Scheduling real-time periodic tasks in multiprocessor systems

Thumbnail Image
Date
1998
Authors
Nathanson, Daphna Dagan
Major Professor
Advisor
Mohapatra, Prasant
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Scheduling of periodic tasks to meet their timing constraints and resource requirements has been an important issue in the design of real-time systems. In this thesis, we have addressed the scheduling of both hard and soft real-time periodic tasks on multiple processor systems. We differentiate between hard and soft real-time jobs by using a quality of service (QoS) factor. The proposed models can be implemented on both shared and distributed memory systems. The scheduling process includes the decision for accepting (admission control) and the selection of a processor (allocation policy) for assigning an incoming task. We have examined two admission control schemes, two quality of service criteria, and a variety of allocation policies. The allocation policies include the selection of processors on the basis of utilization, number of waiting jobs, and round-robin. We have also proposed a new allocation scheme called adaptive grouping that classifies the jobs based on their periods. The performance of all these schemes are evaluated and compared through extensive simulations. Several interesting results (some of which are counterintuitive) were observed in our study. In all cases, the adaptive grouping policy outperforms all the other schemes. Furthermore, we have also quantified the effect of the admission control algorithm in the scheduling process of hard real-time periodic requests on multiple processor systems.
Series Number
Journal Issue
Is Version Of
Versions
Series
Academic or Administrative Unit
Type
thesis
Comments
Rights Statement
Copyright
Funding
DOI
Supplemental Resources
Source