A Methodology for Clock Benchmarking

Julien Ridoux; Darryl Veitch

3rd International ICST Conference on Testbeds and Research Infrastructures for the Development of Networks and Communities (TridentCom)

Research Article

A Methodology for Clock Benchmarking

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1109/TRIDENTCOM.2007.4444689,
    author={Julien Ridoux and Darryl Veitch},
    title={A Methodology for Clock Benchmarking},
    proceedings={3rd International ICST Conference on Testbeds and Research Infrastructures for the Development of Networks and Communities (TridentCom)},
    publisher={IEEE},
    proceedings_a={TRIDENTCOM},
    year={2008},
    month={2},
    keywords={},
    doi={10.1109/TRIDENTCOM.2007.4444689}
}

Julien Ridoux
Darryl Veitch
Year: 2008
A Methodology for Clock Benchmarking
TRIDENTCOM
IEEE
DOI: 10.1109/TRIDENTCOM.2007.4444689

Julien Ridoux¹^,*, Darryl Veitch¹^,*

1: ARC Special Research Center for Ultra-Broadband Information Networks (CUBIN), An affiliated program of National ICT Australia, EEE Department, The University of Melbourne, Australia

*Contact email: j.ridoux@ee.unimelb.edu.au, d.veitch@ee.unimelb.edu.au

Abstract

Accurate timestamping is a basic need in traffic monitoring as well as distributed computing in the broad sense, and is destined to become increasingly important as network latency becomes a hard barrier to improved performance across networks. Software clocks need to be improved to meet this challenge, however evaluating their performance is non trivial, as they are imbedded inside computing systems. We present a methodology for clock validation which allows many of the difficult problems to be resolved. Our method involves a combination of external and internal validation strategies, and makes use of GPS synchronized DAG cards and system clocks. We illustrate in detail how it may be applied using real data collected from 3 clocks implemented in UNIX PCs.

Published: 2008-02-01
Publisher: IEEE
Modified: 2010-05-16

: http://dx.doi.org/10.1109/TRIDENTCOM.2007.4444689