Search Results

Documents authored by Günzel, Mario

Document
DOI: 10.4230/LIPIcs.ECRTS.2025.17
Theoretical Foundations of Utility Accrual for Real-Time Systems

Authors: Jian-Jia Chen, Junjie Shi, Mario Günzel, Georg von der Brüggen, Kuan-Hsun Chen, and Peter Bella

Published in: LIPIcs, Volume 335, 37th Euromicro Conference on Real-Time Systems (ECRTS 2025)

Abstract
Providing guaranteed quantification of properties of soft real-time systems is important in practice to ensure that a system performs correctly most of the time. We study utility accrual for real-time systems, in which the utility of a real-time job is defined as a time utility function with respect to its response time. Essentially, we answer the fundamental questions: Does the utility accrual of a periodic real-time task in the long run converge to a single value? If yes, to which value? We first show that concrete problem instances exist where evaluating the utility accrual by simulating the scheduling algorithm or conducting scheduling experiments in a long run is erroneous. Afterwards, we show how to construct a Markov chain to model the interactions between the scheduling policy, the probabilistic workload of a periodic real-time task, the service provided by the system to serve the task, and the effect on the utility accrual. For such a Markov chain, we also provide the theoretical fundamentals to determine whether the utility accrual converges in the long run and the derivation of the utility accrual if it converges.
Cite as

Jian-Jia Chen, Junjie Shi, Mario Günzel, Georg von der Brüggen, Kuan-Hsun Chen, and Peter Bella. Theoretical Foundations of Utility Accrual for Real-Time Systems. In 37th Euromicro Conference on Real-Time Systems (ECRTS 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 335, pp. 17:1-17:26, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{chen_et_al:LIPIcs.ECRTS.2025.17,
  author =	{Chen, Jian-Jia and Shi, Junjie and G\"{u}nzel, Mario and von der Br\"{u}ggen, Georg and Chen, Kuan-Hsun and Bella, Peter},
  title =	{{Theoretical Foundations of Utility Accrual for Real-Time Systems}},
  booktitle =	{37th Euromicro Conference on Real-Time Systems (ECRTS 2025)},
  pages =	{17:1--17:26},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-377-5},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{335},
  editor =	{Mancuso, Renato},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2025.17},
  URN =		{urn:nbn:de:0030-drops-235950},
  doi =		{10.4230/LIPIcs.ECRTS.2025.17},
  annote =	{Keywords: Soft Real-Time Systems, Utility Accrual, Markov Chains, Dismiss Points}
}
Document
DOI: 10.4230/LIPIcs.ECRTS.2024.4
Tighter Worst-Case Response Time Bounds for Jitter-Based Self-Suspension Analysis

Authors: Mario Günzel, Georg von der Brüggen, and Jian-Jia Chen

Published in: LIPIcs, Volume 298, 36th Euromicro Conference on Real-Time Systems (ECRTS 2024)

Abstract
Tasks are called self-suspending if they can yield their ready state (specifically, releasing the processor while having highest priority) despite being incomplete, for instance, to offload computation to an external device or when waiting on access rights for shared resources or data. This self-suspending behavior requires special treatment when applying analytical results to compute worst-case response time bounds. One typical treatment is modeling self-suspension as release jitter in a so-called jitter-based analysis. The state of the art, when considering task-level fixed-priority scheduling, individually quantifies the jitter term of each higher-priority task by its worst-case response time minus its worst-case execution time. This work tightens the jitter term by taking the execution behavior of the other higher-priority tasks into account. Our improved jitter-based analysis analytically dominates the previous jitter-based analysis. Moreover, an evaluation for synthetically generated sporadic tasks demonstrates that this jitter term results in tighter worst-case response time bounds for self-suspending tasks. We observe an improvement for up to 55.89 % of the tasksets compared to the previous jitter-based analysis.
Cite as

Mario Günzel, Georg von der Brüggen, and Jian-Jia Chen. Tighter Worst-Case Response Time Bounds for Jitter-Based Self-Suspension Analysis. In 36th Euromicro Conference on Real-Time Systems (ECRTS 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 298, pp. 4:1-4:24, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{gunzel_et_al:LIPIcs.ECRTS.2024.4,
  author =	{G\"{u}nzel, Mario and von der Br\"{u}ggen, Georg and Chen, Jian-Jia},
  title =	{{Tighter Worst-Case Response Time Bounds for Jitter-Based Self-Suspension Analysis}},
  booktitle =	{36th Euromicro Conference on Real-Time Systems (ECRTS 2024)},
  pages =	{4:1--4:24},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-324-9},
  ISSN =	{1868-8969},
  year =	{2024},
  volume =	{298},
  editor =	{Pellizzoni, Rodolfo},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2024.4},
  URN =		{urn:nbn:de:0030-drops-203074},
  doi =		{10.4230/LIPIcs.ECRTS.2024.4},
  annote =	{Keywords: Worst-Case Response Time, WCRT, Jitter, Self-Suspension, Analysis}
}
Document
DOI: 10.4230/LIPIcs.ECRTS.2023.10
On the Equivalence of Maximum Reaction Time and Maximum Data Age for Cause-Effect Chains

