Rate monotonic scheduling in hard real-time systems

doi:10.1016/0020-0190(93)90266-C

Information Processing Letters

Volume 48, Issue 1, 29 October 1993, Pages 39-45

https://doi.org/10.1016/0020-0190(93)90266-C Get rights and content

Abstract

We present a systematic method that improves previous results to determine if a Real-Time Multiple Tasks-Single Processor or any other isomorphic system can be Rate Monotonic (RM) scheduled, even with a coarse granularity of priority levels.

References (13)

J.Y.T. Leung et al.
On the complexity of fixed-priority scheduling of periodic real-time tasks
Performance Evaluation
(1982)
J. Santos et al.
Priorities and protocols in hard real-time LANs
Comput. Comm.
(1991)
A. Burns
Scheduling hard real-time systems: A review
Software Engineering J.
(1990)
S. Kirkpatrick et al.
Optimization by simulated annealing
Science
(1987)
P.A. Laplante
Real Time Systems Design and Analysis
(1992)
J.P. Lehoczky et al.
Performance of real time bus scheduling algorithms
ACM Performance Evaluation Rev.
(1986)

There are more references available in the full text version of this article.

Cited by (19)

Power saving and fault-tolerance in real-time critical embedded systems
2009, Journal of Systems Architecture
Citation Excerpt :
The RM discipline, a de facto standard at least in the USA [22], is used to define tasks’ priorities. Several methods have been proposed for testing the RM-schedulability of real-time systems [5,23–25]. The application of k-schedulability to the design of fault-tolerant systems has been presented in [9].
In this paper, a method with the double purpose of reducing the consumption of energy and giving a deterministic guarantee on the fault tolerance of real-time embedded systems operating under the Rate Monotonic discipline is presented. A lower bound exists on the slack left free by tasks being executed at their worst-case execution time. This deterministic slack can be redistributed and used for any of the two purposes. The designer can set the trade-off point between them. In addition, more slack can be reclaimed when tasks are executed in less than their worst-case time. Fault-tolerance is achieved by using the slack to recompute the faulty task. Energy consumption is reduced by lowering the operating frequency of the processor as much as possible while meeting all time-constraints. This leads to a multifrequency method; simulations are carried out to test it versus two single frequency methods (nominal and reduced frequencies). This is done under different trade-off points and rates of faults’ occurrence. The existence of an upper bound on the overhead caused by the transition time between frequencies in Rate Monotonic scheduled real-time systems is formally proved. The method can also be applied to multicore or multiprocessor systems.
A least upper bound on the fault tolerance of real-time systems
2005, Journal of Systems and Software
Citation Excerpt :
Also in the figure it is shown that the interval [1,8] is saturated, no background empty slots appear in it and therefore no recovery could be made in a conventionally RM scheduled system. The complexity of the test for the k-schedulability is the same as that for the RM-schedulability that in (Santos and Orozco, 1993) has been proved to be O(n*Tn), where Tn denotes the maximum period in the system. By application of the previous definitions, in the system of the example above, k1 = 5, k2 = 8, k3 = 7, k4 = 5 and k5 = 4.
This paper presents a method to deal with the reexecution of tasks in a hard real-time system subject to temporary faults. The set of tasks follows the Liu and Layland model: they are periodic, independent and preemptible. Time is considered to be slotted. The system is said to be k-schedulable if it is schedulable in spite of the fact that in the interval between its release and its deadline, every task admits that k slots are devoted to uses other than its first execution. In this case, the k slots are used to reexecute tasks subject to temporary faults. Since the value of k can be easily determined, a least upper bound on all the possible combinations of faults that the system can tolerate while meeting the hard time-constraints, follows immediately. The method is bandwidth preserving and the expression of the bound is a diophantic inequality relating k, the execution time and the period of each task. The method is compared to methods proposed by other authors to solve the same problem and it is evaluated through extensive simulations performed on random generated sets of tasks.
New methods for redistributing slack time in real-time systems: Applications and comparative evaluations
2004, Journal of Systems and Software
Citation Excerpt :
Therefore it makes sense to use it whenever possible, especially in applied systems that may find their way to the market. Several methods have been proposed for testing the RM schedulability of real-time systems (Liu and Layland, 1973; Joseph and Pandya, 1986; Lehoczky et al., 1989; Santos and Orozco, 1993). In the Empty Slots method (Santos and Orozco, 1993), time is considered to be slotted and the duration of one slot is taken as the unit of time.
This paper addresses the problem of scheduling hard and non-hard real-time sets of tasks that share the processor. The notions of singularity and k-schedulability are introduced and methods based on them are proposed. The execution of hard tasks is postponed in such a way that hard deadlines are not missed but slack time is advanced to execute non-hard tasks. In a first application, two singularity methods are used to schedule mixed systems with hard deterministic sets and stochastic non-hard sets. They are compared to methods proposed by other authors (servers, slack stealing), background and M/M/1. The metric is the average response time in servicing non-hard tasks and the proposed methods show a good relative performance. In a second application, the previous methods, combined with two heuristics, are used for the on-line scheduling of real-time mandatory/reward-based optional systems with or without depreciation of the reward with time. The objective is to meet the mandatory time-constraints and maximize the reward accrued over the hyperperiod. To the best of the authors’ knowledge, these are the only on-line methods proposed to address the problem and outperform Best Incremental Return, often used as a yardstick.
Flow Scheduling in Data Center Networks with Time and Energy Constraints: A Software-Defined Network Approach
2022, Future Internet
A Survey of Real-Time Scheduling on Multiprocessor Systems
2021, Communications in Computer and Information Science
FPRTR- Fault Persistent Real Time Routing Algorithm for Underwater Acoustic Sensor Networks
2018, SSRN

View all citing articles on Scopus

View full text

Rate monotonic scheduling in hard real-time systems

Abstract

Performance Evaluation

Comput. Comm.

Scheduling hard real-time systems: A review

Software Engineering J.

Optimization by simulated annealing

Science

Real Time Systems Design and Analysis

Performance of real time bus scheduling algorithms

ACM Performance Evaluation Rev.