정보처리학회논문지A (The KIPS Transactions:PartA)

한국정보처리학회 (Korea Information Processing Society)
권호 표지
DOI QR코드

DOI QR Code

대용량 공유 스토리지 시스템을 위한 토큰 버킷기반 성능 제어 기법

Token-Bucket-based Performance Control Techniques for Large-Scale Shared Storage Systems

  • 발행 : 2005.12.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

스토리지 시스템의 성능과 용량이 증가됨에 따라서, 스토리지 시스템은 이제 다양한 사용자에 의해서 공유되어 사용되는 것이 일반화 되고있는 추세이다. 본 논문은 네트워크에서 널리 이용되는 토큰 버킷을 이용하여 공유 스토리지 시스템 상에서 각 사용자 원하는 스토리지 입출력성능을 확률적으로 보장하는 기법을 설계한다. 또한, 다양한 형태의 작업부하를 이용한 시뮬레이션을 통해서 제안된 알고리즘의 동작 및 성능을 검증한다.

With the increase in I/O performance and capacity, it becomes commonplace that storage systems are shared by multiple storage users. This paper proposes an efficient token-bucket-based performance control technique for the shared storage that can statistically guarantee demanded storage performance from different users. It also verifies the operational characteristics and performance of the proposed scheme under various types of I/O workloads.

키워드

참고문헌

  1. T. Clark, Designing Storage Area Networks: A Practical Reference for Implementing Fibre Channel SANs, Addison Wesley, 1999
  2. Y. Nam, Dynamic Storage QoS Control for Storage Cluster and RAID Performance Enhancement Techniques, Ph.D Dissertation, POSTECH, 2004
  3. J. Wilkes, 'Traveling to rome: QoS specifications for automated storage system management,' Proceedings of International Workshop on QoS, Jun., 2004
  4. L. Huang, G. Peng, T. Chiueh, 'Multi-dimensional storage virtualization,' Proceedings of the Joint International Conf. on Measurement and Modeling of Computer Systems, 2004 https://doi.org/10.1145/1005686.1005692
  5. Y. Nam and C. Park, 'An efficient fair queuing for guaranteed disk bandwidth,' Lecture Notes in Computer Science(Proceedings of Euro-Par2004), Springer-Verlag, Sept., 2004
  6. J. Turner, 'New directions in communications,' IEEE Communications, Oct., 1986
  7. J. Bruno, et al., 'Disk scheduling with quality of service guarantees,' Proceedings of the IEEE International Conf. on Multimedia Computing and Systems, Jun., 1999 https://doi.org/10.1109/MMCS.1999.778459
  8. P. Shenoy and H. Vin, 'Cello: A disk scheduling framework for next-generation operating systems,' Proceedings of SIGMETRICS, Jun., 1998
  9. C. Lumb, A. Merchant, and G. Alvarez, 'Facade: Virtual storage devices with performance guarantees,' Proceedings of Conf. on File and Storage Technologies, Mar., 2003
  10. W. Jin, F. Chase, J. Kaur, 'Interposed proportional sharing for a storage service utility,' Proceedings of the Joint International Conf. on Measurement and Modeling of Computer Systems, 2004 https://doi.org/10.1145/1005686.1005694
  11. A. Veitch and K. Keeton, 'The Rubicon workload characterization tool,' Technical Report HPL -SSP-2003-13, Hewlett Packard, Mar., 2003.