A High-Performance Storage System Based with Dual RAID Engine

  • Jingyu Liu
  • Jinrong Zhang
  • Juan Li
  • Lu LiuEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11910)


With the advent of the 5G, more and more applications use cloud storage to store data. Data becomes the cornerstone of the development of smart society. At the same time, these data have the characteristics of uneven generation rate, large write demand and low read requirement. The dynamic change of load during data storage has new requirements for storage architecture. This paper proposes a storage system that allocates strips in real time based on current load changes. Based on the traditional RAID layout, a dual-engine based high-performance storage system (DSH) is proposed. This system uses software and hardware co-processing architecture to implement strip allocation and address calculation. The strip allocation functions using software and the verification algorithm is implemented by hardware transfer to the FPGA through PCIE. Through experimental analysis shows that the DSH algorithm has a great advantage in saving CPU computing resources and saving disk energy consumption in the dynamic load storage environment.


Disk array Dynamic load Energy-efficient storage Co-design 


  1. 1.
    Meng, X., Ci, X.: Big data management: concepts, techniques and challenges. J. Comput. Res. Dev. 50(01), 146–169 (2013). (in Chinese)Google Scholar
  2. 2.
    Chen, P.M., Lee, E.K., Gibson, G.A., et al.: RAID: high-performance, reliable secondary storage. ACM Comput. Surv. 26(2), 145–185 (1994)CrossRefGoogle Scholar
  3. 3.
    Luo, S., Zhang, G., Wu, C., et al.: Boafft: distributed deduplication for big data storage in the cloud. IEEE Trans. Cloud Comput. (2015)Google Scholar
  4. 4.
    Barroso, L.A., Hlzle, U.: The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines. Synthesis Lectures on Computer Architecture. Morgan & Claypool Publishers, San Rafael (2009)Google Scholar
  5. 5.
    Macko, P., Ge, X., Kelley, J., et al.: SMORE: a cold data object store for SMR drives. In: Proceedings of 34th Symposium on Mass Storage Systems and Technologies (MSST), vol. 35, no. 7, pp. 343–352 (2017)Google Scholar
  6. 6.
    Jie, W., Yu, H., Zuo, P., et al.: Improving restore performance in deduplication systems via a cost-efficient rewriting scheme. IEEE Trans. Parallel Distrib. Syst. 19(7), 121–132 (2019)Google Scholar
  7. 7.
    Xiao, W., Ren, J., Yang, Q.: A case for continuous data protection at block level in disk array storages. IEEE Trans. Parallel Distrib. Syst. 20(6), 898–911 (2009)CrossRefGoogle Scholar
  8. 8.
    Gurumurthi, S., Sivasubramaniam, A., Kandemir, M., et al.: DRPM: dynamic speed control for power management in server class disks. In: Proceedings of the 30th Annual International Symposium on Computer Architecture, pp. 169–179. IEEE, San Diego (2003)Google Scholar
  9. 9.
    Papathanasiou, A.E., Scott, M.L.: Energy efficient prefetching and caching. In: Proceedings of the Annual Conference on USENIX Annual Technical Conference, pp. 24–37. ACM, Boston (2004)Google Scholar
  10. 10.
    Carrera, E.V., Pinheiro, E., Bianchini, R.: Conserving disk energy in network servers. In: Proceedings of International Conference on Supercomputing, pp. 86–97. CiteSeer (2003)Google Scholar
  11. 11.
    Zhu, Q., Chen, Z., Tan, L., et al.: Hibernator: helping disk arrays sleep through the winter. ACM SIGOPS Oper. Syst. Rev. 39(5), 177–190 (2005)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Artificial IntelligenceHebei University of TechnologyTianjinChina
  2. 2.School of Computer Science and TechnologyBeijing Institute of TechnologyBeijingChina
  3. 3.Peng Cheng LaboratoryCenter for Quantum ComputingShenzhenChina

Personalised recommendations