Advertisement

Early Experiences with KTAU on the IBM BG/L

  • Aroon Nataraj
  • Allen D. Malony
  • Alan Morris
  • Sameer Shende
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4128)

Abstract

The influences of OS and system-specific effects on application performance are increasingly important in high performance computing. In this regard, OS kernel measurement is necessary to understand the interrelationship of system and application behavior. This can be viewed from two perspectives: kernel-wide and process-centric. An integrated methodology and framework to observe both views in HPC systems using OS kernel measurement has remained elusive. We demonstrate a new tool called KTAU (Kernel TAU) that aims to provide parallel kernel performance measurement from both perspectives. KTAU extends the TAU performance system with kernel-level monitoring, while leveraging TAU’s measurement and analysis capabilities. As part of the ZeptoOS scalable operating systems project, we report early experiences using KTAU in ZeptoOS on the IBM BG/L system.

Keywords

Kernel performance measurement analysis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
  2. 2.
  3. 3.
  4. 4.
    TAU: Tuning and Analysis Utilities. http://www.cs.uoregon.edu/research/paracomp/tau/
  5. 5.
    ZeptoOS: The Small Linux for Big Computers, http://www.mcs.anl.gov/zeptoos/
  6. 6.
    Gara, A., et al.: Overview of the Blue Gene/L system architecture. IBM Journal of Research and Development 49(2/3), 195–212 (2005)CrossRefGoogle Scholar
  7. 7.
    Mirgorodskiy, A., et al.: Crosswalk: A tool for performance profiling across the user-kernel boundaryGoogle Scholar
  8. 8.
    Tamches, A., et al.: Fine-grained dynamic instrumentation of commodity operating system kernels. In: Operating Systems Design and Implementation (1999)Google Scholar
  9. 9.
    Cantrill, B.M., et al.: Dynamic instrumentation of production systems. In: Proceedings of the 2004 USENIX Annual Technical Conference, Boston, MA, USA (2004)Google Scholar
  10. 10.
    Petrini, F., et al.: The case of the missing supercomputer performance: Achieving optimal performance on the 8,192 processors of ASCI Q. In: SC 2003: Proceedings of the 2003 ACM/IEEE conference on Supercomputing, Washington, DC, USA (2003)Google Scholar
  11. 11.
    Moreira, J.E., et al.: Blue Gene/L programming and operating environment. IBM Journal of Research and Development 49(2/3), 367–376 (2005)CrossRefGoogle Scholar
  12. 12.
    Yaghmour, K., et al.: Measuring and characterizing system behavior using kernel-level event logging. In: USENIX 2000: Proceedings of the 2000 USENIX Annual Technical Conference, Boston, MA, USA (2000)Google Scholar
  13. 13.
    Adiga, N.R., et al.: An overview of the Blue Gene/L supercomputer. In: SC 2002: Proceedings of the 2002 ACM/IEEE conference on Supercomputing (2002)Google Scholar
  14. 14.
    Wisniewski, R.W., et al.: Efficient, unified, and scalable performance monitoring for multiprocessor operating systemsGoogle Scholar
  15. 15.
    Sharma, S., et al.: A Framework for Analyzing Linux System Overheads on HPC Applications. In: LACSI 2005: Proceedings of the 2005 Los Alamos Computer Science Institute Symposium, Santa Fe, NM, USA (2005)Google Scholar
  16. 16.
    Jones, T., et al.: Improving the scalability of parallel jobs by adding parallel awareness to the operating system. In: SC 2003: Proceedings of the 2003 ACM/IEEE conference on Supercomputing, Washington, DC, USA (2003)Google Scholar
  17. 17.
    Nagel, W.E., et al.: VAMPIR: Visualization and analysis of MPI resources. Supercomputer 12(1), 69–80 (1996)Google Scholar
  18. 18.
    Etsion, Y., et al.: Fine Grained Kernel Logging with KLogger: Experience and InsightsGoogle Scholar
  19. 19.
    Ruan, Y., et al.: Making the “Box” Transparent: System Call Performance as a First-class Result. In: USENIX 2004: Proceedings of the 2004 USENIX Annual Technical Conference, Boston, MA, USA (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Aroon Nataraj
    • 1
  • Allen D. Malony
    • 1
  • Alan Morris
    • 1
  • Sameer Shende
    • 1
  1. 1.Performance Research Laboratory, Department of Computer and Information ScienceUniversity of OregonEugeneUSA

Personalised recommendations