As Time Goes By: Research on L4-Based Real-Time Systems

  • Hermann HärtigEmail author
  • Michael Roitzsch


The ideas behind the L4 microkernel were born back in the mid-1990’s when Jochen Liedtke reexamined the design of the earlier generation microkernels around Mach. Trying to prove that a minimal kernel can still provide high system performance, he developed first L3, then L4. The fundamental principle of his microkernels is that a concept will only be allowed inside the kernel, if user-land implementations would be unable to achieve the required functionality. This leads to truly minimalist kernels supporting only address spaces, threads and interprocess communication. These basic services are enough to run isolated user-level processes on top of L4. Any additional functionality must be implemented as a server process. This includes components like file systems, networking and even device drivers, all of which are usually subsumed as an operating system personality.


Virtual Machine Address Space Page Frame Overload Situation Disk Utilization 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



We want to thank all our colleagues at TU Dresden who participated in the work presented. Most notably we thank Michael Hohmuth, Jean Wolter and Sebastian Schönberg for their work on Fiasco and the initial L{ 4}Linux, Adam Lackorzynski for his constant maintainership of L{ 4}Linux and his extensive work on system components, Norman Feske for his work on the DOpE window server, Jork Löser for the real-time network theory and infrastructure, Martin Pohlack and Lars Reuther for the real-time disk scheduler and Claude-Joachim Hamann for his work on scheduling theory. We furthermore thank Ronald Aigner, Robert Baumgartl, Martin Borriss, Frank Mehnert, Udo Steinberg, Michael Peter, Henning Schild and of course Jochen Liedtke. We want to extend our thanks to our friends in the L4 community: the L4 groups in Karlsruhe and in Sydney. Our work was supported by the DFG in SFB 358, by several grants from Intel and by the European Union in the ROBIN and OpenTC projects.


  1. 1.
    Atlas A, Bestavros A (1998) Statistical rate monotonic scheduling. In: Proceedings of the IEEE real-time systems symposium (RTSS), p 123Google Scholar
  2. 2.
    Demo CD (2006) URL
  3. 3.
    Feske N, Härtig H (2003) Demonstration of DOpE – a window server for real-time and embedded systems. In: 24th IEEE real-time systems symposium (RTSS), Cancun, Mexico, pp 74–77Google Scholar
  4. 4.
    Hamann CJ, Löser J, Reuther L, Schönberg S, Wolter J, Härtig H (2001) Quality assuring scheduling – deploying stochastic behavior to improve resource utilization. In: 22nd IEEE real-time systems symposium (RTSS), London, UKGoogle Scholar
  5. 5.
    Hamann CJ, Roitzsch M, Reuther L, Wolter J, Härtig H (2007) Probabilistic admission control to govern real-time systems under overload. In: Proceedings of the 19th euromicro conference on real-time systems (ECRTS 07), Pisa, Italy, URL
  6. 6.
    Härtig H, Hohmuth M, Liedtke J, Schönberg S, Wolter J (1997) The performance of μ-kernel-based systems. In: Proceedings of the 16th ACM symposium on operating system principles (SOSP), Saint-Malo, France, pp 66–77Google Scholar
  7. 7.
    Härtig H, Baumgartl R, Borriss M, Hamann CJ, Hohmuth M, Mehnert F, Reuther L, Schönberg S, Wolter J (1998a) DROPS: OS support for distributed multimedia applications. In: Proceedings of the eighth ACM SIGOPS European workshop, Sintra, PortugalGoogle Scholar
  8. 8.
    Härtig H, Hohmuth M, Wolter J (1998b) Taming Linux. In: Proceedings of the 5th annual Australasian conference on parallel and real-time systems (PART ’98), Adelaide, AustraliaGoogle Scholar
  9. 9.
    Härtig H, Zschaler S, Ronald MP, Aigner, Göbel S, Pohl C, Röttger S (2007) Enforceable component-based realtime contracts: Supporting realtime properties from software development to execution. Real-Time Syst 35(1):1–31zbMATHCrossRefGoogle Scholar
  10. 10.
    Hildebrand D (1992) An architectural overview of QNX. In: 1st USENIX workshop on micro-kernels and other kernel architectures, Seattle, WA, pp 113–126Google Scholar
  11. 11.
    Liedtke J, Härtig H, Hohmuth M (1997) OS-controlled cache predictability for real-time systems. In: Third IEEE real-time technology and applications symposium (RTAS), Montreal, Canada, pp 213–223Google Scholar
  12. 12.
    Lin KJ, Natarajan S, Liu JWS (1987) Imprecise results: Utilizing partial computations in real-time systems. In: Proceedings of the IEEE real-time system symposium (RTSS), San Jose, CA, pp 210–217Google Scholar
  13. 13.
    Loeser J, Härtig H (2004) Low-latency hard real-time communication over switched ethernet. In: Proceedings of the 16th euromicro conference on real-time systems (ECRTS), Catania, Italy, pp 13–22Google Scholar
  14. 14.
    Mehnert F, Hohmuth M, Härtig H (2002) Cost and benefit of separate address spaces in real-time operating systems. In: Proceedings of the 23rd IEEE real-time systems symposium (RTSS), Austin, Texas, pp 124–133Google Scholar
  15. 15.
    Peter M, Schild H, Lackorzynski A, Warg A (2009) Virtual machines jailed: Virtualization in systems with small trusted computing bases. In: VDTS ’09: Proceedings of the 1st EuroSys workshop on virtualization technology for dependable systems, ACM, Nuremberg, Germany, pp 18–23, DOI 1518684.1518688Google Scholar
  16. 16.
    Reuther L, Pohlack M (2003) Rotational-position-aware real-time disk scheduling using a dynamic active subset (DAS). In: 24th IEEE real-time systems symposium (RTSS), Cancun, Mexico, pp 374–385Google Scholar
  17. 17.
    Schild H, Lackorzynski A, Warg A (2009) Faithful virtualization on a real-time operating system. In: Proceedings of the 11th real-time Linux workshop, Dresden, GermanyGoogle Scholar
  18. 18.
    Yodaiken V, Barabanov M (1997) A real-time linux. In: Proceedings of the Linux applications development and deployment conference (USELINUX), The USENIX Association, Anaheim, CAGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Department of Computer ScienceTechnische Universität DresdenDresdenGermany

Personalised recommendations