A Statistical Analysis of the Performance Variability of Read/Write Operations on Parallel File Systems
A Statistical Analysis of the Performance Variability of Read/Write Operations on Parallel File Systems
复制标题
并行文件系统读/写操作性能变化的统计分析
DOI：
10.1016/j.procs.2017.05.026
复制
发表时间：
2017
影响因子：
11.4
通讯作者：
M. Dantas
中科院分区：
文献类型：
--
作者：
E. C. Inacio;P. A. Barbetta;M. Dantas
本文报告了一个统计分析的性能变化的读和写操作的并行文件系统。为了正确解释固有的系统变异性并获得统计学显著性结果，本研究采用了正式的实验设计和分析方法。这项研究表明，在评估的条件下，六个影响占主导地位的I/O时间，响应99.32%的性能变化。此外，传统上在I/O优化建议中探索的一些因素在本研究中没有统计学证据表明有显著影响。此外，高层次的影响，确定了一套统计上显着的因素的解释，提供了一个案例，在这个问题上的进一步研究。
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.