期刊文献+

海量存储系统中磁带文件缓存管理 被引量:1

Cache management of tape files in mass storage system
在线阅读 下载PDF
导出
摘要 针对磁带库的数据访问特点,根据高能物理领域的实际需求,提出了分组协同缓存策略。这一策略以缓存模型为基础,结合本地缓存与协同缓存的优点,把缓冲区分成不同的组,不同组的缓冲区之间相互独立;同一组的缓冲区由网络上不同节点上的磁盘组成,这些磁盘之间相互协作。还对该缓存策略的目录管理、更新算法、一致性等问题进行了详细分析。实验说明,该策略能很好的满足高能物理领域的数据处理和海量存储需求。 This paper proposes the group-cooperative caching policy accordingto the characteristics of tapes and requirements of high energy physics domain. This policy integrates the advantages of traditional local caching and cooperative caching on basis of cache model. It divides cache into independent groups; the same group of cache is made of cooperating disks on network. This paper also analyzes the directory management, update algorithm and cache consistency of the policy. The experiment shows the policy can meet the requirements of data processing and mass storage in high energy physics domain very well.
出处 《核电子学与探测技术》 CAS CSCD 北大核心 2006年第4期438-442,共5页 Nuclear Electronics & Detection Technology
关键词 海量存储 磁带库 缓存管理 分组协同缓存 mass storage tape library group-cooperative caching cache consistency
  • 相关文献

参考文献4

  • 1陈玉鹏,陈玮,石晶,陆达,潘龙法.机械手存储库缓存替换算法研究及应用[J].计算机工程与应用,2003,39(36):5-8. 被引量:3
  • 2Anderson T,et al.Serverless Network File Systems,ACM Transactions on Computer Systems (TOCS),1996,14(1):41.
  • 3Dajian Yang,et al.Building an Advanced Computing Environment with SAN Support[C]// Proceedings of Computing in High Energy Physics.Beijing,September 3-7th,2001:333.
  • 4CASTOR web page:http://castor.web.cern.ch/

二级参考文献6

  • 1[1]G K Zipf. The Psychobiology of Language[M].Boston:Houghton-Mifflin, 1935
  • 2[2]D N Serpanos,G Karakostas,W H Wolf. Effective caching of Web objects using Zipf's Iaw[C].In:IEEE International Conference on Multimedia and Expo,ICME 2000,2000;2:72~730
  • 3[3]Donghee Lee,Jongmoo Choi,Honggi Choe et al. Implementation and performance evaluation of the LRFU replacement policy[C].In:EUROMICRO 97,New Frontiers of Information Technology,Short Contributions,Proceedings of the 23rd Euromicro Conference, 1997-09:106~111
  • 4[4]R Pendse,R Bhagavathula. Performance of LRU block replacement algorithm with pre-fetching[C].In :Proceedings of Midwest Symposium on Circuits and Systems,1998-08:86~89
  • 5[5]J Van den Berg,D T oswley. Properties of the miss ratio for a 2-level storage model with LRU or FIFO replacement strategy and independent references[J].IEEE Transactions on Computers, 1993;42(4) :508~512
  • 6[6]L Rizzo,L Vicisano. Replacement policies for a proxy cache[J].IEEE/ACM Transactions on Networking,2000;8(2):158~170

共引文献2

同被引文献8

  • 1Noels C.The LHC project[EB/OL].http://lhc.web.cem.ch.
  • 2孙功星 陈刚.海量数据处理系统的设计和实现.高性能计算发展与应用,2008,23(2):34-37.
  • 3Cams P H.PVFS: a Parallel File System for Linux clusters[C]// Proceedings of the 4th Annual Linux Showcase and Conference, 2000.
  • 4Zhu Yifeng.CEFT: a Cost-Effective, Fault-Tolerant parallel virtual file system[J].Joumal of Parallel and Distributed Computing,2006,66.
  • 5Gray J.Distributed computing economics[R].Microsoft Research, San Francisco, California, USA, 2003.
  • 6Bayucan A, Lesiak C.MRJ technology solutions[EB/OL].http:// www.mcs.anl.gov/research/projects/openpbs/docs/v2_2 ids.pdf.
  • 7Bayucan A, Henderson R L.MRJ technology solutions[EB/OL]. http://ece,gmu.edu/lucite/manuals/PBSPro5.0/pbs ers.pdf.
  • 8汪璐,石京燕,程耀东.基于Lustre的BES集群存储系统[J].核电子学与探测技术,2010,30(12):1574-1578. 被引量:4

引证文献1

二级引证文献2

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