Authors: Mario Günzel, Harun Teper, Kuan-Hsun Chen, Georg von der Brüggen, and Jian-Jia Chen

Published in: LIPIcs, Volume 262, 35th Euromicro Conference on Real-Time Systems (ECRTS 2023)

Abstract
Real-time systems require a formal guarantee of timing-constraints, not only for individual tasks but also for data-propagation. The timing behavior of data-propagation paths in a given system is typically described by its maximum reaction time and its maximum data age. This paper shows that they are equivalent. To reach this conclusion, partitioned job chains are introduced, which consist of one immediate forward and one immediate backward job chain. Such partitioned job chains are proven to describe maximum reaction time and maximum data age in a universal manner. This universal description does not only show the equivalence of maximum reaction time and maximum data age, but can also be exploited to speed up the computation of such significantly. In particular, the speed-up for synthesized task sets based on automotive benchmarks can be up to 1600. Since only very few non-restrictive assumptions are made, the equivalence of maximum data age and maximum reaction time holds for almost any scheduling mechanism and even for tasks which do not adhere to the typical periodic or sporadic task model. This observation is supported by a simulation of a ROS2 navigation system.
Cite as

Mario Günzel, Harun Teper, Kuan-Hsun Chen, Georg von der Brüggen, and Jian-Jia Chen. On the Equivalence of Maximum Reaction Time and Maximum Data Age for Cause-Effect Chains. In 35th Euromicro Conference on Real-Time Systems (ECRTS 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 262, pp. 10:1-10:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@InProceedings{gunzel_et_al:LIPIcs.ECRTS.2023.10,
  author =	{G\"{u}nzel, Mario and Teper, Harun and Chen, Kuan-Hsun and von der Br\"{u}ggen, Georg and Chen, Jian-Jia},
  title =	{{On the Equivalence of Maximum Reaction Time and Maximum Data Age for Cause-Effect Chains}},
  booktitle =	{35th Euromicro Conference on Real-Time Systems (ECRTS 2023)},
  pages =	{10:1--10:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-280-8},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{262},
  editor =	{Papadopoulos, Alessandro V.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2023.10},
  URN =		{urn:nbn:de:0030-drops-180392},
  doi =		{10.4230/LIPIcs.ECRTS.2023.10},
  annote =	{Keywords: End-to-End, Timing Analysis, Maximum Data Age, Maximum Reaction Time, Cause-Effect Chain, Robot Operating Systems 2 (ROS2)}
}
Document
Artifact
DOI: 10.4230/DARTS.8.1.2
Unikernel-Based Real-Time Virtualization Under Deferrable Servers: Analysis and Realization (Artifact)

Authors: Kuan-Hsun Chen, Mario Günzel, Boguslaw Jablkowski, Markus Buschhoff, and Jian-Jia Chen

Published in: DARTS, Volume 8, Issue 1, Special Issue of the 34th Euromicro Conference on Real-Time Systems (ECRTS 2022)

Abstract
This artifact provides the source code to validate and reproduce the numerical results of the associated paper "Unikernel-Based Real-Time Virtualization under Deferrable Servers: Analysis and Realization". Due to the nature of a close-source project with the company, i.e., EMVICORE GmbH, the source code of the case study in Section 6.2 is not included in this artifact.
Cite as

Kuan-Hsun Chen, Mario Günzel, Boguslaw Jablkowski, Markus Buschhoff, and Jian-Jia Chen. Unikernel-Based Real-Time Virtualization Under Deferrable Servers: Analysis and Realization (Artifact). In Special Issue of the 34th Euromicro Conference on Real-Time Systems (ECRTS 2022). Dagstuhl Artifacts Series (DARTS), Volume 8, Issue 1, pp. 2:1-2:2, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)

Copy BibTex To Clipboard

@Article{chen_et_al:DARTS.8.1.2,
  author =	{Chen, Kuan-Hsun and G\"{u}nzel, Mario and Jablkowski, Boguslaw and Buschhoff, Markus and Chen, Jian-Jia},
  title =	{{Unikernel-Based Real-Time Virtualization Under Deferrable Servers: Analysis and Realization (Artifact)}},
  pages =	{2:1--2:2},
  journal =	{Dagstuhl Artifacts Series},
  ISSN =	{2509-8195},
  year =	{2022},
  volume =	{8},
  number =	{1},
  editor =	{Chen, Kuan-Hsun and G\"{u}nzel, Mario and Jablkowski, Boguslaw and Buschhoff, Markus and Chen, Jian-Jia},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DARTS.8.1.2},
  URN =		{urn:nbn:de:0030-drops-164987},
  doi =		{10.4230/DARTS.8.1.2},
  annote =	{Keywords: Unikernel, Virtualization, Reservation Servers, Deferrable Servers, Cyber-Physical Systems, Real-Time Systems}
}
Document
DOI: 10.4230/LIPIcs.ECRTS.2022.6
Unikernel-Based Real-Time Virtualization Under Deferrable Servers: Analysis and Realization

