Skip to main content

Abstract

To develop optimal parallel I/O subsystems, one must have a thorough understanding of the workload characteristics of parallel I/O and its exploitation of the associated parallel file system. Presented are the results of a study conducted to analyze the parallel I/O workloads of several applications on a parallel processor using the Vesta parallel file system. Traces of the applications are obtained to collect system events, communication events, and parallel I/O events. The traces are then analyzed to determine workload characteristics. The results show I/O request rates on the order of hundreds of requests per second, a large majority of requests are for small amounts of data (less than 1500 bytes), a few requests are for large amounts of data (on the order of megabytes), significant file sharing among processes within a job, and strong temporal, traditional spatial, and interprocess spatial locality.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 219.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. M.G. J.H. Hartman M.D. Kupfer K.W. Shirriff Baker and J.K. Ousterhout. Measurements of a distributed file system. ACM Symposium on Operating System Principles, pages 198–212., 1991.

    Google Scholar 

  2. S.J. C. Benveniste Baylor and Y. Hsu. Performance evaluation of a parallel i/o architecture. International Conference on Supercomputing, pages 404–413., July 1995.

    Google Scholar 

  3. M.L. A. Greenberg C. Stanfill Best and L.W. Tucker. Cmmd i/o: A parallel unix i/o. International Parallel Processing Symposium, pages 489–495., April 1993.

    Google Scholar 

  4. P.F. Corbett and D.G. Feitelson. Design and implementation of the vesta parallel file system. Scalable High Performance Computing Conference, pages 63–70., 1994.

    Google Scholar 

  5. P.F. D.G. Feitelson J-P. Prost Corbett and SJ. Baylor. Parallel access to files in the vesta file system. Supercomputing’93, pages 472–481., November 1993.

    Google Scholar 

  6. T.W. Crockett. File concepts for parallel i/o. Supercomputing’89, pages 574–579., 1989.

    Google Scholar 

  7. E. DeBenedictis and J.M. Rosario, ncube parallel i/o software. International Phoenix Conference on Computers and Communications, pages 117–124., April 1992.

    Google Scholar 

  8. J.M. del Rosario and A. Choudary. High performance i/o for parallel computers: Problems and prospects. Computer, 27(3):59–68., March 1994.

    Article  Google Scholar 

  9. P.C. Dibble. A Parallel Interleaved File System. Univeristy of Rochester, March 1990.

    Google Scholar 

  10. Alverson et. al. The tera computer system. International Conference on Super-computing, pages 1–6., June 1990.

    Google Scholar 

  11. Corbett et. al. Parallel file systems for the ibm sp computers. IBM System Journal, 34(2):222–248.,1995.

    Article  Google Scholar 

  12. Hayes et. al. A microporcessor-based hypercube supercomputer. IEEE Micro, 6(5):6–17., October 1986.

    Article  Google Scholar 

  13. Leiserson et. al. The network architecture of the connection machine cm-5. 4th Symposium on Parallel Algorithms and Architectures, pages 272–285., June 1992.

    Google Scholar 

  14. International Business Machines Corporation. Scalable POWERparallel Systems High-Performance Technical Computing Solutions, March 1994.

    Google Scholar 

  15. E.T. Kalns and Y. Hsu. Video-on-demand using the vesta parallel file system. Third Annual Workshop on I/O in Parallel and Distributed Systems, pages 30–46., April 1995.

    Google Scholar 

  16. Kendal Square Research. KSR1 Technology Background, January 1992.

    Google Scholar 

  17. D. Kotz. Multiprocessor file system interfaces. International Conference on Parallel and Distributed Information Systems, pages 194–201., 1993.

    Google Scholar 

  18. D. Kotz and N. Nieuwejaar. Dynamic file-access characteristics of a production parallel scientific workload. Supercomputing’94, pages 640–649., November 1994.

    Google Scholar 

  19. O. Krieger and M. Stumm. Hfs: A flexible file system for large-scale multiprocessors. DAGS/PC Symposium, pages 6–14., June 1993.

    Google Scholar 

  20. P. Messina. The concurrent supercomputing consortium: Year 1. IEEE Parallel and Distributed Technology, 1(1):9–16., February 1993.

    Article  Google Scholar 

  21. E.L. Miller and R.H. Katz. Input/output behavior of supercomputer applications. Supercomputing’91, pages 567–576., November 1991.

    Google Scholar 

  22. E.L. Miller and R.H. Katz. Rama: A file system for massively-parallel computers. IEEE Symposium on Mass Storage Systems, pages 163–168., April 1993.

    Google Scholar 

  23. ParaSoft Corporation. Express C Reference Guide, 1990.

    Google Scholar 

  24. B.K. Pasquale and G.C. Polyzos. A static analysis of i/o characteristics of scientific applications in a production workload. Supercomputing’93, pages 388–397., November 1993.

    Google Scholar 

  25. B.K. Pasquale and G.C. Polyzos. Dynamic i/o characterization of i/o intensive scientific applications. Supercomputing’94, pages 660–669., November 1994.

    Google Scholar 

  26. P. Pierce. A concurrent file system for a high parallel mass storage subsystem. Fourth Conference on Hypercube Computers and Applications, pages 155–160., 1989.

    Google Scholar 

  27. A.L.N. Reddy and P. Banerjee. A study of i/o behavior of perfect benchmarks on a multiprocessor. International Symposium on Computer Architecture, pages 312–321., 1990.

    Google Scholar 

  28. C.B. D.G. Shea D.G. Grice P.H. Hochschild Stunkel and M. Tsao. The sp1 high-performance switch. Scalable High Performance Computing Conference, May 1994.

    Google Scholar 

  29. C.E. Y.-H. Liu C. Benveniste L. Chen Wu and W.H. Chiang. Trace-based analysis and tuning for distributed parallel applications. International Conference on Parallel and Distributed Systems, pages 716–723., December 1994.

    Google Scholar 

  30. C.E. Y.-H. Liu Y. Hsu Wu. Timestamp consistency and trace-driven analysis for distributed parallel systems. International Parallel Processing Symposium, pages 680–686., April 1995.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1996 Kluwer Academic Publishers

About this chapter

Cite this chapter

Baylor, S.J., Wu, C.E. (1996). Parallel I/O Workload Characteristics Using Vesta. In: Jain, R., Werth, J., Browne, J.C. (eds) Input/Output in Parallel and Distributed Computer Systems. The Kluwer International Series in Engineering and Computer Science, vol 362. Springer, Boston, MA. https://doi.org/10.1007/978-1-4613-1401-1_7

Download citation

  • DOI: https://doi.org/10.1007/978-1-4613-1401-1_7

  • Publisher Name: Springer, Boston, MA

  • Print ISBN: 978-1-4612-8607-3

  • Online ISBN: 978-1-4613-1401-1

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics