Advertisement

Abstract

Real-time systems must meet, in addition to their functional requirements, requirements regarding their timing behavior. In the case of hard real-time systems, such requirements include the absence of deadline misses. In contrast, for soft real-time systems, a “reasonable” number of deadline misses may happen without leading to a system failure. The usual definition of what a “reasonable” number of deadline misses formally means is based on probability distributions. Another option is to use weakly-hard constraints, which describe bounds on the number of allowed deadline misses in a given time window.

In this paper we show the interest of using weakly-hard constraints for other purposes than describing deadline misses, e.g. to describe execution times or jitter. We discuss in depth the semantics of weakly-hard constraints with an emphasis on how they can be inferred from other weakly-hard constraints and compared to probabilistic constraints.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    ATESST2 project, http://www.atesst.org
  2. 2.
    Bernat, G.: Specification and Analysis of Weakly Hard Real-Time Systems. PhD thesis, Universitat de les Illes Balears (1998)Google Scholar
  3. 3.
    Bernat, G., Burns, A., Llamosí, A.: Weakly hard real-time systems. IEEE Trans. Computers 50(4), 308–321 (2001)CrossRefGoogle Scholar
  4. 4.
    Henia, R., Hamann, A., Jersak, M., Racu, R., Richter, K., Ernst, R.: System level performance analysis - the SymTA/S approach. In: IEE Proceedings Computers and Digital Techniques (2005)Google Scholar
  5. 5.
    Ivers, M., Ernst, R.: Probabilistic Network Loads with Dependencies and the Effect on Queue Sojourn Times. In: Bartolini, N., Nikoletseas, S., Sinha, P., Cardellini, V., Mahanti, A. (eds.) QShine 2009. LNICST, vol. 22, pp. 280–296. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  6. 6.
    Jersak, M., Henia, R., Ernst, R.: Context-aware performance analysis for efficient embedded system design. In: Proceedings of DATE 2004, pp. 1046–1051. IEEE Computer Society (2004)Google Scholar
  7. 7.
    López, J.M., Díaz, J.L., Entrialgo, J., García, D.F.: Stochastic analysis of real-time systems under preemptive priority-driven scheduling. Real-Time Systems 40(2), 180–207 (2008)zbMATHCrossRefGoogle Scholar
  8. 8.
    Quinton, S., Ernst, R., Bertrand, D., Yomsi, P.M.: Challenges and new trends in probabilistic timing analysis. In: Proceedings of DATE 2012 (2012); Hot Topic Special SessionGoogle Scholar
  9. 9.
    Quinton, S., Hanke, M., Ernst, R.: Formal analysis of sporadic overload in real-time systems. In: Proceedings of DATE 2012 (2012)Google Scholar
  10. 10.
    TADL: Timing Augmented Description Language – TIMMO public deliverable D6, http://timmo-2-use.org/timmo/pdf/D6_TIMMO_TADL_Version_2_v12.pdf
  11. 11.
    Thiele, L., Chakraborty, S., Naedele, M.: Real-time calculus for scheduling hard real-time systems. In: Proceedings of ISCAS 2000, vol. 4, pp. 101–104. IEEE Computer Society (2000)Google Scholar
  12. 12.
  13. 13.
    TIMMO-2-USE project, http://timmo-2-use.org

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Sophie Quinton
    • 1
  • Rolf Ernst
    • 1
  1. 1.Institute of Computer Network and EngineeringTU BraunschweigGermany

Personalised recommendations