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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Procedia computer science Jg. 108; S. 2393 - 2397
Hauptverfasser: Inacio, Eduardo C., Barbetta, Pedro A., Dantas, Mario A.R.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 2017
Schlagworte:
experimental design
Parallel file systems
performance variability
statistical analysis
experimental design
Parallel file systems
statistical analysis
performance variability
ISSN:1877-0509, 1877-0509
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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