Method and apparatus for failure recovery in a multi-processor computer system

Abstract

Multiple instances of operating systems execute cooperatively in a single multiprocessor computer wherein all processors and resources are electrically connected together. The single physical machine with multiple physical processors and resources is subdivided by software into multiple partitions, each with the ability to run a distinct copy, or instance, of an operating system. At different times, different operating system instances may be loaded on a given partition. Resources, such as CPUs and memory, can be dynamically assigned to different partitions and used by instances of operating systems running within the machine by modifying the configuration. The partitions themselves can also be changed without rebooting the system by modifying the configuration tree. The system makes use of a failure protocol that results in the transfer of processing resources controlled by an instance that experiences a failure to new destination instances on other partitions. For CPUs, destination instance IDs are stored in an array which is accessed upon occurrence of a failure to determine where the CPUs will be assigned. The secondary CPUs then dump their processing contexts, and each invoke a migration routine to transfer their control to the new instances. A destination instance may be a backup instance for the instance experiencing the failure, having no processing functions prior to the failure. Thus, the processing activities of the failed instance may be resumed quickly by the backup instance.