Mechanisms for enhancing the flexibility and utility of hard real-time systems

Abstract

Adaptive and dynamic behaviour is seen as one of the key characteristics of next generation hard real-time systems. Whilst fixed priority pre-emptive scheduling is rapidly becoming a de facto standard in real-time systems engineering, it remains inflexible in its purest form. One method of increasing flexibility is via the incorporation of optional components into processes with hard deadlines. Such components are not guaranteed off-line, but may be accepted at run-time if sufficient spare capacity becomes available. This paper describes new mechanisms which are required to schedule effectively optional components: mechanisms which enable spare capacity to be detected early and on-line guarantees to be given.<>