Improving the Average Response Time in Collective I/O

  • Chen Jin
  • Saba Sehrish
  • Wei-keng Liao
  • Alok Choudhary
  • Karen Schuchardt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6960)


In collective I/O, MPI processes exchange requests so that the rearranged requests can result in the shortest file system access time. Scheduling the exchange sequence determines the response time of participating processes. Existing implementations that simply follow the increasing order of file offsets do not necessary produce the best performance. To minimize the average response time, we propose three scheduling algorithms that consider the number of processes per file stripe and the number of accesses per process. Our experimental results demonstrate improvements of up to 50% in the average response time using two synthetic benchmarks and a high-resolution climate application.


Schedule Strategy Versus Versus Versus Versus Access Pattern Average Response Time Versus Versus Versus Versus Versus 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    del Rosario, J., Brodawekar, R., Choudhary, A.: Improved Parallel I/O via a Two-Phase Run-time Access Strategy. In: The Workshop on I/O in Parallel Computer Systems at IPPS (1993)Google Scholar
  2. 2.
    Kotz, D.: Disk-directed I/O for MIMD Multiprocessors. ACM Transactions on Computer Systems 15(1), 41–74 (1997)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Seamons, K., Chen, Y., Jones, P., Jozwiak, J., Winslett, M.: Server-directed Collective I/O in Panda. In: Supercomputing (November 1995)Google Scholar
  4. 4.
    Thakur, R., Gropp, W., Lusk, E.: Users Guide for ROMIO. Technical Report ANL/MCS-TM-234, Argonne National Laboratory (October 1997)Google Scholar
  5. 5.
    Thakur, R., Gropp, W., Lusk, E.: Data Sieving and Collective I/O in ROMIO. In: The Symposium on the Frontiers of Massively Parallel Computation (1999)Google Scholar
  6. 6.
    Ying, L.: Lustre ADIO Collective Write Driver. Lustre Technical White Paper (September 2008)Google Scholar
  7. 7.
    Liao, W., Choudhary, A.: Dynamically Adapting File Domain Partitioning Methods for Collective I/O Based on Underlying Parallel File System Locking Protocols. In: SuperComputing Conference (2008)Google Scholar
  8. 8.
    Liao, W.: Design and Evaluation of MPI File Domain Partitioning Methods under Extent-Based File Locking Protocol. IEEE Transactions on Parallel and Distributed Systems 22(2), 260–272 (2011)CrossRefGoogle Scholar
  9. 9.
    Randall, D., Khairoutdinov, M., Arakawa, A., Grabowski, W.: Breaking the Cloud Parameterization Deadlock. Bull. Amer. Meteor. Soc. 84, 1547–1564 (2003)CrossRefGoogle Scholar
  10. 10.
    Schuchardt, K., Palmer, B., Daily, J., Elsethagen, T., Koontz, A.: IO Strategies and Data Services for Petascale Data Sets from a Global Cloud Resolving Model. Journal of Physics: Conference Series 78 (2007)Google Scholar
  11. 11.
    Li, J., et al.: Parallel netCDF: A High-Performance Scientific I/O Interface. In: SuperComputing Conference (2003)Google Scholar
  12. 12.
    Jain, R., Somalwar, K., Werth, J., Browne, J.: Scheduling Parallel I/O Operations in Multiple Bus Systems. Journal of Parallel and Distributed Computing 16(4), 352–362 (1992)CrossRefzbMATHGoogle Scholar
  13. 13.
    Durand, D., Jain, A., Tseytlin, D.: Applying Randomized Edge Coloring Algorithms to Distributed Communication: An Experimental Study. In: SPAA (1995)Google Scholar
  14. 14.
    Wu, J., Lin, Y., Liu, P.: Efficient Distributed Algorithms for Parallel I/O Scheduling. In: International Conference on Parallel and Distributed Systems (2005)Google Scholar
  15. 15.
    Isaila, F., Singh, D., Carretero, J., Garcia, F.: On Evaluating Decentralized Parallel I/O Scheduling Strategies for Parallel File Systems. In: VECPAR (2006)Google Scholar
  16. 16.
    Chaarawi, M., Chandok, S., Gabriel, E.: Performance Evaluation of Collective Write Algorithms in MPI I/O. In: Allen, G., Nabrzyski, J., Seidel, E., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds.) ICCS 2009. LNCS, vol. 5544, pp. 185–194. Springer, Heidelberg (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Chen Jin
    • 1
  • Saba Sehrish
    • 1
  • Wei-keng Liao
    • 1
  • Alok Choudhary
    • 1
  • Karen Schuchardt
    • 2
  1. 1.Northwestern UniversityEvanstonUSA
  2. 2.Pacific Northwest National LaboratoryRichlandUSA

Personalised recommendations