Trade-Off Between Performance, Fault Tolerance and Energy Consumption in Duplication-Based Taskgraph Scheduling

  • Patrick Eitschberger
  • Simon Holmbacka
  • Jörg Keller
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10793)


Fault tolerance in parallel systems can be achieved by duplicating task executions onto several processing units, so in case one processing unit (PU) fails, the task can continue executing on another unit. Duplicating task execution affects the performance of the system in fault-free and fault cases, and its energy consumption. Currently, there are no tools for properly handling the three-variable optimization problem: Performance \(\leftrightarrow \) Fault Tolerance \(\leftrightarrow \) Energy Consumption, and no facilities for integrating it into an actual system. We present a fault-tolerant runtime system (called RUPS) for user defined schedules, in which the user can give their preferences about the trade-off between performance, energy and fault tolerance. We present an approach for determining the best trade-off for modern multicore architectures and we test RUPS on a real system to verify the accuracy of our approach itself.


Scheduling Fault tolerance Energy efficiency Trade-off Power modeling Optimization Runtime system 


  1. 1.
    Alam, B., Kumar, A.: Fault tolerance issues in real time systems with energy minimization. Int. J. Inf. Comput. Technol. 3(10), 1001–1008 (2013)Google Scholar
  2. 2.
    Albers, S.: Energy-efficient algorithms. Commun. ACM 53(5), 86–96 (2010)CrossRefGoogle Scholar
  3. 3.
    Aupy, G., Benoit, A., Renaud-Goud, P., Robert, Y.: Energy-aware algorithms for task graph scheduling, replica placement and checkpoint strategies. In: Khan, S., Zomaya, A. (eds.) Handbook on Data Centers, pp. 37–80. Springer, New York (2015). Google Scholar
  4. 4.
    Basmadjian, R., de Meer, H.: Evaluating and modeling power consumption of multi-core processors. In: Proceedings of the 3rd International Conference on Future Systems: Where Energy, Computing and Communication Meet (e-Energy 2012), pp. 1–10 (2012)Google Scholar
  5. 5.
    Bland, W.: User level failure mitigation in MPI. In: Caragiannis, I., Alexander, M., Badia, R.M., Cannataro, M., Costan, A., Danelutto, M., Desprez, F., Krammer, B., Sahuquillo, J., Scott, S.L., Weidendorfer, J. (eds.) Euro-Par 2012. LNCS, vol. 7640, pp. 499–504. Springer, Heidelberg (2013). CrossRefGoogle Scholar
  6. 6.
    Cai, Y., Reddy, S.M., Al-Hashimi, B.M.: Reducing the energy consumption in fault-tolerant distributed embedded systems with time-constraint. In: 8th International Symposium on Quality Electronic Design (ISQED 2007), pp. 368–373 (2007)Google Scholar
  7. 7.
    Cichowski, P., Keller, J., Kessler, C.: Modelling power consumption of the Intel SCC. In: Proceedings of the 6th Many-Core Applications Research Community Symposium (MARC 2012), pp. 46–51 (2012)Google Scholar
  8. 8.
    Eitschberger, P., Keller, J.: Efficient and fault-tolerant static scheduling for grids. In: Proceedings of the 14th IEEE International Workshop on Parallel and Distributed Scientific and Engineering Computing (PDSEC 2013), pp. 1439–1448 (2013)Google Scholar
  9. 9.
    Eitschberger, P., Keller, J.: Energy-efficient and fault-tolerant taskgraph scheduling for manycores and grids. In: an Mey, D., et al. (eds.) Euro-Par 2013. LNCS, vol. 8374, pp. 769–778. Springer, Heidelberg (2014). CrossRefGoogle Scholar
  10. 10.
    Fechner, B., Hönig, U., Keller, J., Schiffmann, W.: Fault-tolerant static scheduling for grids. In: Proceedings of the 13th IEEE Workshop on Dependable Parallel, Distributed and Network-Centric Systems (DPDNS 2008), pp. 1–6 (2008)Google Scholar
  11. 11.
    Goel, B., McKee, S.A.: A methodology for modeling dynamic and static power consumption for multicore processors. In: Proceedings of the 30th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2016), pp. 273–282 (2016)Google Scholar
  12. 12.
    Hashimoto, K., Tsuchiya, T., Kikuno, T.: Effective scheduling of duplicated tasks for fault tolerance in multiprocessor systems. IEICE Trans. Inf. Syst. 85, 525–534 (2002)Google Scholar
  13. 13.
    Hongxia, W., Xin, Q.: Dynamic replication of fault-tolerant scheduling algorithm. Open Cybern. Syst. J. 9, 2670–2676 (2015)CrossRefGoogle Scholar
  14. 14.
    Hönig, U., Schiffmann, W.: A comprehensive test bench for the evaluation of scheduling heuristics. In: Proceedings 16th IASTED International Conference on Parallel and Distributed Computing and Systems (PDCS 2004), pp. 437–442 (2004)Google Scholar
  15. 15.
    Kianzad, V., Bhattacharyya, S., Ou, G.: CASPER: an integrated energy-driven approach for task graph scheduling on distributed embedded systems. In: Proceedings of the 16th IEEE International Conference on Application-Specific Systems, Architectures and Processors (ASAP 2005) (2005)Google Scholar
  16. 16.
    Pruhs, K., van Stee, R., Uthaisombut, P.: Speed scaling of tasks with precedence constraints. Theory Comput. Syst. 43(1), 67–80 (2008)MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Singh, J., Auluck, N.: DVFS and duplication based scheduling for optimizing power and performance in heterogeneous multiprocessors. In: Proceedings of the High Performance Computing Symposium (HPC 2014), pp. 22:1–22:8 (2014)Google Scholar
  18. 18.
    Takouna, I., Dawoud, W., Meinel, C.: Accurate mutlicore processor power models for power-aware resource management. In: Proceedings of the 9th IEEE International Conference on Dependable, Autonomic and Secure Computing (DASC 2011), pp. 419–426 (2011)Google Scholar
  19. 19.
    Tosun, S., Mansouri, N., Kandemir, M., Ozturk, O.: An ILP formulation for task scheduling on heterogeneous chip multiprocessors. In: Levi, A., Savaş, E., Yenigün, H., Balcısoy, S., Saygın, Y. (eds.) ISCIS 2006. LNCS, vol. 4263, pp. 267–276. Springer, Heidelberg (2006). CrossRefGoogle Scholar
  20. 20.
    Zhao, L., Ren, Y., Xiang, Y., Sakurai, K.: Fault-tolerant scheduling with dynamic number of replicas in heterogeneous systems. In: 12th IEEE International Conference on High Performance Computing and Communications (HPCC), pp. 434–441 (2010)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Patrick Eitschberger
    • 1
  • Simon Holmbacka
    • 2
  • Jörg Keller
    • 1
  1. 1.Faculty of Mathematics and Computer ScienceFernUniversität in HagenHagenGermany
  2. 2.Faculty of Science and EngineeringAbo Akademi UniversityTurkuFinland

Personalised recommendations