소프트웨어 RAID 파일 시스템에서 오손 블록 교체시에 효율적인 캐슁 기법

An efficient caching scheme at replacing a dirty block for softwre RAID filte systems

  • 김종훈 (홍익대학교 컴퓨터공학과) ;
  • 노삼혁 (홍익대학교 컴퓨터공학과) ;
  • 원유헌 (홍익대학교 컴퓨터공학과)
  • 발행 : 1997.07.01

초록

The software RAID file system is defined as the system which distributes data redundantly across an aray of disks attached to each workstations connected on a high-speed network. This provides high throughput as well as higher availability. In this paper, we present an efficient caching scheme for the software RAID filte system. The performance of this schmem is compared to two other schemes previously proposed for convnetional file systems and adapted for the software RAID file system. As in hardware RAID systems, small-writes to be the performance bottleneck in softwre RAID filte systems. To tackle this problem, we logically divide the cache into two levels. By keeping old data and parity val7ues in the second-level cache we were able to eliminate much of the extra disk reads and writes necessary for write-back of dirty blocks. Using track driven simulations we show that the proposed scheme improves performance for both the average response time and the average system busy time.

키워드

참고문헌

  1. In Proceedings of the Summer 1985 USENIX Conference Design and Implementation of the SUN Network File System Russel Sandberg (et al.)
  2. IEEE Computer v.21 The Sprite Network Operating System J. K. Ousterhout;A. R. Cherenson;F. Douglis;M. N. Nelson;B. B. Welch
  3. ACM Transactions on Computer System v.13 no.3 The Zebra striped network file system J. H. Hartman;J. K. Ousterhout
  4. ACM Transactions on Computer Systems v.14 no.1 Serverless Network File System T. E. Anderson;M. D. Dahlin;J. M. Neefe;D. A. Patterson;D. S. Roselli;R. Y. Wang
  5. IEEE Micro v.15 no.1 A Case for NOW(Networks of Workstations) T. E. Anderson;D. E. Culler;D. A. Patterson
  6. 한국통신학회 논문지 v.22 no.6 NOW(Network of Work-stations) 환경에서 소프트웨어 RAID 파일 시스템의 설계 및 성능 평가 김종훈;노삼혁;원유헌
  7. Proceedings of the First Symposium on Operating System Design and Implementation Cooperative Caching : Using remote client memory to improve file system performance M. D. Dahlin;R. Y. Wang;T. E. Anderson ;D. A. Patterson
  8. ACM Computing Surveys v.26 no.2 RAID:High-Performance, Reliable Secondary Storage P. M. Chen;E. K. Lee;G. A. Gibson;R. H. Katz;D. A. Patterson
  9. ACM Transactions on Computer Systems v.12 no.3 Parity-logging Disk Arrays Daniel Stodolsky;Mark Holland;Wiiliam V.;Courtright III;Garth A. Gibson
  10. Journal of Parallel and Distributed Computing Floating Parity and Data Disk Arrays Jai Menon;Janes Roche;Jim Kasson
  11. Proceedings of the 20th Annual International Symposium on Computer Architecture(ISCA '93) The Architecture of a Fault-tolerant Cached RAID Controller Jai Menon;Jim Cortney
  12. IEEE Transactions on Parallel and Distributed Systems v.7 no.2 Efficient LRU-Based Buffering in a LAN Remote Caching Architecture A. Leff;J. L. Wolf;P. S. Yu
  13. Proceedings of the ACM Thirteenth Symposium on Operating Systems Principles Measurements of a Distributed File System M. G. Baker;J. H. Hartman;M. D. Kupfer;K. W. Shirriff;J. K. Ousterhout
  14. Proceedings of the 1994 Hot Interconnects II Conference HPAM: An Active Messaage Layer for a Network of HP Workstations R. Martin
  15. Proceedings of the 1995 Hot Interconnects III Conference LogP Quantified: The Case for Low-Overhead Local Area Networks K. K. Keeton;T. E. Anderson;D. A. Patterson
  16. Technical Report PCS-TR94-220 A Detailed Simulation Model of the HP 97560 Disk Drive David Kotz;Song Bac Toh;Sriram Radhakrisshnan