A Statistical Analysis of the Performance Variability of Read/Write Operations on Parallel File Systems

This paper reports a statistical analysis about the performance variability of read and write operations on parallel file systems. To properly account for the inherent system variability and to obtain statistically significant results, formal experimental design and analysis methods were employed in...

Full description

Saved in:
Bibliographic Details
Published in:Procedia computer science Vol. 108; pp. 2393 - 2397
Main Authors: Inacio, Eduardo C., Barbetta, Pedro A., Dantas, Mario A.R.
Format: Journal Article
Language:English
Published: Elsevier B.V 2017
Subjects:
experimental design
Parallel file systems
performance variability
statistical analysis
experimental design
Parallel file systems
statistical analysis
performance variability
ISSN:1877-0509, 1877-0509
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper reports a statistical analysis about the performance variability of read and write operations on parallel file systems. To properly account for the inherent system variability and to obtain statistically significant results, formal experimental design and analysis methods were employed in this study. This research reveals that in the evaluated conditions six effects dominate I/O time, responding for 99.32% of the performance variability. Further, some factors traditionally explored in I/O optimization proposals presented no statistical evidence of significant effects in this study. Moreover, high-level effects were identified by the interpretation of the set of statistically significant factors, providing a case for further research in the subject.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2017.05.026