Authors: Kuan-Hsun Chen, Mario Günzel, Boguslaw Jablkowski, Markus Buschhoff, and Jian-Jia Chen

Published in: LIPIcs, Volume 231, 34th Euromicro Conference on Real-Time Systems (ECRTS 2022)

Abstract
For cyber-physical systems, real-time virtualization optimizes the hardware utilization by consolidating multiple systems into the same platform, while satisfying the timing constraints of their real-time tasks. This paper considers virtualization based on unikernels, i.e., single address space kernels usually constructed by using library operating systems. Each unikernel is a guest operating system in the virtualization and hosts a single real-time task. We consider deferrable servers in the virtualization platform to schedule the unikernel-based guest operating systems and analyze the worst-case response time of a sporadic real-time task under such a virtualization architecture. Throughout synthesized tasksets, we empirically show that our analysis outperforms the restated analysis derived from the state-of-the-art, which is based on Real-Time Calculus. Furthermore, we provide insights on implementation-specific issues and offer evidence that the proposed scheduling architecture can be effectively implemented on top of the Xen hypervisor while incurring acceptable overhead.
Cite as

Kuan-Hsun Chen, Mario Günzel, Boguslaw Jablkowski, Markus Buschhoff, and Jian-Jia Chen. Unikernel-Based Real-Time Virtualization Under Deferrable Servers: Analysis and Realization. In 34th Euromicro Conference on Real-Time Systems (ECRTS 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 231, pp. 6:1-6:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)

Copy BibTex To Clipboard

@InProceedings{chen_et_al:LIPIcs.ECRTS.2022.6,
  author =	{Chen, Kuan-Hsun and G\"{u}nzel, Mario and Jablkowski, Boguslaw and Buschhoff, Markus and Chen, Jian-Jia},
  title =	{{Unikernel-Based Real-Time Virtualization Under Deferrable Servers: Analysis and Realization}},
  booktitle =	{34th Euromicro Conference on Real-Time Systems (ECRTS 2022)},
  pages =	{6:1--6:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-239-6},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{231},
  editor =	{Maggio, Martina},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2022.6},
  URN =		{urn:nbn:de:0030-drops-163239},
  doi =		{10.4230/LIPIcs.ECRTS.2022.6},
  annote =	{Keywords: Unikernel, Virtualization, Reservation Servers, Deferrable Servers, Cyber-Physical Systems, Real-Time Systems}
}
Document
DOI: 10.4230/LIPIcs.ECRTS.2021.10
Hard Real-Time Stationary GANG-Scheduling

Authors: Niklas Ueter, Mario Günzel, Georg von der Brüggen, and Jian-Jia Chen

Published in: LIPIcs, Volume 196, 33rd Euromicro Conference on Real-Time Systems (ECRTS 2021)

Abstract
The scheduling of parallel real-time tasks enables the efficient utilization of modern multiprocessor platforms for systems with real-time constrains. In this situation, the gang task model, in which each parallel sub-job has to be executed simultaneously, has shown significant performance benefits due to reduced context switches and more efficient intra-task synchronization. In this paper, we provide the first schedulability analysis for sporadic constrained-deadline gang task systems and propose a novel stationary gang scheduling algorithm. We show that the schedulability problem of gang task sets can be reduced to the uniprocessor self-suspension schedulability problem. Furthermore, we provide a class of partitioning algorithms to find a stationary gang assignment and show that it bounds the worst-case interference of each task. To demonstrate the effectiveness of our proposed approach, we evaluate it for implicit-deadline systems using randomized task sets under different settings, showing that our approach outperforms the state-of-the-art.
Cite as

Niklas Ueter, Mario Günzel, Georg von der Brüggen, and Jian-Jia Chen. Hard Real-Time Stationary GANG-Scheduling. In 33rd Euromicro Conference on Real-Time Systems (ECRTS 2021). Leibniz International Proceedings in Informatics (LIPIcs), Volume 196, pp. 10:1-10:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)

Copy BibTex To Clipboard

@InProceedings{ueter_et_al:LIPIcs.ECRTS.2021.10,
  author =	{Ueter, Niklas and G\"{u}nzel, Mario and von der Br\"{u}ggen, Georg and Chen, Jian-Jia},
  title =	{{Hard Real-Time Stationary GANG-Scheduling}},
  booktitle =	{33rd Euromicro Conference on Real-Time Systems (ECRTS 2021)},
  pages =	{10:1--10:19},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-192-4},
  ISSN =	{1868-8969},
  year =	{2021},
  volume =	{196},
  editor =	{Brandenburg, Bj\"{o}rn B.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2021.10},
  URN =		{urn:nbn:de:0030-drops-139410},
  doi =		{10.4230/LIPIcs.ECRTS.2021.10},
  annote =	{Keywords: Real-Time Systems, Gang Scheduling, Parallel Computing, Scheduling Algorithms}
}
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact