Transformation methods for off-line schedules to attributes for fixed priority scheduling

Detta är en avhandling från Institutionen för Datavetenskap

Författare: Radu Dobrin; Mälardalens Högskola.; Mälardalens Högskola.; [2003]

Nyckelord: ;

Sammanfattning: Off-line scheduling and fixed priority scheduling (FPS) are often consideredas complementing and incompatible paradigms. A number of industrial applications demand temporal properties (predictability, jitter constraints, end-to-end deadlines, etc.) that are typically achieved by using off-line scheduling.The rigid off-line scheduling schemes used, however, do not provide forflexibility. FPS has been widely studied and used in a number of industrial applications, e.g., CAN bus, mostly dueto its simple run-time scheduling and small overhead.It can provide more flexibility, but is limited with respect to predictability, as actual start and completion times of executions depend on run-time events.In this work we show how off-line scheduling and FPS run-time scheduling canbe combined to get the advantages of both -- the capability to cope withcomplex timing constraints while providing run-time flexibility. The proposed approaches assume that a schedule for a set of tasks with complexconstraints has been constructed off-line. We present methods to analyze the off-line schedule and derive FPS attributes, e.g.,priorities, offsets, and periods, such that the runtime FPS execution matches the off-line schedule. The basic idea is to analyze the schedule and to derive task attributes for fixed priority scheduling.In some cases, i.e., when the off-line schedule can not be expressed directly by FPS,we split tasks into instances to obtain a new task set with consistent task attributes. Furthermore, we provide a method to keep the number of newly generated artifact tasks minimal.Finally, we apply the proposed method to schedule messages with complex constraints onController Area Network (CAN). We analyze an off-line schedule constructed to solvecomplex constraints for messages, e.g., precedence, jitter or end-to-end deadlines, and we derive attributes, i.e., message identifiers, required by CAN's native protocol. At run time,the messages are transmitted and received within time intervals such that the original constraints are fulfilled.

  Denna avhandling är EVENTUELLT nedladdningsbar som PDF. Kolla denna länk för att se om den går att ladda ner.