Abstract

We investigate the mathematical properties of event bound functions as they are used in the worst-case response time analysis and utilization tests. We figure out the differences and similarities between the two approaches. Based on this analysis, we derive a more general form do describe events and event bounds. This new unified approach gives clear new insights in the investigation of real-time systems, simplifies the models and will support algebraic proofs in future work. In the end, we present a unified analysis which allows the algebraic definition of any scheduler. Introducing such functions to the real-time scheduling theory will lead two a more systematic way to integrate new concepts and applications to the theory. Last but not least, we show how the response time analysis in dynamic scheduling can be improved.

Highlights

  • If we have a careful review of existing work in real-time scheduling theory, mainly two different approaches to satisfy the real-time capability of an embedded system exist: the bound test or, in more general, the utilization based approach1 and the response time analysis

  • As we will later see in this paper, the concept of a unified event bound allows the integration of different task models developed during the past decades to only one analysis approach

  • Because we defined a compact unified event, request- and demand bound by using an integral and we model its limits by a Heaviside function, we can combine the result of the network respective the real-time calculus with the work done in established scheduling theory

Read more

Summary

Introduction

If we have a careful review of existing work in real-time scheduling theory, mainly two different approaches to satisfy the real-time capability of an embedded system exist: the bound test or, in more general, the utilization based approach and the response time analysis. Looking at related work, the two approaches are different in a tiny detail: while the utilization based computations built on the floor operator, the response time analysis uses the ceiling operator. Looking closer to previous work leads to problems in formulating a utilization-based test for static scheduling and a response time analysis for dynamic scheduling. The work of [12] and [43] show the limitations on floor and ceil operators in the context of the real-time scheduling theory Both papers postulate new analysis techniques if an event count with more mathematical expressiveness is known. The idea of this paper is to adapt mathematical models used in physics, signal- and control theory to the problem of real-time scheduling analysis. – we adopt assumptions of the analysis of arbitrary deadlines to the analysis of response times in dynamic scheduled systems and found a deterministic and tighter analysis as in previous work

Related work
Model of computation
Events
Motivation to a unified theory
Event bound approaches to real-time systems analysis
Problem formulation
Goals and organization
The unified event bound function
A mathematical view on events and tasks
Modeling jobs
Events as Dirac delta
Event models
To count or not to count
Counting by integrating dirac deltas
Traditional unified event bound
Unified analysis of real-time systems
A general event model
The request bound of interfering jobs
Analysis preliminaries
Unified response time analysis
Relationship to related work
Bursty events in response time analysis
Response time analysis in dynamic scheduling
Conclusion
A Mathematical framework
B Examples

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.