Processing board, a computer, and a fault recovery method for the computer

摘要

A fault recovery process of a computer is provided for removing a fault from the system as soon as possible, minimizing the secondary fault and improving the availability of the system. In a reliable computer, which includes a system bus, a main memory connected to the system bus, and at least one processing board connected to the system bus, at least one processing board executes the same instructions by n (n>=3) processing units having cache memories respectively. When one of the processing units of the processing board becomes faulty, the other processing units continue executing the processes, which are being executed by the faulty processing board, and then, the processes to be registered in the faulty processing board, are succeeded by other processing boards.