| 摘要 |
A computing system comprises two or more processing sets, for example for fault tolerant operation. The multiple processing sets have a connection to at least one device, typically many devices. The ownership of each device is allocated to one of the two or more processing sets. When an interrupt is generated within a device, this is transmitted from the device to the processing set to which ownership of the device has been allocated, but not to the remaining processing sets. In addition, a command for a device may be generated by a processing set. However, receipt of this command by the device is disabled if the processing set that generated the command has not been allocated ownership of the device.
|
