期刊文献+

MassCloud云存储系统构架及可靠性机制 被引量:16

Architecture and reliability of cloud storage system MassCloud
下载PDF
导出
摘要 为了解决分布式存储系统的存储容量、可靠性以及效率问题,首先提出了高可靠性海量云存储系统MassCloud的分层体系结构,并在此构架的基础上提出了基于纠删码机制的快速编解码算法——双表法,以及基于纠删码、副本冗余和RAID技术相结合的MassCloud可靠性保证策略,并且进行了测试与分析.结果表明:双表法具有较高的编解码效率,在广域网环境下不会成为性能瓶颈;MassCloud采用4组(8块硬盘)作为每个低功耗存储节点包含的硬盘数,云存储站点层采用3个副本,分布式环境下冗余倍数取2,文件分块数取8,能够保证系统整体可靠性在0.99以上. The hierarchic architecture of the cloud storage system MassCloud with high reliability and mass data storage capability was proposed to solve the current problems of distributed storage system,that is,storage capacity,reliability and efficiency.On such a basis,a double-table method was designed based on the erasure code to gain high encoding/decoding speed in order to suit the distributed storage environment.The reliability of MassCloud was guaranteed by a policy combining the erasure code,duplicate redundancy and RAID.The relevant tests were performed and analyzed.The results show that the double-table method has high encoding/coding efficiency and may not become a bottleneck under the WAN environment.The whole reliability of MassCloud can be ensured to be above 0.99 by using 4 groups of disks(8 pieces of disks) with low cost storage level,3 replicas for cloud storage level,2 times redundancy in distributed environment and 8 pieces of file division.
出处 《河海大学学报(自然科学版)》 CAS CSCD 北大核心 2011年第3期348-354,共7页 Journal of Hohai University(Natural Sciences)
基金 国家高技术研究发展计划(863计划)(2008AA01A309)
关键词 MassCloud 云存储 纠删码 副本冗余 存储可靠性 MassCloud cloud storage erasure code duplicate redundancy storage reliability
  • 相关文献

参考文献20

  • 1张江陵,冯丹.海地信息存储[M].北京:科学出版社,2000.95-107.
  • 2WEATHERSPOON H,EATON P, KUIBIATOWICZ J, et al. Antiquity: exploiting a secure log for wide-area distributed storage[ C ]// Proceedings of the 2nd ACM SIGOPS/EuroSys European Coifference on Computer-Systems 2007, Lisbon, Portugal. New York: ACM, 2007 : 371-384.
  • 3LAKSHMAN A, MALIK P. Cassandra: structured storage system on a P2P network[C]//Proceedings of the 28th ACM Syrnpositun on Principles of Distributed Computing. New York : ACM, 2009 : 5-5.
  • 4BEHRMANN G, FUHRMANN P, GRONAGER M, et al. A distributed storage system with dCache[J].Journal of Physics, 2008, 119(6): 2014- 2025.
  • 5DUBNICKI C,GHYZ L, HEILDT L, et al. HYDRAstor: a sealable secondary storage[ C]//Proceedings of the 7th Conference on File and Storage Technologies. California, LISA : USEN1X Association Berkeley, 2009 : 197-210.
  • 6SHI Guang-yu, CHEN Jian, GONG Hao, et al. SandStone: a DHT based carrier grade distributed slorage system[ C]//2009 International Conference on Parallel Processing. Vienna, Austria : IEEE Computer Society, 2009 : 420-428.
  • 7JEFF T, MICHAEl, J. Freedman bject storage on CRAQ: high-throughput chain replication for read-mostly workloads[C[//Proceedings of the 2009 Conference on USENIX Annual Technical Conference. California, USA: USENIX Association Berkeley, 2009: 11.
  • 8杨德志,许鲁,张建刚.蓝鲸分布式文件系统元数据服务[J].计算机工程,2008,34(7):4-6. 被引量:9
  • 9张敬亮,张军伟,张建刚,许鲁.蓝鲸文件系统中元数据与数据隔离技术[J].计算机工程,2010,36(2):28-30. 被引量:9
  • 10田荣华,卢显良,侯孟书,王晓斌.P2P分布式存储系统[J].计算机科学,2007,34(6):47-48. 被引量:8

二级参考文献60

  • 1杨德志,黄华,张建刚,许鲁.大容量、高性能、高扩展能力的蓝鲸分布式文件系统[J].计算机研究与发展,2005,42(6):1028-1033. 被引量:28
  • 2黄华,张建刚,许鲁.蓝鲸分布式文件系统的分布式分层资源管理模型[J].计算机研究与发展,2005,42(6):1034-1038. 被引量:12
  • 3侯孟书,王晓斌,卢显良,任立勇.一种新的动态副本管理机制[J].计算机科学,2006,33(9):50-51. 被引量:13
  • 4田敬,代亚非.P2P持久存储研究[J].软件学报,2007,18(6):1379-1399. 被引量:52
  • 5Roselli D, Lorch J, Anderson T. A Comparison of File System Workloads[C]//Proc. of USENIX'00. San Diego, CA, USA: [s. n.],2000: 41-54.
  • 6Ruemmler C, Wilkes J. UNIX disk access patterns[C]//Proc, of the USENIX'93. San Diego, CA, USA: [s. n.], 1993: 405-420.
  • 7Traeger A, Zadok E, Joukov N, et al. A Nine Year Study of File System and Storage Benchmarking[R]. New York, USA: Computer Science Department, Stony Brook University, Teeh. Rep.: FSL-07-01, 2008.
  • 8NetBench[Z]. (2002-04-06). http://www.veritest.com/benchmarks/ netbench/.
  • 9Kubiatowicz J, Bindel D, Chen Y, et al. OceanStore: An Architecture for Global-scale Persistent Storage [ C ]//9th International Conference on Architectural Support for Programming Languages and Operating Systems ( ASPLOS Ⅸ). November 2000.
  • 10Bek F, Kaashoek M F, Karger D, et al. Wide-area Cooperative Storage with CFS [ C ]//18th ACM Symposium on Operating Systems Principles ( SOSP01 ). October 2001.

共引文献38

同被引文献120

引证文献16

二级引证文献90

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