| 摘要 |
An apparatus and method shares predictive failure information between computer systems in a computer network. The shared predictive failure information allows a requester of a network resource to determine whether the resource will be available to perform the request based on its predictive failure information. According to a first embodiment, predictive failure information is written by each computer system on the network to a common storage that is accessible by one or more other computer systems on the network. When a computer system on the network needs a resource on another system, the requesting computer system can check the predictive failure status of the system that contains the needed resource by reading the predictive failure information in the common storage. If the predictive failure information indicates that the resource may perform the requested function, the requesting computer system issues the request to the resource. In a second embodiment, one or more network protocols for communicating between computer systems on the network are modified so that messages given in response to resource requests include the predictive failure status of the requested system. Thus, if a requester needs data from another computer system, a message returned from that system in response to the request preferably includes predictive failure status or information indicating whether or not the request can be granted. If the predictive failure status or information indicates that the request can be granted, the requester performs the operation on the requested computer system. In this manner, predictive failure information can be used in granting access to resources between computer systems on a network, which allows accesses to be prevented if the predictive failure information indicates that the resource is likely to fail before completing the request.
|
