Dynamic end-to-end guarantees in distributed real time systems

Many distributed real-time applications are structured as a set of processes communicating through synchronous channels. Unfortunately, process interactions and especially synchronous communications make the problem of predictably scheduling the tasks more complex. In distributed systems the local and remote tasks as well as the messages over the network must be properly scheduled and synchronized to meet the deadlines of the application. To find such a, schedule is not an easy task, in fact, this problem is NP complete even if one has complete knowledge of the future arrival times for all the processes in the system. The objective of this paper is to develop a scheme that allows for the dynamic scheduling and guaranteeing of distributed processes communicating via synchronous primitives. For efficiency reasons a combination of off-line and on-line scheduling is performed. Precedence and communication constraints are converted off-line into pseudo-deadlines for each task, enabling efficient on-line processing. The on-line scheduling operates in parallel at the sites involved in the distributed computation, further obtaining efficiency. The overall end-to-end scheduling includes the joint and coordinated scheduling of tasks and messages in a reflective memory distributed architecture.<>