期刊文献+

DCFS2的元数据一致性策略 被引量:11

Metadata Consistency in DCFS2
下载PDF
导出
摘要 随着集群应用对机群文件系统的性能、容量和规模等需求的日益增长,采用多元数据服务器是机群文件系统发展的必然趋势.基于多元数据服务器的分布式元数据处理是文件系统研究的一个重要问题.机群文件系统DCFS2采用分布式日志技术和改进的两阶段提交协议解决了分布式元数据处理下元数据的一致性问题.性能测试结果表明,DCFS2所采用的基于分布式日志的元数据处理策略能够提供高的IO性能,并能够保证在元数据服务器失效后文件系统快速恢复. With the increase of required performance, capacity and scalability for a cluster file system, the multi-metadata-server structure is the trend for future cluster file systems. Distributed metadata processing based on multiple metadata servers is an important but difficult issue. In order to get high metadata performance and scalability, DCFS2, a cluster file system, uses distributed metadata processing over multiple metadata servers. Moreover, DCFS2 solved the metadata consistency problem for distributed metadata processing through a distributed logging technology and a simplified two-phase commit protocol. And performance results show that DCFS2's metadata processing policy based on distributed logging can deliver high I?O performance, and the file system can quickly recover from a metadata server failure.
出处 《计算机研究与发展》 EI CSCD 北大核心 2005年第6期1019-1027,共9页 Journal of Computer Research and Development
基金 国家"八六三"高技术研究发展计划基金项目(2002AA1Z2102 2002AA104410)
关键词 机群文件系统 文件系统一致性 元数据一致性 分布式元数据处理 cluster file system file system consistency metadata consistency distributed metadata processing
  • 相关文献

参考文献24

  • 1R. J. Morris, B. J. Truskowski. The evolution of storage systems. IBM Systems Journal, 2003, 42(2): 205~217
  • 2P. Sarkar, K. Voruganti, K. Meth, et al. Internet protocol storage area network. IBM Systems Journal, 2003, 42(2): 218~231
  • 3K. W. Preslan, A. Barry, J. Brassow, et al. Implementing journaling in a Linux shared disk file system. The 8th NASA Goddard Conf. Mass Storage Systemsand Technologies in Cooperation with the Seventeenth IEEE Symposium on Mass Storage Systems, Maryland, 2000
  • 4Laura Shepard, Eric Eppe. SGI InfiniteStorage Shared Filesystem CXFSTM: A High-Performance, Multi-OS SAN File System from SGI. Mountain View, CA: Silicon Graphics, Inc. 2004
  • 5F. Schmuck, R. Haskin. GPFS: A shared-disk file system for large computing clusters. The First USENIX Conf. File and Storage(FAST2002), Monterey, 2002
  • 6J. Menon, D. A. Pease, R. Rees, et al. IBM storage tank-A heterogeneous scalable SAN file system. IBM Systems Journal,2003, 42(2): 250~267
  • 7P. J. Braam. The Lustre Storage Architecture. Medford, MA:Cluster File Systems, Inc. 2004
  • 8Uresh Vahalia. UNIX Internals: The New Frontiers. Englewood Cliffs, NJ: Prentice-Hall, 1996
  • 9J. Gray. Notes on data base operating systems. In: R. Bayer, R.M. Graham, G. Seegmuller, eds, Operating Systems: An Advanced Course, Lecture Notes on Computer Science 60. New York: Springer-Verlag, 1978. 393~481
  • 10T. Haerder, A. Reuter. Principles of transaction-oriented database recovery. ACM Computing Surveys, 1983, 15(4): 287~317

同被引文献66

引证文献11

二级引证文献78

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