Abstract: A method is described for rapidly recovering a multi-processor data processing system from failure of a boot disk. Each data processing unit in the system has a private boot disk, and at least one shared disk. The processing units are interconnected so that each processing unit has access to its own private boot disk and also to the shared disks in all of the processing units. If the boot disk of one of the processing units fails, the system is temporarily reconfigured to connect a new boot disk in place of the shared disk in that processing unit. Another of the processing units is then operated to copy the contents of its own boot disk to the new boot disk.

Abstract: A high-availability computer system comprises at least two processors, each having its own private disk drive, and a shared disk drive, accessible by both processors. Each of the private disk drives holds system files for establishing a processor as a secondary processor, and the shared disk drive holds system files for establishing a processor as a primary processor. When it boots up, each processor decides whether to use the system files from its private disk so as to become a secondary, or to use the system files from the shared disk so as to become the primary. As as result, after a system failure or reboot, either processor can pick up the characteristics of the the primary processor, and will have all the most up-to-date primary information available to it.

Abstract: A computer system comprises a number of replicated units. At least two of the units include monitoring components for monitoring the status of the system. The monitoring components communicate with each other to exchange status information, so as to enable both of the monitoring components to form a combined view of the status of the system, based on information gathered by both of the monitoring components. This enables each monitoring component to locate faults more precisely, and thus enables more appropriate recovery action to be taken.

Abstract: A data processing system comprises a plurality of processing modules, and a central services module, connected by a system bus. Details of the expected system configuration and of a normal bootstrap load path are held in a non-volatile store. On power-up or system restart, the non volatile store is tested. If the test is satisfactory, a defined bootstrap procedure is executed; otherwise an undefined bootstrap procedure is performed. The defined bootstrap procedure compares the expected configuration with the actual system configuration. If they match, the bootstrap program is loaded from the normal load path. If they do not match, the undefined bootstrap procedure may be entered. In the undefined bootstrap procedure, the central services module searches for possible bootstrap load paths and attempts a load from one of these paths. The defined bootstrap is expected to be the normal procedure, and is faster.