New hard real-time kernel for embedded computing systems

Predictability and adaptability are two essential requirements of real-time systems. This paper presents a new real-time kernel whose design explicitly addresses the above requirements. It is intended for systems involving both static and dynamic tasks, and it employs a single scheduling algorithm to accommodate all task types. The algorithm utilizes the extent of known information about each type to achieve better management of time. It provides a priori guarantees for static tasks and on-line guarantees for dynamic ones. The kernel adapts to changes in the environment which may result in the dynamic generation of new tasks, on-line modification of tasks' timing constraints and large changes in task arrival rates.