NODE FAILURE MANAGEMENT

摘要

A method and computer-readable storage media are provided for managing resources of a first node. The method may include detecting a failure in a first node. The first node may include one or more cores and supporting resources. The method may further include determining that one or more cores in the first node survived the failure. The method may further include determining that any supporting resources survived the failure. The method may also include reconfiguring a second node to add the surviving supporting resources of the first node using communication interface between the first and second node if the determinations found a surviving core and surviving supporting resource in the first node.

主权项

1. A method for managing resources of a first node, comprising:
detecting a failure in a first node, the first node comprising one or more cores and supporting resources; determining that one or more cores in the first node survived the failure; determining that any supporting resources survived the failure; and reconfiguring a second node to add the surviving supporting resources of the first node using communication interface between the first and second node if the determinations found a surviving core and surviving supporting resource in the first node.