Share Email Print

Proceedings Paper

Massive data processing on the Acxiom cluster testbed
Author(s): Amy W. Apon; Pawel Dominik Wolinski; Dennis Alan Reed; Greg M. Amerson; Prathima Gorjala
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The Acxiom Cluster Testbed is a high-performance, low-cost cluster that is being constructed at the University of Arkansas for the purpose of designing, constructing, and evaluating cluster architectures for massive data processing. Our evaluation efforts include performance testing of cluster hardware and a variety of middleware configurations for the cluster. One of the most important middleware components for massive data processing is a high-performance cluster file system. In this paper we present system requirements for a parallel cluster-based file system, our experimental evaluation of the NFS file system and the PVFS parallel file system for Linux, and future research goals.

Paper Details

Date Published: 27 July 2001
PDF: 12 pages
Proc. SPIE 4528, Commercial Applications for High-Performance Computing, (27 July 2001); doi: 10.1117/12.434867
Show Author Affiliations
Amy W. Apon, Univ. of Arkansas (United States)
Pawel Dominik Wolinski, Univ. of Arkansas (United States)
Dennis Alan Reed, Univ. of Arkansas (United States)
Greg M. Amerson, Univ. of Arkansas (United States)
Prathima Gorjala, Univ. of Arkansas (United States)

Published in SPIE Proceedings Vol. 4528:
Commercial Applications for High-Performance Computing
Howard Jay Siegel, Editor(s)

© SPIE. Terms of Use
Back to Top