The Journal of the Korea Contents Association (한국콘텐츠학회논문지)

The Korea Contents Association (한국콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

SBR-k(Sized-base replacement-k) : File Replacement in Data Grid Environments

SBR-k(Sized-based replacement-k) : 데이터 그리드 환경에서 파일 교체

  • Published : 2008.11.28
Download PDF
⟨ Previous Next ⟩

Abstract

The data grid computing provides geographically distributed storage resources to solve computational problems with large-scale data. Unlike cache replacement policies in virtual memory or web-caching replacement, an optimal file replacement policy for data grids is the one of the important problems by the fact that file size is very large. The traditional file replacement policies such as LRU(Least Recently Used), LCB-K(Least Cost Beneficial based on K), EBR(Economic-based cache replacement), LVCT(Least Value-based on Caching Time) have the problem that they have to predict requests or need additional resources to file replacement. To solve theses problems, this paper propose SBR-k(Sized-based replacement-k) that replaces files based on file size. The proposed policy considers file size to reduce the number of files corresponding to a requested file rather than forecasting the uncertain future for replacement. The results of the simulation show that hit ratio was similar when the cache size was small, but the proposed policy was superior to traditional policies when the cache size was large.

데이터 그리드는 대용량의 데이터 어플리케이션 처리를 위해 지리적으로 분산되어 있는 저장 자원을 제공한다. 대용량을 처리해야 하는 데이터 그리드 환경에서는 기존 웹 캐싱 정책이나 가상 메모리 캐쉬 교체 정책과는 다른 파일 교체 정책이 필요하다. LRU(Least Recently Used)나 LCB-K(Least Cost Beneficial based on K), EBR(Economic-based cache replacement), LVCT(Least Value-based on Caching Time) 같은 기존의 파일 교체 전략은 파일 교체를 위해 추가적인 자원이 필요하거나 미래를 예측해야한다. 본 논문은 이를 해결하기 위해 파일의 크기에 기반하여 파일 교체를 수행하는 SBR-k(Sized-based replacement-k)을 제안한다. 제안된 정책은 불확실한 미래 예측의 부담을 줄이고, 요청된 파일에 대응되는 교체 파일의 개수가 적게 하이 위해 파일 크기를 고려하였다. 성능평가 결과 캐쉬 크기가 작은 경우에 적중률이 비슷하나 캐쉬 크기가 크면 본 논문에서 제시한 정책이 우수함을 보였다.

Keywords

References

  1. B. Allcock, I. Foster, V. Nefedova, A. Chervenak, and D. Deelman, "High-performance remote access to climate simulation data : A challenge problem for data grid technologies," Proceeding of the SuperComputing Conference, Non., 2003.
  2. K. IIoltman, "Data grid system overview and requirements," Technical report, CERN 2001(7).
  3. M. Russel, G. Allen, G. Daues, I. Foster, E. Seidel, J. Novotny, J. Shalf, and G. von Laszewski, "The astophysics simulation collaboratory : A science portal enabling community software deveopment," Cluster Computing , 2002.
  4. A. Chervenak, I. Foster, C. Kesselman, C. Salisbury, and S. Tueckes, "The data grid: Towards an architecture for the distributed management and analysis of large scientific data-sets," Journal of Network and Computer Applications, pp.187-200, 2002.
  5. E. J. Otoo, F. Olken, and A. Shoshani, "Disk Cache replacement algorithm for storage resource managers in data grids," In The 15th Annual Super Computer Conference, pp.1-15, 2002(11).
  6. J. H. Abawajy, "File Replacement Algorithm for Storage Resource Managers in Data Grids," LNCS 3038, pp.339-346, 2004.
  7. M. Carman, F. Serafini, L. Stokinger, and K. Stockinger, "Towards an Economy-Based Optimisation of File Access and Replication on a Data Grid," In Procedings of 2nd CCGRID, pp.120-126, 2002.
  8. S. Jiang and X. Zhang, "An Efficient Distributed Disk Caching in Data Grid Managemnet," In Proceedings of Cluster Computing, 2003.
  9. S. Aberham, G. Peter Baer, and G. Greg, Operating system principles, 7th, Wiley, 2006.
  10. E. J. Otoo, F. O'Neil, and G. Weilum, "The LRU-K page repalcement Algorithm for Database Disk Buffering," The 15th Annual Super Computer Conference, 2002(11).
  11. http://cern.ch/edg-wp2/optimization/ opotorsim.html
  12. W. H. Bell and D. G. Gameron, "Optorsim - A grid simulator for studying dynamic data replication strategies," Journal of High Performance Computing Application, 2003.