A Utilization-Based Schedulability Test of Real-Time Systems Running on a Multiprocessor Virtual Machine

Niyizamwiyitira, Christine; Lundberg, Lars

doi:10.1093/comjnl/bxz005

Cited by 3 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The task order was based on recovery time constraints. A distinct approach of utilization-based task scheduling has been proposed by Niyizamwiyitira and Lundberg (2019) for multiprocessor real-time systems. This utilization-based technique is modified and used in our paper for task allocation along with criticality-based allocation.…”

Section: Background Of Fault-tolerant Task Scheduling In Real-time Sy...mentioning

confidence: 99%

Utilization and criticality based fault-tolerant scheduling in multicore mixed critical systems

Godabole¹,

Bhole²

2023

IJPCC

View full text Add to dashboard Cite

Purpose The main purpose of the paper is timing analysis of mixed critical applications on the multicore system to identify an efficient task scheduling mechanism to achieve three main objectives improving schedulability, achieving reliability and minimizing the number of cores used. The rise in transient faults in embedded systems due to the use of low-cost processors has led to the use of fault-tolerant scheduling and mapping techniques. Design/methodology/approach The paper opted for a simulation-based study. The simulation of mixed critical applications, like air traffic control systems and synthetic workloads, is carried out using a litmus-real time testbed on an Ubuntu machine. The heuristic algorithms for task allocation based on utilization factors and task criticalities are proposed for partitioned approaches with multiple objectives. Findings Both partitioned earliest deadline first (EDF) with the utilization-based heuristic and EDF-virtual deadline (VD) with a criticality-based heuristic for allocation works well, as it schedules the air traffic system with a 98% success ratio (SR) using only three processor cores with transient faults being handled by the active backup of the tasks. With synthetic task loads, the proposed criticality-based heuristic works well with EDF-VD, as the SR is 94%. The validation of the proposed heuristic is done with a global and partitioned approach of scheduling, considering active backups to make the system reliable. There is an improvement in SR by 11% as compared to the global approach and a 17% improvement in comparison with the partitioned fixed-priority approach with only three processor cores being used. Research limitations/implications The simulations of mixed critical tasks are carried out on a real-time kernel based on Linux and are generalizable in Linux-based environments. Practical implications The rise in transient faults in embedded systems due to the use of low-cost processors has led to the use of fault-tolerant scheduling and mapping techniques. Originality/value This paper fulfills an identified need to have multi-objective task scheduling in a mixed critical system. The timing analysis helps to identify performance risks and assess alternative architectures used to achieve reliability in terms of transient faults.

show abstract

Section: Background Of Fault-tolerant Task Scheduling In Real-time Sy...mentioning

confidence: 99%

Utilization and criticality based fault-tolerant scheduling in multicore mixed critical systems

Godabole¹,

Bhole²

2023

IJPCC

View full text Add to dashboard Cite

show abstract

“…Unlike any other user given tasks, device drivers are not preemptible and therefore any request to the device runs to the completion. One virtual device generates busy looping inside the kernel and the other regulates a periodic task to run inside the kernel [32]. In the course of the completion of the operations in the devices through the drivers, it surely preempts the kernel in case of the preemptible kernels.…”

Section: Experimental Modelmentioning

confidence: 99%

Measurement of Kernel Preemption Time of Real Time Operating Systems

2023

MCET

View full text Add to dashboard Cite

In a Real Time System, when a high priority task is scheduled, it preempts ongoing lower priority tasks and sometimes it preempts even the kernel too. In normal cases, the time needed for the preemption is too small and hence is not considered in task scheduling. But, in some mission critical hard real time systems, even a small fraction of a second should be taken into account as it could affect the deadline. This research work proposes two models -embedded model and software model, among which the latter has been used for the experiment that calculates the kernel preemption time. The hardware model consists of a triangular wave generator called TRIANG that takes timer values from real time tasks and sends outputs to a comparator module. Finally, the comparator compares the time differences, and hence, calculates the kernel preemption time. Whereas the software model uses the RT-Linux architecture in which device drivers are used instead of hardware components. A high precision timer clock is also used to measure the task release times.The results from the experiments show that the release time jitter due to the kernel preemption is found to be fluctuating in the range of -94 and +93 microseconds in 3% of the cases. So, the kernel preemption time for the hard and mission critical real time systems is taken to be less than 99 microseconds. Whereas 85% of the cases have release time jitters of single digit only. So, the kernel preemption time in average case is considered to be less than 9 microseconds.

show abstract

“…Scheduling must ensure the completion of the execution of each task within the deadline associated with it, taking into consideration task priorities. The purpose of scheduling is to utilize most of the processor time without failures in the real-time system [6] . In addition, scheduling should limit simultaneous access to system resources in order to reduce conflicts between tasks and obtain a more efficient system, and make the scheduling process optimal.…”

Section: -Scheduling In Real-time Systemsmentioning

confidence: 99%

“…Figure (6) shows context switching overheads scenario results when working on two, four and eight cores.…”

Section: Context Switching Scenariomentioning

confidence: 99%

Development of Energy- Efficient Load Balancing Scheduling Algorithm in Real-time Systems

نتيفه¹,

حجازية²

2022

Journal of Engineering Sciences and Information Technology

View full text Add to dashboard Cite

Real- time systems are considered as one of the most important topics that have attracted the attention of researchers in various scientific and technical fields due to their widespread in many fields of communication, informatics, operating systems and automatic control systems. The basic idea in real- time systems is the execution of a set of tasks that are assigned to CPUs, within a time constraint associated with each of them, and this time constraint is called a deadline. Task scheduling in real- time systems is the main factor in determining the success or failure of the system. Therefore, many studies have imposed suggestions and hypotheses for improving scheduling, according to the underlined platform, whether it is single- processor, multi- processor, or multi- core processor. Researchers have recently focused on studying and providing solutions to scheduling problems, taking into account energy consumption since energy consumption today plays an important role in determining the efficiency and reliability of the system. Energy consumption can be saved either statically by turning the processor into sleep mode or dynamically by changing the frequency of the processor cores and thus reducing power consumption. However, a slight increase in frequency leads to executing more tasks in less time and thus can lead to an increase in the efficiency of the real- time system by reducing tasks which may miss its deadline at the time of execution. In this research, a new method has been proposed to control the processor frequency in an optimal manner that makes a balanced trade- off between power consumption and execution of tasks in real- time systems.

show abstract

A Utilization-Based Schedulability Test of Real-Time Systems Running on a Multiprocessor Virtual Machine

Cited by 3 publications

References 8 publications

Utilization and criticality based fault-tolerant scheduling in multicore mixed critical systems

Utilization and criticality based fault-tolerant scheduling in multicore mixed critical systems

Measurement of Kernel Preemption Time of Real Time Operating Systems

Development of Energy- Efficient Load Balancing Scheduling Algorithm in Real-time Systems

Contact Info

Product

Resources

About