Load adaptive dynamic scheduling of tasks with hard deadlines useful for industrial applications

Abstract

All intrinsic properties of the earliest deadline taks scheduling discipline are compiled and discussed in order to show that this is the most advantageous scheme at hand, characterised by efficiency and allowing predictable system behaviour. It is then pointed out how the method naturally extends to the scheduling of tasks having non-pre-emptable regions due to resource access constraints. A sufficient condition is derived, which allows, at any arbitrary point in time and under observation of resource constraints, to check the feasible schedulability of the tasks competing for processor allocation. This condition applies to entirely non-pre-emptable tasks as well. Taking the corresponding overhead into consideration, the circumstances are characterised under which the task context-switches imposed by the scheduling algorithm can be avoided. Favourable consequences of deadline scheduling for virtual storage management are mentioned. Finally, application oriented schemes for coping with transient overloads and thus allowing load adaptive dynamic scheduling are introduced. Such overloads can be easily detected at an early stage utilising the here established schedulability criterion.