Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2014, Vol. 15 Issue (8): 607-621    DOI: 10.1631/jzus.C1300314
    
基于固态硬盘能耗和性能的最优文件系统和I/O调度策略组合
Hui Sun, Xiao Qin, Chang-sheng Xie
National Laboratory for Optoelectronics and School of Science and Technology Huazhong University of Science and Technology, Wuhan 430074, China; Department of Computer Science and Software Engineering, Auburn University, Auburn, AL 36849, USA
Exploring optimal combination of a file system and an I/O scheduler for underlying solid state disks
Hui Sun, Xiao Qin, Chang-sheng Xie
National Laboratory for Optoelectronics and School of Science and Technology Huazhong University of Science and Technology, Wuhan 430074, China; Department of Computer Science and Software Engineering, Auburn University, Auburn, AL 36849, USA
 全文: PDF 
摘要: 研究目的:负载下,不同文件系统和I/O调度策略对固态盘性能和能耗的影响较大。本文介绍固态盘性能和能耗综合最优情形下,系统文件系统和I/O调度策略配置的理论依据和实现方法。
创新要点:引入一种综合评测指标(aggregativeindicator,简写为AI),AI的数值等于固态盘性能和能耗的比值。同等负载环境下,对于不同文件系统和I/O调度策略,AI值越大,固态盘越趋于性能和能耗综合最优,即文件系统和I/O调度策略对负载下固态盘性能和能耗的影响越小;反之,影响越大。
方法提亮:以常见的五种文件系统(Ext2、Ext3、NILFS2、ReiserFS和XFS)和三种I/O调度策略(CFQ、Deadline和NOOP)为例。文件系统测试工具采用Filebench作为负载发生器,仿真了Varmail,Fileserver和Webserver三种负载,并将这三种负载分别加载到三种测试盘上,采用综合指标(AI)研究使固态盘性能和能耗达到综合最优的文件系统和I/O调度策略组合,并分析特定盘在最优AI值下的性能和能耗变化趋势。
实验结果:基于Varmail负载(以随机读和附加写文件操作为主)的实验结果表明,任意一种I/O调度策略下,基于扩展文件系统(Ext2或Ext3)的测试盘AI值较大;基于Fileserver负载(以随机读和随机写文件操作为主)的实验结果表明,任意一种I/O调度策略下,基于NILFS2文件系统的测试盘AI值较大;基于Webserver负载(以大量随机读文件操作为主)的实验结果表明,基于扩展文件系统(Ext2或Ext3)和CFQI/O调度策略组合下的测试盘AI值较大。对于扩展文件系统(Ext2和Ext3)而言,因Ext2文件系统无日志写操作,大多数情况下,基于Ext2文件系统的固态盘能耗较低,但Ext2文件系统安全性比Ext3差。NIFLS2文件系统利用日志文件管理顺序化随机访问模式的文件操作,因此随机负载下基于NIFLS2文件系统的固态盘AI值较大。大多数情况下,基于CFQ和NOOP调度策略的固态盘AI值较大。
重要结论:不同负载下,固态盘的性能和能耗很大程度上取决于测试系统的文件系统和I/O调度策略组合。
关键词: 固态盘文件系统I/O调度策略综合评测指标性能和能耗变化趋势    
Abstract: Performance and energy consumption of a solid state disk (SSD) highly depend on file systems and I/O schedulers in operating systems. To find an optimal combination of a file system and an I/O scheduler for SSDs, we use a metric called the aggregative indicator (AI), which is the ratio of SSD performance value (e.g., data transfer rate in MB/s or throughput in IOPS) to that of energy consumption for an SSD. This metric aims to evaluate SSD performance per energy consumption and to study the SSD which delivers high performance at low energy consumption in a combination of a file system and an I/O scheduler. We also propose a metric called Cemp to study the changes of energy consumption and mean performance for an Intel SSD (SSD-I) when it provides the largest AI, lowest power, and highest performance, respectively. Using Cemp, we attempt to find the combination of a file system and an I/O scheduler to make SSD-I deliver a smooth change in energy consumption. We employ Filebench as a workload generator to simulate a wide range of workloads (i.e., varmail, fileserver, and webserver), and explore optimal combinations of file systems and I/O schedulers (i.e., optimal values of AI) for tested SSDs under different workloads. Experimental results reveal that the proposed aggregative indicator is comprehensive for exploring the optimal combination of a file system and an I/O scheduler for SSDs, compared with an individual metric.
Key words: Solid state disk (SSD)    Performance    Energy consumption    File system    I/O scheduler
收稿日期: 2013-10-29 出版日期: 2014-08-06
CLC:  TP316  
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
Hui Sun
Xiao Qin
Chang-sheng Xie

引用本文:

Hui Sun, Xiao Qin, Chang-sheng Xie. Exploring optimal combination of a file system and an I/O scheduler for underlying solid state disks. Front. Inform. Technol. Electron. Eng., 2014, 15(8): 607-621.

链接本文:

http://www.zjujournals.com/xueshu/fitee/CN/10.1631/jzus.C1300314        http://www.zjujournals.com/xueshu/fitee/CN/Y2014/V15/I8/607

[1] Osama A. Khashan, Abdullah M. Zin, Elankovan A. Sundararajan. ImgFS:一种利用用户空间文件系统的图片存储透明加密技术[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(1): 28-42.
[2] Hong-yan Li, Nai-xue Xiong, Ping Huang, Chao Gui. PASS:一种简单、高效、并行感知的固态盘I/O调度器[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(5): 321-336.