A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems

  • Axel KellerEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10773)


This paper describes a data structure and a heuristic to plan and map arbitrary resources in complex combinations while applying time dependent constraints. The approach is used in the planning based workload manager OpenCCS at the Paderborn Center for Parallel Computing (PC\(^2\)) to operate heterogeneous clusters with up to 10000 cores. We also show performance results derived from four years of operation.


Scheduling Planning Mapping Workload management 



I would like to thank Christoph Kleineweber, Dr. Lars Schäfers, and Dr. Jörn Schumacher for their valuable contribution to the current OpenCCS release.


  1. 1.
    Battre, D., Hovestadt, M., Kao, O., Keller, A., Voss, K.: Planning-based scheduling for SLA-awareness and grid integration. In: Proceedings of the 26th Workshop of the UK Planning and Scheduling Special Interest Group (PlansSIG 2007) (2007)Google Scholar
  2. 2.
    Brune, M., Gehring, J., Keller, A., Reinefeld, A.: RSD - resource and service description. In: Schaeffer, J. (ed.) High Performance Computing Systems and Applications (HPCS 1998), pp. 193–206. Kluwer Academic Press, Dordrecht (1998)CrossRefGoogle Scholar
  3. 3.
    OpenCCS Manual, July 2017.
  4. 4.
    Chlumský, V., Klusáček, D., Ruda, M.: The extension of torque scheduler allowing the use of planning and optimization in grids. Comput. Sci. 13(2), 5–19 (2012). CrossRefGoogle Scholar
  5. 5.
    Curino, C., Difallah, D.E., Douglas, C., et al.: Reservation-based scheduling: if you’re late don’t blame us! Tech-report MSR-TR-2013-108, Microsoft (2013)Google Scholar
  6. 6.
    Hovestadt, M., Kao, O., Keller, A., Streit, A.: Scheduling in HPC resource management systems: queuing vs. planning. In: Feitelson, D., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2003. LNCS, vol. 2862, pp. 1–20. Springer, Heidelberg (2003). CrossRefGoogle Scholar
  7. 7.
    Jyothi, S.A., Curino, C., Menache, I., et al.: Morpheus: towards automated SLOs for enterprise clusters. In: Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2016), November 2016Google Scholar
  8. 8.
    Kay, J., Lauder, P.: A fair share scheduler. Commun. ACM 31, 44–55 (1998)CrossRefGoogle Scholar
  9. 9.
    Kleban, S.D., Clearwater, S.: Fair share on high performance computing systems: what does fair really mean? In: Proceedings of 3rd IEEE International Symposium on Cluster Computing and the Grid (CCGrid 2003), pp. 145–153. IEEE Computer Society (2003)Google Scholar
  10. 10.
    Lifka, D.A.: The ANL/IBM SP scheduling system. In: Feitelson, D.G., Rudolph, L. (eds.) JSSPP 1995. LNCS, vol. 949, pp. 295–303. Springer, Heidelberg (1995). CrossRefGoogle Scholar
  11. 11.
    Mu’alem, A., Feitelson, D.G.: Utilization, predictability, workloads, and user runtime estimates in scheduling the IBM SP2 with backfilling. IEEE Trans. Parallel Distrib. Syst. 12(6), 529–543 (2001)CrossRefGoogle Scholar
  12. 12.
    PBSPro Open Source, January 2017.
  13. 13.
    PC\(^2\): Paderborn Center for Parallel Computing, July 2017.
  14. 14.
    Schneider, J., Linnert, B.: List-based data structures for efficient management of advance reservations. Int. J. Parallel Prog. 42, 77–93 (2014). CrossRefGoogle Scholar
  15. 15.
  16. 16.
    Tumanov, A., Zhu, T., Park, J.W., et al.: TetriSched: global rescheduling with adaptive plan-ahead in dynamic heterogeneous clusters. In: Proceedings of the 11th European Conference on Computer Systems (EuroSys 2016), April 2016.
  17. 17.
    Vavilapalli, V.K., Murthy, A.C., Douglas, C., et al.: Apache Hadoop YARN: yet another resource negotiator. In: Proceedings of the 4th Annual Symposium on Cloud Computing (SOCC 2013), October 2013.

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Paderborn Center for Parallel ComputingPaderborn UniversityPaderbornGermany

Personalised recommendations