A Lightweight Dynamic Application Monitor for SMP Clusters

  • Karl Fürlinger
  • Michael Gerndt
Conference paper


In the Peridot project our goal is a portable environment for performance analysis for terascale computing that realizes a combination of new concepts including distribution, on-line processing and automation. In this paper we present the lightweight dynamic application monitoring approach that forms the basis for this environment. In our distributed monitoring solution we try to minimize the perturbation of the target application while retaining flexibility with respect to configurability and close-to-source filtering and pre-processing of performance data. We achieve this goal by separating the monitor in a passive monitoring library linked to the application and an active component called runtime information producer (RIP) which provides performance data (metric and event based) for individual nodes of the system through a monitoring request interface (MRI). By querying a directory service, tools discover which RIPs provide the data they need.


Performance Data Directory Service Target Application Performance Counter Application Thread 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bartosz Balis, Marian Bubak, Wlodzimierz Funika, Tomasz Szepieniec, and Roland Wismüller. Monitoring of Interactive Grid Applications. To appear in Proceedings of Dagstuhl Seminar 02341 on Performance Analysis and Distributed Computing. Kluiver Academi Publishers. 2003.Google Scholar
  2. 2.
    Bernd Mohr, Allen D. Malony, Sameer Shende, and Felix Wolf. Towards a Performance Tool Interface for OpenMP: An Approach Based on Directive Rewriting. In EWOMP'01 Third European Workshop on OpenMP, Sept. 2001.Google Scholar
  3. 3.
    The Top 500 Supercomputer Sites. http://www.top500.orgGoogle Scholar
  4. 4.
    Michael Gerndt and Karl Fürlinger. Towards Automatic Performance Analysis for Large Scale Systems. At the 10th International Workshop on Compilers for Parallel Computers (CPC 2003). Amsterdam, The Netherlands. January 2003.Google Scholar
  5. 5.
    The Hitachi Performance Monitor Function (Hitachi Confidential).Google Scholar
  6. 6.
    S. Browne and J. Dongarra and N. Garner and K. London and P. Mucci. A Scalable Cross-Platform Infrastructure for Application Performance Tuning Using Hardware Counters. Proc. SC'2000, November 2000.Google Scholar
  7. 7.
    T. Fahringer, M. Gerndt, G. Riley, and J.L. Träff. Formalizing OpenMP Performance Properties with the APART Specification Language (ASL), International Workshop on OpenMP: Experiences and Implementation, Lecture Notes in Computer Science, Springer Verlag, Tokyo, Japan, pp. 428–439, October 2000.Google Scholar
  8. 8.
    T. Fahringer, M. Gerndt, G. Riley, and J.L. Träff. Knowledge Specification for Automatic Performance Analysis. APART Technical Report. http://www.fz-juelich.de/apart. 2001.Google Scholar
  9. 9.
    CrossGrid Project: http://www.eu-crossgrid.orgGoogle Scholar
  10. 10.
    T. Ludwig, R. Wismüller, V. Sunderam, and A. Bode. OMIS — On-line Monitoring Interface Specification (Version 2.0). Shaker Verlag, Aachen Vol 9, LRR-TUM Research Report Series, (1997). http://wwwbode.in.tum.de/~omis/OMIS/Version-2.0/version-2.0.ps.gzGoogle Scholar
  11. 11.
    Dynamic Probe Class Library. http://oss.software.ibm.com/dpcl/Google Scholar
  12. 12.
    Dyninst. An Application Program Interface (API) for Runtime Code Generation. http://www.dyninst.orgGoogle Scholar
  13. 13.
    Ch. Thiffault, M. Voss, S. T. Healey and S. W. Kim. Dynamic Instrumentation of Large-Scale MPI/OpenMP Applications. To appear in Proc. of IPDPS'2003: International Parallel and Distrubuted Processing Symposium, Nice, France, April 2003.Google Scholar
  14. 14.
    B. Tierney, R. Aydt, D. Gunter, W. Smith, M. Swany, V. Taylor, and R. Wolski. A Grid Monitoring Architecture. http://www-didc.lbl.gov/GGF-PERF/GMA-WG/papers/GWD-GP-16-2.pdfGoogle Scholar
  15. 15.
    W. E. Nagel, A. Arnold, M. Weber, H. C. Hoppe, and K. Solchenbach. VAMPIR: Visualization and analysis of MPI resources. Supercomputer, 12(1):69–80, January 1996. http://www.pallas.com/e/products/vampir/index.htmGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Karl Fürlinger
    • 1
  • Michael Gerndt
    • 1
  1. 1.Institut für Informatik, Lehrstuhl für Rechnertechnik und RechnerorganisationTechnische Universität MünchenMünchen

Personalised recommendations