Implementation of Conditional Critical Regions in Systems Using Different Process Communication Techniques

Abstract

Conditional Critical Regions (CCR) are a very good instrument for describing and designing process-synchronisation in real time systems. A straightforward implementation is not a feasible solution because of its huge runtime-overhead, but certain properties of the CCR allow the separation of the synchronizing operations on the shared data from the non - synchronizing ones. This allows to use standardized conditions (“normalized CCR”) instead of general conditional expressions and to extend the monitor-concept by integrating the normalized CCR. Thus a very efficient implementation has been found. The feasibility of this solution in multitasking systems on a single processor has been proven by an industrial project, a large data-acquisition system in a rolling mill, where many difficult problems of event-, timeout- and exception-handling in a very rough process environment had to be solved. Then some ideas concerning the applicability of the CCR in multiprocessor environments will be discussed, especially in distributed systems where the shared data concept in the original meaning is no longer valid and is replaced by other process-communication techniques (signals, mailboxes, rendezvous). It is shown, that the normalized CCR as synchronizing system-control element need not necessarily be embedded in the shared data-concept and the concept is suited for distributed systems also, preserving its advantages such as transparent programming of process control on user level, functional separation of long- and medium term scheduling, simplicity and generality.