivas Narayana, Ori Rottenstreich, S. Muthu Muthukrishnan, Jennifer Rexford. ACM SIGCOMM Symposium on Software Defined Networking Research, 2016
475 citations recorded by the source corpus.
Identifying the "heavy hitter" flows or flows with large traffic volumes in the data plane is important for several applications e.g., flow-size aware routing, DoS detection, and traffic engineering. However, measurement in the data plane is constrained by the need for line-rate processing (at 10-100Gb/s) and limited memory in switching hardware. We propose HashPipe, a heavy hitter detection algorithm using emerging programmable data planes. HashPipe implements a pipeline of hash tables which retain counters for heavy flows while evicting lighter flows over time. We prototype HashPipe in P4 and evaluate it with packet traces from an ISP backbone link and a data center. On the ISP trace (which contains over 400,000 flows), we find that HashPipe identifies 95% of the 300 heaviest flows with less than 80KB of memory.
View Paper: https://www.semanticscholar.org/paper/cd7b4fdd5d945cb3be828cc544f3239e060b802a
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- This paper is included in the Proceedings of the 2022 USENIX Annual Technical Conference. (unknown): “Programmable network devices [1,2] together with domain-specific programming languages ( e.g. P4 [3]) have enabled many in-data-plane (DP) network functions, such as monitoring [4–6], security [7–9], routing [10–12] and so on.”
- Elastic sketch: adaptive and fast network-wide measurements (2018, methodology): “For the other tested algorithms, only Space-Saving (SS) and HashPipe could achieve zero packet loss and perfect accuracy, but in that case, they can only sustain 10Mpps packet rate.”