Distributed computing architecture with dynamically reconfigurable hypervisor nodes

A distributed computing architecture with dynamically reconfigurable processing nodes, the architecture comprising:

• a supervisor node including physical computing hardware and executable software;
• a first processing node and a second processing node in communication with the supervisor node over a data network, each of the first and second processing nodes respectively including physical computing hardware, a hypervisor, and a plurality of virtual machines, the hypervisor being configured to apportion use of the physical computing hardware to the plurality of virtual machines according to a hypervisor configuration file;
• and
• a reconfiguration manager operating on the supervisor node and configured to:
• detect a fault condition on the first processing node;
• assess the criticality of a software function performed by each of the respective virtual machines on the first processing node;
• and
• reassign at least one first virtual machine of the plurality of virtual machines on the first processing node to the second processing node if the at least one first virtual machine is assessed as being above a threshold level of criticality, wherein reassigning the at least one first virtual machine includes:
• providing a second hypervisor configuration file to the first processing node;
• apportioning processing resources on the first processing node to a second virtual machine of the plurality of virtual machines at the direction of the second hypervisor configuration file;
• and
• wherein the second virtual machine is a copy of a portion of the first virtual machine.

A method of dynamically reconfiguring a distributed computing architecture having a first and a second processing node, each processing node including a respective hypervisor configured to apportion processing resources of the respective processing node between a plurality of virtual machines at the direction of a hypervisor configuration file, the method comprising:

• apportioning processing resources on the first processing node between a first virtual machine and a second virtual machine at the direction of a first hypervisor configuration file;
• detecting a fault condition on a second processing node, the second processing node including a third virtual machine;
• assessing the criticality of a software function performed by the third virtual machine;
• reassigning the third virtual machine to the first processing node if the third virtual machine is assessed as being above a threshold level of criticality, wherein reassigning the third virtual machine includes:
• providing a second hypervisor configuration file to the first processing node;
• apportioning processing resources on the first processing node to a fourth virtual machine at the direction of the second hypervisor configuration file;
• and
• wherein the fourth virtual machine is a copy of a portion of the third virtual machine;
• and
• reducing an apportionment of processing resources to at least one of the first and the second virtual machines.