期刊文献+

一种用磁盘备份SSD的高性能可靠存储系统 被引量:11

A High Performance Reliable Storage System Using HDDs as the Backup of SSDs
下载PDF
导出
摘要 固态盘(solid state drive,SSD)因为其优越的性能已被大量部署于当前的存储系统中.但是,由于寿命有限,SSD的可靠性受到广泛的质疑.磁盘阵列(redundant arrays of inexpensive disk,RAID)是一种传统的用来提高可靠性的手段,但并不适用于SSD.这项工作提出一种基于SSD和磁盘的混合存储系统,构建该系统的主要思想是SSD响应所有I/O请求,从而获得较高的性能;磁盘备份所有数据,从而保证系统的可靠性.但是,磁盘的I/O性能显著低于SSD,构建该系统的问题在于磁盘能否及时地备份SSD上的数据.为了解决这一问题,从两方面提出优化:在延迟方面,采用非易失主存弥补磁盘与SSD的延迟差距;在带宽方面,采用两种措施:1)在单块磁盘内部重组I/O请求,使磁盘尽可能的顺序读写;2)采用多块磁盘备份多块SSD,通过将一块SSD上的写请求分散到多块磁盘上,有效应对单块SSD上出现的突发写请求.通过原型系统实现表明,该混合系统是可行的:磁盘能够为SSD提供实时的数据备份;与其他系统相比,该混合系统取得较高的性价比. SSD (solid state drive) has been widely deployed due to its high performance. But, its cost and reliability have not met the demand of large-scale storage systems. RAID (redundant arrays of inexpensive disks) is a conventional scheme to enhance reliability. However, existing RAID schemes are not effective for SSDs anymore. Instead, we propose a hybrid array consisting of SSDs and HDDs (hard disk drive) ~ SSDs are used for responding to I/O requests, and HDDs supply backup for SSDs. The hybrid array guarantees both performance and reliability at a reasonable cost. However, HDDs lose to SSDs in term of both latency and bandwidth. Therefore, we employ a nonvolatile memory to bridge the latency gap, and take other two measures to improve HDD's bandwidth. Firstly, workloads within an HDD are reconfigured to be more sequential. Secondly, multiple HDDs collaborate with each other to supply much higher aggregate bandwidth. By these ways, HDDs can replicate SSDs' data in time. We implement a prototype to evaluate the proposed array. First of all, we demonstrate that the hybrid array is feasible. Then, we compare the hybrid array with other solutions. Experimental results show that the hybrid array covers both performance and reliability, and is also cost-effective.
出处 《计算机研究与发展》 EI CSCD 北大核心 2013年第1期80-89,共10页 Journal of Computer Research and Development
基金 国家自然科学基金项目(61025009 60903040 61170288)
关键词 闪存 固态盘 磁盘阵列 混合存储系统 可靠性 flash memory solid state drive (SSD) redundant arrays of inexpensive disk (RAID) hybrid storage system reliability
  • 相关文献

参考文献12

  • 1Patterson D, Gibson G, Katz R. A case for redundant arrays of inexpensive disks (RAID)[C] //Proe of ACM SIGMOD'88. New York: ACM, 1997: 109-116.
  • 2Kadav A, Balakrishnan M, Prabhakaran V, et al. Differential RAID: Rethinking RAID for SSD reliability [J]. ACM Trans on Storage, 2010, 6(2): 1-12.
  • 3Hu X, Eleftheriou E, Haas R, et al. Write amplification analysis in flash-based solid state drives [C] //Proe of SYSTOR'09. New York: ACM, 2009: 1-12.
  • 4Intel. SSD320 data sheet [EB/OL]. [2011- 03 -30]. http:// www. intel, com.
  • 5Seagate. Barracuda 7200.10 data sheet [EB/OL]. [2007- 04 -18]. http://www, seagate, com.
  • 6Narayanan D, Donnelly A, Rowstron A. Write off-loading: Practical power management for enterprise storage[J]. ACM Trans on Storage, 2008, 4(3): 1-23.
  • 7SNIA. SNIA block I/O traces [EB/OL]. [2010-06-12]. http ://iotta. snia. org/traces.
  • 8Mao Bo, Jiang Hong, Feng Dan, et al. HPDA: A hybrid parity based disk array for enhanced performance and reliability [C] //Proc of IEEE IPDPS'10. Piscataway, NJ: IEEE, 2010: 1-12.
  • 9Soundararajan G, Prabhakaran V, Balakrishnan M, et al. Extending SSD lifetimes with disk-based write caches [C] //Proc of FAST'10. Berkeley, CA: USENIX Association, 2010: 101-114.
  • 10Ren Jin, Yang Qing. I CASH: Intelligently coupled array of SSD and HDD [C] //Proc of IEEE HPCA'll. Piscataway, NJ: IEEE, 2011:278-289.

