A scalable and accurate distributed traffic generator with Fourier transformed distribution over multiple commodity platforms

Ching Hao Chang, Ying-Dar Lin, Yu Kuen Lai*, Yuan Cheng Lai

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

The rapid growth of high-speed computer networks poses a challenge in the design of testing and verification equipment. The hardware-based packet generators that are often used in the verification process are accurate but costly. Software-based packet generators, on the other hand, are relatively low-cost but have a limited performance with low accuracy. This paper proposes a Fourier-based profile decomposition and formulation methodology for a distributed packet generating system, featuring good horizontal scalability and high accuracy. Different from traditional software-based packet generators, this proposed system extracts the traffic components from a specific traffic distribution applying Fourier transformation to generate traffic components. These traffic components are distributed to one or more worker nodes for packet generation, and thus achieving higher aggregated traffic rate in any given distribution. The system design is based on the Data Plane Development Kits (DPDK) framework to maximize the traffic generation performance. The accuracy and performance of the proposed system scale according to the number of worker nodes used. Currently, with multiple CPU cores and five workers, the proposed system can generate aggregated traffic of more than 40 Gbps in a Poisson distribution.

Original languageEnglish
Pages (from-to)102-117
Number of pages16
JournalJournal of Network and Computer Applications
Volume144
DOIs
StatePublished - 15 Oct 2019

Keywords

  • Commercial off-the-shelf packet generator
  • DPDK
  • Fourier transformation
  • Packet generator

Fingerprint Dive into the research topics of 'A scalable and accurate distributed traffic generator with Fourier transformed distribution over multiple commodity platforms'. Together they form a unique fingerprint.

  • Cite this