KIISE Transactions on Computing Practices (정보과학회 컴퓨팅의 실제 논문지)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

SSD Cache for RAID: Integrating Data Caching and Parity Update Delay

RAID를 위한 SSD 캐시: 데이터 캐싱과 패리티 갱신 지연 기법의 결합

  • 하성태 (서울시립대학교 컴퓨터과학부) ;
  • 이동희 (서울시립대학교 컴퓨터과학부)
  • Received : 2017.03.15
  • Accepted : 2017.04.03
  • Published : 2017.06.15
⟨ Previous Next ⟩

Abstract

In enterprise environments, hybrid storage typically utilizes SSDs over disk-based RAID. Typically, SSDs over RAID are used as the data cache. Recently, the LeavO caching scheme was introduced to reduce the parity update overhead of the underlying RAID. In this paper, we combine the data caching and LeavO caching schemes and derive cost models of the combined cache to determine the optimal data and LeavO cache sizes. We also propose the Adaptive Combined Cache that dynamically adjusts the data cache and LeavO cache sizes for evolving workloads. Experimental results show that the performance of the Adaptive Combined Cache is significantly superior to that of the conventional data caching scheme and is comparable with that of the off-line optimal scheme.

디스크 기반 RAID와 SSD를 결합한 하이브리드 스토리지가 기업 환경에서 널리 이용되고 있다. RAID 상단의 SSD는 주로 데이터 캐시로 사용된다. 최근 SSD를 사용하여 패리티 갱신 비용을 감소시키는 LeavO 캐시 기법이 제안되었으며, 본 논문에서는 데이터 캐시와 LeavO 캐시를 결합한 혼합 캐시기법을 제안한다. 특히 SSD 공간을 데이터 캐시와 LeavO 캐시, 두 영역으로 최적으로 분할하기 위해 비용 모델을 도출하고, 워크로드에 따라 두 영역의 크기를 동적으로 조절하는 적응형 혼합 캐시 기법을 개발하였다. 실험 결과에 따르면 적응형 혼합 캐시 기법은 기존 데이터 캐시 기법에 비해 좋은 성능을 보이며, 오프라인 최적 기법과 대등한 성능을 보인다.

Keywords

Acknowledgement

Supported by : 서울시립대학교

References

  1. P. M. Chen and E. K. Lee, "Striping in a RAID Level 5 Disk Array," Proc. of the ACM SIGMETRICS, 1995.
  2. F. Chen, D. Koufaty, and X. Zhang, "Hystor: Making the best use of solid state drives in high performance storage systems," Proc. of the 25th International Conference on Supercomputing (ICS), 2011.
  3. T. Kgil, D. Roberts, and T. Mudge, "Improving NAND flash based disk caches," Proc. of the 35th Annual International Symposium on Computer Architecture (ISCA), 2008.
  4. E. Lee, Y. Oh, J. Choi, D. Lee, and S. H. Noh, "LeavO cache: SSD cache overcoming small write problem of RAID by keeping old data," International Workshop on Non-Volatile Memory, 2013.
  5. J. Kim, J. Lee, J. Choi, D. Lee, and S. H. Noh, "Enhancing SSD reliability through efficient RAID support," Proc. of the Third ACM SIGOPS Asia-Pacic Conference on Systems (APSYS), 2012.
  6. D. Stodolsky, G. Gibson, and M. Holland, "Parity logging overcoming the small write problem in redundant disk arrays," Proc. of the 20th Annual International Symposium on Computer Architecture, 1993.
  7. J. Wilkes, R. Golding, C. Staelin, and T. Sullivan, "The HP AutoRAID hierarchical storage system," Proc. of the Fifteenth ACM Symposium on Operating Systems Principles (SOSP), 1995.
  8. Bcache [Online]. Available: http://bcache.evilpiepirate.org
  9. Flashcache [Online]. Available: https://github.com/facebook/flashcache/
  10. S. Byan, J. Lentini, A. Madan, L. Pabon, M. Condict, J. Kimmel, S. Kleiman, C. Small, and M. Storer, "Mercury: Host-side flash caching for the data center," Proc. of the IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST), 2012.
  11. A. Varma and Q. Jacobson, "Destage algorithms for disk arrays with non-volatile caches," Proc. of the 22nd Annual International Symposium on Computer Architecture (ISCA), 1995.
  12. T. Johnson and D. Shasha, "2Q: Low overhead high performance buffer management replacement algorithm," Proc. of the 20th International Conference on Very Large Data Bases (VLDB), 1994.
  13. R. Karedla, J. S. Love, and B. G. Wherry, "Caching strategies to improve disk system performance," Computer, Vol. 29, No. 5, 1994.
  14. N. Megiddo and D. S. Modha, "ARC: A self-tuning, low overhead replacement cache," Proc. of the USENIX Conference on File and Storage Technologies (FAST), 2003.

Cited by

  1. Modeling and simulation of the redundant array of inexpensive/independent disks storage for internet of things monitoring servers pp.2050-4578, 2019, https://doi.org/10.1177/0020720918822736