期刊文献+

基于I/O空闲率的硬盘功耗建模与评估方法研究

Disk power module and evaluation based on I/O idle rate
下载PDF
导出
摘要 存储设备的功耗在整个计算机系统尤其是数据中心所占的比例已经越来越大。要进行硬盘功耗优化,在缺少硬件直接测量硬盘功耗的情况下就需要对硬盘功耗进行建模。现代操作系统通过文件系统层进行硬盘I/O操作管理,并提供实时监控数据。通过对EXT2、EXT4和NILFS2等常用文件系统的硬盘I/O过程进行实验分析,发现不同的文件系统对硬盘功耗具有不同的影响,为了刻画这种差异性,提出基于I/O空闲率的硬盘功耗建模与评估方法。同时使用I/O空闲率来指导硬盘进行功耗优化,将视频播放器的I/O空闲率由4.79%提高到96.55%,硬盘的功耗降低45.28%。 Storage is consuming more and more energy in computer, especially in data center. In order to reduce disk power, it needs to establish the disk power module when there no hardware to measure the power. Modern operating system uses file systems to manage I/O and provide real-time monitoring data. This paper analyzes the I/O processing of EXT2, EXT4 and NILFS2 file systems, and discovers that different file systems have different influence on disk power. This paper presents I/O idle rate to depict the difference, more specifically, proposes the disk power module and evaluates method by using I/O idle rate. This paper also uses I/O idle rate to reduce disk power, when improving the I/O idle rate of video from 4.79%to 96.55, reducing the disk power 45.28%.
出处 《计算机工程与应用》 CSCD 2014年第10期216-220,共5页 Computer Engineering and Applications
基金 国家自然科学基金(No.61272131 No.61202053) 江苏省自然科学基金(No.SBK201240198) 江苏省产学研前瞻性联合研究项目(No.BY2009128)
关键词 文件系统 功耗模型 I O空闲率 功耗优化 file system power module I/O idle rate power optimization
  • 相关文献

参考文献21

  • 1ENERGY STAR^* Version 5.0 system implementation[EB/OL]. (2009) .Available : http ://www.intel.com/Assets/PDF/white- paper/321556.pdf.
  • 2Schulz G.Storage industry trends and it infrastructure re- source management (irm) [Z].2007.
  • 3Zedlewski J,Sobit S,Gang N.Modeling hard-disk power consumption[C]//Proceedings of the 2nd USENIX Con- ference on File and Storage Technologies,2003,28.
  • 4Huang Hai, Hung Wanda, Shin K G.FS2 : dynamic data repli- cation in free disk space for improving disk performance and energy consumption[J].ACM SIGOPS Operating Systems Review, 2005,39(5) : 263-276.
  • 5Buccy J S, Ganger G R.The DiskSim simulation envi- ronment version 4.0 reference manual(CMU-PDL-08-101 )[R]. Parallel Data Laboratory, 2008.
  • 6Zheng Fengzhou.Considering the energy consumption of mobile storage alternatives[C]//11th IEEE/ACM Interna- tional Symposium on Modeling, Analysis and Simulation of Computer Telecommunications Systems.[S.l.] : IEEE, 2003.
  • 7Suzanne R, Ranganathan P, Kozyrakis C.A comparison of high-level full-system power models[C]//Proceedings of the 2008 Conference on Power Aware Computing and Systems. [S.l.] : USENIX Association, 2008.
  • 8Zeng Heng.ECOSystem:managing energy as a first class operating system resource[J].ACM SIGPLAN Notices, 2002,37(10).
  • 9Aman K.Virtual machine power metering and provisioning[C]// Proceedings of the 1st ACM Symposium on Cloud Com- puting. [S.l.] : ACM, 2010.
  • 10Abhinav P,Hu Y C,Zhang Ming.Where is the energy spent inside my app?: fine grained energy accounting on smartphones with eprof[C]//Proceedings of the 7th ACM European Conference on Computer Systems.[S.l.]:ACM, 2012.

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部