Improving fault-tolerance in distributed systems: The saturation approach

Work done for the research project SATURNE is summarized. The technique developed in this project maximizes the redundancy level of tasks and tolerates hardware faults by majority voting in the context of a pool of interconnected processors (network of workstations, multiprocessor machines, etc.). The technique, called saturation, is presented and briefly compared with similar approaches. The distributed scheduling algorithm implementing this technique is described by using formal description techniques based on Estelle. Description analysis involves available simulation tools from which results were obtained and used as input parameters to the model defined for evaluation.<
>