System and method for managing energy consumption in a compute environment
AssigneeAdaptive Computing Enterprises, Inc.
InventorDavid Brian Jackson
Life of this patent
Estimating the term…
Abstract
A system, method and non-transitory computer readable storage medium are disclosed for managing workload in a data center. The method includes receiving, at a workload manager, energy consumption information associated with at least one of a first data center and a second data center that is geographically distanced from the first data center. The method further includes receiving workload information associated with at least one of the first data center and the second data center, and transmitting, as controlled by the workload manager, at least part of workload scheduled to be processed at the second data center to the first data center based on at least one of the energy consumption information and the workload information.
Claims13
A method of managing workload, the method comprising:
- receiving, at a workload manager, energy consumption information associated with a first data center and a second data center that is geographically distanced from the first data center, the energy consumption information comprising a node-based analysis of at least one of power consumption and temperature;
- receiving, at a first time, workload information associated with the first data center and the second data center;
- migrating a reservation of compute resources for workload that is scheduled to consume the compute resources in the second data center to yield a new reservation of compute resources in the first data center;
- and
- processing, as controlled by the workload manager, at least part of the workload previously associated with the reservation in the second data center using nodes in the first data center associated with the new reservation based on the energy consumption information and the workload information.
A system for managing workload, the system comprising:
- a processor;
- and
- a computer-readable storage medium storing instructions which, when executed by the processor, perform a method comprising:
- receiving, at a workload manager, energy consumption information associated with a first data center and a second data center that is geographically distanced from the first data center, the energy consumption information comprising a node-based analysis of at least one of power consumption and temperature;
- receiving, at a first time, an energy consumption profile for workload information associated with at least one of the first data center and the second data center;
- migrating a reservation of compute resources for workload that is scheduled to consume the compute resources in the second data center to yield a new reservation of compute resources in the first data center;
- and
- processing, as controlled by the workload manager, at least part of the workload previously associated with the reservation in the second data center using nodes in the first data center that are associated with the new reservation based on the energy consumption information and the energy consumption profile.
A non-transitory computer-readable storage medium storing instructions which, when executed by a computing device, cause the computing device to perform a method comprising:
- receiving, at a workload manager, energy consumption information associated with a first data center and a second data center that is geographically distanced from the first data center, the energy consumption information comprising a node-based analysis of at least one of power consumption and temperature;
- receiving, at a first time, an energy consumption profile for workload information associated with the first data center and the second data center;
- and
- migrating a reservation of compute resources for workload that is scheduled to consume the compute resources in the second data center to yield a new reservation of compute resources in the first data center;
- and
- processing, as controlled by the workload manager, at least part of the workload previously associated with the reservation in the second data center using nodes in one of the first data center and the second data center associated with the new reservation based on the energy consumption information and the energy consumption profile.
Dependencies are inferred from the claim text.