Multi-dimensional Storage QoS Guarantees for an Object-Based Storage System

  • Fei Mu
  • Jiwu Shu
  • Bigang Li
  • Weimin Zheng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3993)


The Object-based storage is an emerging storage architecture that could easily fulfill multi-dimensional storage QoS requests. This paper focuses on providing QoS guarantees under Object storage infrastructure along the three most prevalent dimensions: capacity, bandwidth and latency through storage resource allocation and IO commands scheduling. Firstly we propose an algorithm on storage resource mapping derived from Toyoda algorithm, which achieves efficient resource utilization through consideration of the OSDs’ serving ability. Secondly we propose an object commands scheduling mechanism and develop a prototype system based on the Lustre filesystem. Through adding timestamp to each object command and scheduling the command queue by final finish time, the system can efficiently fulfill the demands on latency from the front applications.


Object Storage Resource Vector Latency Guarantee Object Storage Device Command Request 


  1. 1.
    Lumb, C.R., Mrchant, A., Alvarez, G.A.: Façade: virtual storage devices with performance guarantees. In: Conference on File and Storage Technology (FAST 2003) (2003)Google Scholar
  2. 2.
    Dimitrijevic, Z., Rangaswami, R.: Quality of service support for real-time storage systems. In: Proc. of Intl. IPSI-2003 Conference (2003)Google Scholar
  3. 3.
    de Miguel, M., Ruiz, J., Garcia, M.: QoS-Aware Component Frameworks. In: Tenth IEEE International Workshop on Quality of Service, May 2002, pp. 161–169 (2002)Google Scholar
  4. 4.
    Mesnier, M., Ganger, G.R., Riedel, E.: Object-Based Storage. IEEE Communications Magazine 41(8), 84–90 (2003)CrossRefGoogle Scholar
  5. 5.
    Webster, R.O.: Information Technology - SCSI Object-Based Storage Device Commands (OSD), Rev 9 (February 2004)Google Scholar
  6. 6.
    Lu, Y., Du, D.H.C., Ruwart, T.: QoS Provisioning Framework for an OSD-based Storage System. In: NASA Goddard Conference on Mass Storage Systems and Technologies (MSST 2005) (2005)Google Scholar
  7. 7.
    Wu, J., Brandt, S.A.: QoS Support in Object-based Storage Devices. In: International Workshop on Storage Network Architecture and Parallel I/O (SNAPI 2005), held in conjunction with the International Conference on Parallel Architectures and Compilation Techniques (PACT 2005), Saint Louis, Missouri, September 17–21 (2005)Google Scholar
  8. 8.
    KleinOsowski, K., Ruwart, T., Lilja, D.J.: Communicating Quality of Service Requirements to an Object-Based Storage Device. In: NASA Goddard Conference on Mass Storage Systems and Technologies (MSST 2005) (2005)Google Scholar
  9. 9.
    Huang, L., Peng, G., Chiueh, T.-C.: Multi-dimensional storage virtualization. SIGMETRICS Perform. Eval. Rev. 32(1), 14–24 (2004)CrossRefGoogle Scholar
  10. 10.
    Schwan, P.: Lustre: Building a file system for 1000-node clusters. In: Proceedings of the 2003 Linux Symposium (July 2003)Google Scholar
  11. 11.
    Lustre project,
  12. 12.
    Braam, P.J.: The Lustre storage architecture (2002)Google Scholar
  13. 13.
    Parekh, A.K., Gallagher, R.G.: A generalized processor sharing approach to flow control in integrated services networks: the multiple node case. IEEE/ACM Transactions on Networking 2(2), 137–150 (1994)CrossRefGoogle Scholar
  14. 14.
    Toyoda, Y.: A simplified algorithm for obtaining approximate solutions to zero-one programming problems. Management Science 21(12), 1417–1427 (1975)MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Fei Mu
    • 1
  • Jiwu Shu
    • 1
  • Bigang Li
    • 1
  • Weimin Zheng
    • 1
  1. 1.Department of Computer Science and TechnologyTsinghua UniversityBeijingP.R. China

Personalised recommendations