Advertisement

Evaluation of I/O Performance Regulating Function with a Virtual Machine

  • Takashi NagaoEmail author
  • Nasanori Tanabe
  • Kazutoshi Yokoyama
  • Hideo Taniguchi
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1036)

Abstract

A function that keeps the execution speed of a process constant despite the operation of other processes improves computer operational convenience. In this paper, we have described an I/O performance regulating function, which regulates execution time of a process’s I/O request (I/O time) according to the performance level that has been specified. Specifically, the proposed function limits the number of I/O requests for an I/O device, in order to guarantee that the I/O response time of the target process will achieve a specified time. Furthermore, the proposed function delays waking up the process until the time corresponding to the specified performance, in order to regulate the I/O time of the process. Regarding the usage form on the computer, borrowing virtual machines is widespread, and in this paper, we show that the proposed function can regulate the process I/O time on a virtual machine with high accuracy. In practice, the introduced function cannot regulate the timing of individual I/O actions particularly well, because the I/O time on the virtual machine is too short; however, the function can regulate with high accuracy over a longer term by carrying forward the deviations from each individual regulating events.

References

  1. 1.
    Taniguchi, H.: A process schedule mechanism for regulating service processing time. IEICE Trans. Inf. Syst. J81-D-I(4), 386–392 (1998). (Japanese Edition)Google Scholar
  2. 2.
    Nagao, T., Taniguchi, H.: Implementation and evaluation of mechanism for regulating the service time based on controlling the number of I/O requests. IEICE Trans. Inf. Syst. J94-D(7), 1047–1057 (2011). (Japanese Edition)Google Scholar
  3. 3.
    Seelam, S., Romero, R., Teller, P., Buros, B.: Enhancements to Linux I/O scheduling. In: Linux Symposium (2005)Google Scholar
  4. 4.
    Kim, J., Seo, S., Jung, D., Kim, J., Huh, J.: Parameter-Aware I/O management for solid state disks (SSDs). IEEE Trans. Comput. 61(5), 636–649 (2012)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Son, Y., Yeom, H.Y., Han, H.: Optimizing I/O operations in file systems for fast storage devices. IEEE Trans. Comput. 66(6), 1071–1084 (2017)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Yu, Y.J., Shin, D.I., Shin, W., Song, N.Y., Choi, J.W., Kim, H.S., Eom, H., Yeom, H.Y.: Optimizing the block I/O subsystem for fast storage devices. ACM Trans. Comput. Syst. (TOCS) 32(6), 1–48 (2014)CrossRefGoogle Scholar
  7. 7.
    Park, S., Shen, K.: FIOS: a fair, efficient flash I/O scheduler. In: 10th USENIX Conference on File and Storage Technologies (2012)Google Scholar
  8. 8.
    He, S., Wang, Y., Sun, X., Huang, C., Xu, C.: Heterogeneity-aware collective I/O for parallel I/O systems with hybrid HDD/SSD servers. IEEE Trans. Comput. 66(6), 1091–1098 (2017)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Jo, M.H., Ro, W.W.: Dynamic load balancing of dispatch scheduling for solid state disks. IEEE Trans. Comput. 66(6), 1034–1047 (2017)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Won, Y., Jung, J., Choi, G., Oh, J., Son, S., Hwang, J., Cho, S.: Barrier-enabled IO stack for flash storage. In: 16th USENIX Conference on File and Storage Technologies, FAST 2018, pp. 211–226 (2018)Google Scholar
  11. 11.
    Zhang, X., Davis, K., Jiang, S.: Opportunistic data-driven execution of parallel programs for efficient I/O services. In: 2012 IEEE 26th International Parallel and Distributed Processing Symposium (IPDPS), pp. 330–341 (2012)Google Scholar
  12. 12.
    Betti, E., Bak, S., Pellizzoni, R., Caccamo, M., Sha, L.: Real-Time I/O management system with COTS peripherals. IEEE Trans. Comput. 62(1), 45–58 (2013)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Kim, S., Kim, H., Lee, J., Jeong, J.: Enlightening the I/O path: a holistic approach for application performance. In: 15th USENIX Conference on File and Storage Technologies, FAST 2017, pp. 345–358 (2017)Google Scholar
  14. 14.
    Liu, C.L., Layland, J.W.: Scheduling algorithms for multiprogramming in a hard-real-time environment. J. ACM 20(1), 46–67 (1973)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Povzner, A., Kaldewey, T., Brandt, S., Golding, R., Wong, T.M., Maltzahn, C.: Efficient guaranteed disk request scheduling with Fahrrad. In: EuroSys 2008: Third ACM European Conference on Computer Systems, pp. 13–25 (2008)Google Scholar
  16. 16.
    Han, S., Chen, D., Xiong, M., Lam, K., Mok, A.K., Ramamritham, K.: Schedulability analysis of deferrable scheduling algorithms for maintaining real-time data freshness. IEEE Trans. Comput. 63(4), 979–994 (2014)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Zhang, Q., Feng, D., Wang, F., Xie, Y.: An interposed I/O scheduling framework for latency and throughput guarantees. J. Appl. Sci. Eng. 17(2), 193–202 (2014)Google Scholar
  18. 18.
    Kang, D., Jung, S., Tsuruta, R., Takahashi, H.: Range-BW: I/O scheduler for predicable disk I/O bandwidth. In: 2010 2nd International Conference on Computer Engineering and Applications (ICCEA), pp. 175–180 (2010)Google Scholar
  19. 19.
    Povzner, A., Sawyer, D., Brandt, S.: Horizon: efficient deadline-driven disk I/O management for distributed storage systems. In: Proceedings of 19th ACM International Symposium on High Performance Distributed Computing (2010)Google Scholar
  20. 20.
    Tsai, C., Huang, T., Chu, E., Wei, C., Tsai, Y.: An efficient real-time disk-scheduling framework with adaptive quality guarantee. IEEE Trans. Comput. 57(5), 634–657 (2008)MathSciNetCrossRefGoogle Scholar
  21. 21.
    Valente, P., Checconi, F.: High throughput disk scheduling with fair bandwidth distribution. IEEE Trans. Comput. 59(9), 1172–1186 (2010)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Merchant, A., Uysal, M., Padala, P., Zhu, X., Singhal, S., Shin, K.: Maestro: quality-of-service in large disk arrays. In: Proceedings of the 8th ACM International Conference on Autonomic computing (ICAC), pp. 245–254 (2011)Google Scholar
  23. 23.
    Wu, Y., Jia, B., Qi, Z.: IO QoS: a new disk I/O scheduler module with QoS guarantee for cloud platform. In: 2012 4th International Symposium on Information Science and Engineering (ISISE), pp. 441–444 (2012)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Takashi Nagao
    • 1
    • 3
    Email author
  • Nasanori Tanabe
    • 1
    • 4
  • Kazutoshi Yokoyama
    • 2
  • Hideo Taniguchi
    • 1
  1. 1.Graduate School of Natural Science and TechnologyOkayama UniversityOkayama-shiJapan
  2. 2.School of InformationKochi University of TechnologyKami-shiJapan
  3. 3.Hitachi, Ltd.Tokyo-toJapan
  4. 4.NTT Data CorporationTokyo-toJapan

Personalised recommendations