二级参考文献28

  • 1Hwang C-G.Nanotechnology enables a new memory growth model.Proceedings of the IEEE,2003,91(11):1765-1771.
  • 2Babaoglu O,Joy W.Converting a swap-based system to do paging in an architecture lacking page-reference bits.ACM SIGOPS Operating Systems Review,1981,15(5):78-86.
  • 3Robinson J T,Devarakonda M V.Data cache management using frequency-based replacement//Proceedings of the ACM SIGMETRICS.Boulder,Colorado,USA,1990:134-142.
  • 4O'Neil E J,O'Neil P E,Weikum G.The LRU-K page replacement algorithm for database disk buffering//Proceedings of the ACM SIGMOD Conference.Washington,1993:297-306.
  • 5Johnson T,Shasha D.2Q:A low overhead high performance buffer management replacement algorithm//Proceedings of the 20th International Conference on Very Large Data Base.Santiago de Chile,Chile,1994:439-450.
  • 6Jiang S,Zhang X.Making LRU friendly to weak locality workloads:A novel replacement algorithm to improve buffer cache performance.IEEE Transactions on Computers,2005,54(8):939-952.
  • 7Megiddo N,Modha D S.ARC:A self-tuning,low overhead replacement cache//Proceedings of the FAST'03 Conference on File and Storage Technologies.San Francisco,California,USA,2003:115-130.
  • 8Lee D,Choi J,Kim J-H,Noh S H,Min S L,Cho Y,Kim C-S.LRFU:A spectrum of policies that subsumes the least recently used and least frequently used policies.IEEE Transactions on Computers,2001,50(12):1352-1361.
  • 9Effelsberg W,Haerder T.Principles of database buffer management.ACM Transactions on Database Systems,1984,9(4):560-595.
  • 10Park S-Y,Jung D,Kang J-U,Kim J,Lee J.CFLRU:A replacement algorithm for flash memory//Proceedings of the 2006 International Conference on Compilers,Architecture,and Synthesis for Embedded Systems (CASES).Seoul,Korea,2006:234-241.

共引文献10

同被引文献74

  • 1支阿龙.操作系统安全解决方案浅析[J].信息网络安全,2008(2):52-53. 被引量:5
  • 2陈卓,熊劲,马灿.基于SSD的机群文件系统元数据存储系统[J].计算机研究与发展,2012,49(S1):269-275. 被引量:8
  • 3陈川,肖侬,赖明澈.Meteoric固态盘设计中的并行性策略研究[J].计算机研究与发展,2011,48(S1):283-288. 被引量:3
  • 4Kgil T, Roberts D, Mudge T. Improving NAND Flash Based Disk Caches[C]. ISCA'08,Washington,2008.
  • 5Oh Y, Choi J. Caching less for better performance: balancing cache size and update cost of flash memory cache in hybrid storage systems [C]. FAST'12, Berkeley,2012.
  • 6Cohen F. Computational aspects of computer viruses[J].Computers and Security, 1989, ( 04 ) : 325-344.
  • 7Wu Michael,Zwaenepoel Willy.eNVy:a non-volatile,main memory storage system[C].ASPLOS,New York,1994.
  • 8Kawaguchi Atsuo,Nishioka Shingo,Motoda Hiroshi.A flash memory based file system[C].USENIX ATC,Berkeley,1995.
  • 9Chang Li-Pin,Kuo Tei-Wei.An adaptive striping architecture for flash memory storage systems of embedded systems[C].RTAS'02,Washington,2012.
  • 10Hsieh Jen-Wei,Chang Li-Pin,Kuo Tei-Wei.Efficient on-line identification of hot data for flash-memory management[C].SAC,New York,2005.

引证文献11

二级引证文献11

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