期刊文献+

自适应分片算法研究 被引量:1

A Novel Adaptive Disk Stripping Algorithm
下载PDF
导出
摘要 论文提出了一个自适应磁盘分片算法。首先,利用M/G/1排队理论对单个文件和整个阵列的平均存储响应时间建模,并提出了最优分片宽度理论计算公式;考虑到访问流之间的竞争,论文提出了一个磁盘分片的启发算法,它同时计算没有背景负荷和有背景负荷下访问流对应的磁盘优化分片,最终的磁盘分片是两者的结合;模拟试验表明自适应分片算法在四种分片算法中的性能最佳。 A novel disk stripping algorithm is proposed in this paper.Firstly,the queue theory of M/G/1 is used to model single file and RAID's response time,and the optimal strip width is proposed.Secondly,in order to account for the inter-stream competition,a heuristic algorithm is proposed.The algorithm considers the optimal strip width with and without background disk load and the final strip width is decided by both widths.Finally,the simulation shows that the adaptive algorithm is the best among four disk stripping algorithms.
出处 《计算机工程与应用》 CSCD 北大核心 2004年第30期68-70,共3页 Computer Engineering and Applications
关键词 分片 M/G/1 自适应 disk stripping,M/G/1,adaptive
  • 相关文献

参考文献11

  • 1Peter M Chen,David A Patterson. Maximizing Performance in a Striped Disk Array[C].In:ISCA,Proceedings of 17th Annual International Symposium on Computer Architecture, 1990: 322~331
  • 2Christopher L Elford,Daniel A Reed.Effects of Trends in Disk Technology on Disk Arrays[J]Journal of Parallel and Distributed Computing, 1997 ;46(2): 136~147
  • 3P Triantafillou,C Faloutsos. Overlay Striping and Optimal Parallel I/O in Modern Applications[J].Parallel Computing Journal ,Special Issue on Parallel Data Servers and Applications, 1998; 24 (1): 21~43
  • 4P M Chen,E K Lee. Striping in a RAID Level 5 Disk Array[C].In:Proceedings of the 1995 ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems, 1995:136~145
  • 5Edward K Lee ,Randy H Katz. An analytic performance model of disk arrays[J].ACM SIGMETRICS Performance Evaluation Overview,1993;21 (1) :98~109
  • 6Mustafa Uysal, Guillermo A Alvarez,Arif Merchant. A Modular,Analytical Throughput Model for Modern Disk Arrays[C].In:9th International Symposium on Modeling ,Analysis and Simulation of Computer and Telecommunication Systems,2001
  • 7Athena Vakali.Data block prefetching and caching in a hierarchical storage model[J].Information Science,2000; 128:19~41
  • 8Elizabeth A M Shriver,Arif Merchant,John Wilkes. An Analytic Behavior Model for Disk Drives with Readahead Caches and Request Reordering. Measurement and Modeling of Computer Systems, 1998:182~191
  • 9Daniel A Menasc′e,Odysseas I Pentakalos.Analytic Modeling of Distributed Hierarchical Mass Storage Systems with Network-Attached Storage Devices.http:∥ citeseer. nj.nec.com/217412.html,1996
  • 10Peter Scheuermann,Gerhard Weikum,Peter Zabback. Data Partitioning and Load Balancing in parallel disk systems[J].VLDB Journal,1998; (7) :48~66

同被引文献8

  • 1Peter Dinda,Thomas Gross,David O′Hallaron et.al.,The CMU Task Parallel Program Suite.Tech.Rep.CMU-CS-94-131,School of Computer Science,Carnegie Mellon University,http:∥citeseer.nj.nec.com/dinda94cmu.html,1994.
  • 2Daniel D.Corkill.Blackboard Systems.AI Expert,6(9),1991:40~47.
  • 3余瑞钊 史济建.人工智能原理与技术[M].浙江大学出版社,1993..
  • 4Albert Alexandrov,Mihai F.Ionescu,Klaus E.Schauser et.al.,LogGP:Incorporating Long Messages into the LogP Model--One step closer towards a realistic model for parallel computation.Journal of Parallel and Distributed Computing.1997,44(1):71~79.
  • 5Andrei Radulescu,Cristina Nicolescu,Arjan J.C.van Gemund.CPR:Mixed Task and Data Parallel Scheduling for Distributed Systems.proceedings of The 15^thInternational Parallel and Distributed Symposium.2001:39~41.
  • 6Rajeev Thakur William Gropp Ewing Lusk.Data Sieving and Collective I/O in ROMIO.Proceedings of the 7th Symposium on the Frontiers of Massively Parallel Computation,1999:182~189.
  • 7Marco Vanneschi.The programming model of ASSIST,an environment for parallel and distributed portable applications.Parallel Computing.2002,28:1709~1732.
  • 8Alexey Lastovetsky.Adaptive parallel computing on heterogeneous networks with mpC.Parallel Computing.2002,28:1369~1407.

引证文献1

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