Static file layout strategy for large-scale storage system

被引：0
作者：
机构：
[1] School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, Guangdong
[2] School of Computer Engineering and Technology, Guangdong Institute of Science and Technology, Zhuhai 519090, Guangdong
来源：
Long, S.-Q. (longsaiqin@163.com) | 1600年 / South China University of Technology卷 / 41期
关键词：
File layout strategy; Large-scale storage system; Load balancing; Mean response time; Static layout;
D O I：
10.3969/j.issn.1000-565X.2013.01.011
中图分类号：
学科分类号：
摘要：
Proposed in this paper is a static file layout strategy (SFLS) in improving the access performance of large-scale storage systems. In SFLS, first, the disk is divided into two groups that are respectively used to store hot files and large files. Then, the files sorted according to the service time are assigned to the two groups of disks in the ways of Round-robin or Greedy. The disk group that should be accessed is selected according to the size and heat of files, which speeds up the I/O access of files and improves the access performance of the storage system. Experimental results show that SFLS dynamically adapts to the increase of system scale, costs less response time and possesses better load balancing performance, as compared with the static layout strategies SP and SOR and with the dynamic layout strategy HP.
引用
收藏
页码：70 / 76
页数：6
相关论文
共 13 条
  • [1] Deng Z.J., An optimization load balancing algorithm design in massive storage system, International Conference on Environmental Science and Information Application Technology, pp. 310-313, (2009)
  • [2] Liu Z., Zhou X.-M., A data object placement algorithm based on dynamic interval mapping, Journal of Software, 16, 11, pp. 1886-1893, (2005)
  • [3] Xie T., SEA: A striping-based energy-aware strategy for data placement in RAID-structured storage systems, IEEE Transactions on Computers, 57, 6, pp. 748-761, (2008)
  • [4] Ma Y.C., Chiu J.C., Chen T.F., Et al., Variable-size data item placement for load and storage balancing, The Journal of Systems and Software, 66, 2, pp. 157-166, (2003)
  • [5] Scheuermann P., Weikum G., Zabback P., Data partitioning and load balancing in parallel disk systems, The VLDB Journal, 7, 1, pp. 48-66, (1998)
  • [6] Verma A., Anand A., General store placement for response time minimization in parallel disks, Journal of Parallel and Distributed Computing, 67, 12, pp. 1286-1300, (2007)
  • [7] Triantafillou P., Christodoulakis S., Georgiadis C., Optimal data placement on disks: A comprehensive solution for di-fferent technologies, IEEE Transactions on Knowledge and Data Engineering, 12, 2, pp. 324-330, (2000)
  • [8] Chu W.W., Optimal file allocation in a multiple computer system, IEEE Transactions on Computers, 18, 10, pp. 885-889, (1969)
  • [9] Xie T., Sun Y., A file assignment strategy independent of workload characteristic assumptions, ACM Transactions on Storage, 5, 3, pp. 1-24, (2009)
  • [10] Lee L.W., Scheuermann P., Vingralek R., File assignment in parallel I/O systems with minimal variance of service time, IEEE Transactions on Computers, 49, 2, pp. 127-140, (2000)
12