期刊文献+

基于工作负载感知的固态硬盘阵列系统的架构设计与研究 被引量:1

Research of SSD Array Architecture Based on Workload Awareness
下载PDF
导出
摘要 在RAID-0阵列中设计了一种基于冷热数据分离存储的固态硬盘阵列系统架构HA-RAID,并结合滑动窗口技术进行优化.其主要思想是,利用固定长度的滑动窗口将阵列系统中的盘划分为普通盘和热点盘,热点盘专门存放热数据,普通盘存放普通数据,且阵列中各盘的角色随着滑动窗口的移动而不断变化.在8块商用固态硬盘组成的RAID-0阵列系统上对HA-RAID予以实验分析.实验结果表明,相比于未引入冷热数据分离机制的原始RAID-0做法,HA-RAID可以将热数据相对均匀地存储到各个盘上,很好地实现了阵列系统级的负载和磨损均衡,从而将阵列中热点盘出现的比例降低到几乎为0.在真实的企业级工作负载下,相比原始RAID-0,HA-RAID减少12.01%~41.06%的平均响应时间,很好地实现了阵列系统级的I/O性能提升. The fixed data layout of traditional array system and the locality of workloads cause the partial disks of the array system to become hot disks,which affects the reliability and the overall concurrency performance of the array system.This paper proposes a new RAID architecture for SSD array systems,HA-RAID,which leverages hot cold data separation and sliding window techniques.The main idea is that HA-RAID divides the disk array into hot disks and ordinary disks,which stores hot data on hot disks and cold data on ordinary disks,and it changes the role of each disk dynamically by moving a fixed-length sliding window.So,each disk has the opportunity to become a hot disk and stores hot data which achieves the purpose of storing hot data evenly on each disk.Experiments under real-world workloads on a RAID-0 array system composed of eight commercial SSDs show that HA-RAID can achieve an even distribution of hot data across all disks and reduce the percentage of hot disks appearing in the array to almost zero.This implies that HA-RAID achieves load balance and wear balance at the device level.In terms of performance,HA-RAID reduces the average response time by 12.01%~41.06% which achieves the I/O performance enhancement,compared with traditional RAID-0 array.
作者 张强 梁杰 许胤龙 李永坤 Zhang Qiang;Liang Jie;Xu Yinlong;Li Yongkun(School of Computer Science and Technology,University of Science and Technology of China,Hefei 230026;Anhui Province Key Laboratory of High Performance Computing(University of Science and Technology of China),Hefei 230026)
出处 《计算机研究与发展》 EI CSCD 北大核心 2019年第4期755-766,共12页 Journal of Computer Research and Development
关键词 SSD阵列架构设计 冷热数据区分 RAID-0 负载均衡 响应时间 SSD array architecture design cold and hot data identification RAID -0 load balance response time
  • 相关文献

参考文献1

二级参考文献11

  • 1CHEN Zhi-guang, XIAO Nong, LIU Fang, etal. Hot data-awm'e FTL based on page-level address mapping[ C ]//Proc of the 12th International Conference on High Performance Computiag and Communications. Washington DC: /EEE Computer Society,2010: 713-718.
  • 2PARK J S, KIM H S, CHUNG K S, et al. PRAM and NAND flash hybrid architecture based on hot data detection[ C]//Proc of the 2nd International Conference on Mechanical and Electronics Engineering. 2010:93-97.
  • 3KUMAR V, PRABHU N, CHRYSANTHIS P K. HDC: hot data caching in mobile database systems[ C]//Proc of ACS/IEEE International Conference on Computer Systems and Applications. Washington DC: IEEE Computer Society,2005:37-44.
  • 4LEE H S, YUN H S, LEE D H. HFTL: hybrid flash translation layer based on hot data identification for flash memory[ J]. IEEE Trans on Consumer Eloctronlcs ,2009,55 (4) :2005- 2011.
  • 5CHANG Li-pin, KUO Tei-wei. An adaptive striping architecture for flash memory storage systems of embedded systems[ C ]//Proc of the 8th Real-Time and Embedded Technology and Applications Symposium. Washington DC: IEEE Computer Society,2002:187-196.
  • 6HSIEH J W, KUO Tei-wei, CHANG Li-pin. Efficient Identification ofhot data for flash memory storage systems[ J]. ACM Trans on Sotorage,2006,2(1):22-40.
  • 7WU C H, CHANG W Y, HONG Zen-wei. A reliable non.yolatilo memory system: exploiting file-system characteristics[ C]//Pmc:of the 15th IEEE Pacific Rim International Symposium on Dependable Computing. 2009:202- 207.
  • 8CHANG Li-pin, KUO Tei-wei. Efficient management for large-scale flash memory storage systems with resource conservation [ J ]. AGM Trans on Storage,2005,1 (4) :381-418.
  • 9CHANG Li-pin, KUO Tei-wei. An efficient management scheme for large-scale flash memory storage systems[ C]//Proc of ACM Symposium on Applied Computing. New YOrk: ACM Press,2004:862-868.
  • 10LIM S P, LEE S W,MOON B. FASTer FTL for enterprise-class flash memory SSDs [ C ]//Proc of International Workshop on Storage Net work Architecture and Parallel I/Os. 2010:3-12.

同被引文献17

引证文献1

二级引证文献7

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