| 摘要 |
PROBLEM TO BE SOLVED: To arbitrate failure handling for each computer performed at an occurrence of a failure in an I/O device, when a plurality of computers shares the I/O device. SOLUTION: A resource management unit of a management server 105 for controlling a multi-root I/O manager connected to a PCI switch for connecting a plurality of I/O devices and a plurality of computers with each other, upon reception of failure handling content information indicating, for each computer sharing a multi-root I/O device, the content of a failure handling at an occurrence of a failure in the multi-root I/O device, failure handling status information indicating whether a hardware reset of the multi-root I/O device is possible, and a notification of the occurrence of the failure in the multi-root I/O device, updates the failure handling status information, and instructs, based on the failure handling status information, the multi-root I/O manager to restrain or cancel the hardware reset of the multi-root I/O device. COPYRIGHT: (C)2010,JPO&INPIT
|
