期刊文献+

蓝鲸文件系统中元数据与数据隔离技术 被引量:9

IsolatI/On Technology of Metadata from Data in Blue Whale File System
下载PDF
导出
摘要 针对文件系统中元数据访问对应用数据访问的干扰问题,基于资源分配分离及访问路由分发技术,在蓝鲸文件系统中实现元数据和数据存储及I/O时的隔离。测试结果表明,将元数据从数据中隔离并将其独立配置到高速存储后,应用I/O带宽提高了2.6倍~2.8倍,操作吞吐率提高了2倍~5倍。 Aiming at the performance interference between metadata and data access,this paper proposes a novel mechanism in Blue Whale File System(BWFS) to isolate metadata from data both in physical storage and I/O path. The isolatI/On is realized by the resource separatI/On and I/O request dispatching. Test results show that,after metadata is separated and put in the high-performance media,the applicatI/On I/O bandwidth is increased by 2.6 times~2.8 times,while OPS is improved by 2 times~5 times.
出处 《计算机工程》 CAS CSCD 北大核心 2010年第2期28-30,38,共4页 Computer Engineering
基金 国家"863"计划基金资助项目(2007AA01Z402) 国家"973"计划基金资助项目(2004CB318205)
关键词 蓝鲸文件系统 集群文件系统 元数据隔离 Dbench测试集 Blue Whale File System(BWFS) cluster file system metadata isolatI/On Dbench test set
  • 相关文献

参考文献5

  • 1Roselli 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.
  • 2Ruemmler C, Wilkes J. UNIX disk access patterns[C]//Proc, of the USENIX'93. San Diego, CA, USA: [s. n.], 1993: 405-420.
  • 3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
  • 4Traeger 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.
  • 5NetBench[Z]. (2002-04-06). http://www.veritest.com/benchmarks/ netbench/.

二级参考文献10

  • 1S. Shepler, B. Callaghan. Network File System (NFS) version 4 Protocol. The Internet Engineering Task Force. http:∥www.ietf. org/rfc3530. txt, 2003-04
  • 2Pavel Machek. Network Block Device (TCP version) . http: ∥atrey. karlin. mff. cuni. cz/~ pavel/nbd/nbd. html, 1997
  • 3J. Satran, K. Meth. Internet Small Computer Systems Interface (iSCSI) . The Internet Engineering Task Force. http:∥www.ietf. org/rfc3720. txt, 2004-04
  • 4Adam Sweeney. Scalability in the XFS file system. The USENIX 1996 Annual Technical Conf., San Diego, California, 1996
  • 5Steve Best. JFS Overview-How the Journaled File System Cuts System Restart Times to the Quick. http:∥www-106.ibm.com/developerworks/library/l-jfs. html, 2000-01
  • 6Peter Braam. The lustre storage architecture. http: ∥ www.lustre.org/docs/lustre.pdf, 2004-04-03
  • 7J. 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
  • 8Jin Xiong, Sining Wu, Dan Meng, et al. Design and performance of the Dawning cluster file system. Int'l Conf. Cluster Computing (Cluster 2003), Hong Kong, 2003
  • 9netperf. http:∥www.netperf.org/, 2004
  • 10田颖,许鲁.分布式文件系统中的负载平衡技术[J].计算机工程,2003,29(19):42-44. 被引量:9

共引文献11

同被引文献80

引证文献9

二级引证文献59

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