DOI QR코드

DOI QR Code

오픈스택 기반 객체 스토리지를 위한 전력관리 기법과 성능 평가

Power Management Strategy and Performance Evaluation for OpenStack Object Storage

  • 투고 : 2016.03.18
  • 심사 : 2016.04.07
  • 발행 : 2016.06.15

초록

객체 기반 스토리지 솔루션은 비정형 데이터를 효과적으로 처리할 뿐만 아니라 보안, 확장성에서 기존 블록 스토리지보다 장점을 갖고 있다. 그러나 전력관리 관점에서, 객체 기반 스토리지가 기록하는 많은 수의 사본들은 여러 서버들을 유휴상태에서 불필요한 전력을 소모하게 하는 문제가 있다. 이 문제를 해결하기 위해서는 작업량에 따라 유휴상태 서버들의 전원모드를 변화시키는 전력관리기법의 적용이 필요하다. 본 논문에서는 프락시 서버에서 보내는 작업량 정보를 기반으로 스토리지 서버의 전력 상태를 동적으로 전환하는 전력관리 기법을 제안한다. 실험 결과, 제안한 전력관리 기법은 오픈스택 기반 스위프트 객체 스토리지에서 전체 전력 소모량을 12% 감소시키는 것으로 나타났다.

Object-based storage is an efficient storage solution that can handle unstructured data and shows better security and scalability than traditional block-based storage. However, in terms of power management, Object-based storage writes multiple copies in storage cluster, hence many servers consume unnecessary power in idle state. In order to resolve this problem, it is necessary to apply power management strategy by adjusting power mode of servers in idle state according to their workloads. In this paper, we proposed a new dynamic power management (DPM) method to transform power mode of storage servers dynamically according to workload information sent from proxy server. The experimental result shows that the proposed power management technic reduces total power consumption by 12% in the OpenStack based Swift object storage.

키워드

과제정보

연구 과제 주관 기관 : 한국연구재단

참고문헌

  1. M. Mesnier, G. R. Ganger and E. Riedel, "Object-Based Storage," IEEE Communications Magazine, Vol. 41, No. 8, pp. 84-90, Aug. 2003.
  2. M. Factor, K. Meth, et al., "Object storage: The future building block for storage systems," Proc. of IEEE: Local to Global Data Interoperability-Challenges and Technologies, pp. 119-123, 2005.
  3. Y. Yi, and S. Bhatti, "Energy measurement for the cloud," Proc. of IEEE: Parallel and Distributed Proc. with Applications (ISPA), International Symposium, pp. 619-624, 2010.
  4. T. Clark, A. Yoder, "Best practices for energy efficient storage operations Version 1.0," SNIA Green Initiative, Oct. 2008.
  5. A. Beloglazov, R. Buyya, "OpenStack Neat: a framework for dynamic and energy-efficient consolidation of virtual machines in OpenStack clouds," Journal of Concurrency and Computation: Practice and Experience, Vol. 27, No. 5, pp. 1310-1333, 2015. https://doi.org/10.1002/cpe.3314
  6. F. Wuhib, R. Stadler, et al., "Dynamic resource allocation with management objectives-Implementation for an OpenStack cloud," Proc. of IEEE: Network and service management 8th international conference and workshop on systems virtualiztion management, pp. 309-315, 2012.
  7. V. Cima, B. Grazioli, and S. Murphy, et al., "Adding energy efficiency to Openstack," Proc. of IEEE: Sustainable Internet and ICT for Sustainability (SustainIT), pp. 1-8, 2015.
  8. L. Benini, A. Bogliolo and G. De Micheli, "A survey of design techniques for system-level dynamic power management," Journal of IEEE: Transactions on Very Large Scale Integration Systems, Vol. 8, No. 3, pp. 299-316, 2000. https://doi.org/10.1109/92.845896
  9. C. J. Ahn, T. G. Song, D. H. Kim, "Circulation Power Management strategy for The OpenStack Object Storage System," Proc. of KIISE: the 42th Winter Conference, pp. 1292-1294, 2015. (in Korean)