Granted Patent B2

US 9,413,687 · App. 11/276,853 · Granted Aug 9, 2016

Abstract

Claims (43)

1. A method of managing resources, the method comprising:

detecting an event in a local compute environment, the local compute environment comprising a plurality of resources configured to process workload, to yield a detected event;

based on the detected event, receiving a request for resources in an on-demand compute environment, the resources comprising at least one of a server, memory, network bandwidth, a processor, and a virtual resource, wherein a specification of the resources associated with the request is one of fully explicit, partially explicit, and fully implicit based on workload;

establishing a communication between the local compute environment and the on-demand compute environment having a plurality of resources available to process workload under common management separate from the local compute environment;

based on the communication, establishing, at a first time and associated with the request for resources, a reservation of the resources for use at a second time later than the first time within the on-demand compute environment to yield reserved resources; and

transferring workload, submitted for processing in the local compute environment, transparently to the on-demand compute environment to yield transferred workload, wherein the transferred workload consumes the reserved resources in the on-demand compute environment at the second time.

2. The method of claim 1 , wherein at least one of: (1) local information associated with the local compute environment is imported to the on-demand compute environment and (2) on-demand information associated with the on-demand compute environment is communicated to the local compute environment.

3. The method of claim 2 , wherein workload information is communicated from the local compute environment to the on-demand compute environment.

4. The method of claim 2 , wherein if on-demand information is communicated to the local compute environment, the on-demand information relates to an availability of resources in the on-demand compute environment for use by the local compute environment.

5. The method of claim 1 , further comprising:

transparently handling data management between a slave module in the on-demand compute environment and a client module in the local compute environment.

6. The method of claim 5 , wherein transparently handling data management further comprises handling the data management such that the establishing of the reservation of resources within the on-demand compute environment and transferring the workload from the local compute environment is performed unknown to a user who submitted the workload to the local compute environment.

7. The method of claim 1 , wherein the event is related to at least one: of a resource threshold, a service threshold, a policy threshold and an event outside the local compute environment.

8. The method of claim 1 , wherein the event further comprises a failure of at least one a compute node, a network device, a storage device, a license, a service, an information service, a web service, a database service and a security service.

9. The method of claim 1 , wherein establishing communication with the on-demand compute environment further comprises importing from the local compute environment at least one of class information, configuration policy information and other information to the on-demand compute environment.

10. The method of claim 1 , wherein establishing communication with the on-demand compute environment occurs automatically.

11. The method of claim 1 , wherein the event is based on one of all workload associated with the local compute environment or a subset of workload associated with the local compute environment.

12. The method of claim 1 , wherein establishing a reservation of compute resources within the on-demand compute environment is based on at least one of implicit and explicit requirements.

13. A method of managing a relationship between a local compute environment and an on-demand compute environment, the method comprising:

detecting a resource need event in the local compute environment under common management separate from the on-demand compute environment, the local compute environment comprising a plurality of resources configured to process workload, to yield a detected resource need event;

based on the detected resource need event, negotiating and establishing a relationship between the local compute environment and the on-demand compute environment;

receiving a request for resources in the on-demand compute environment, the resources comprising at least one of a server, memory, network bandwidth, a processor, and a virtual resource, wherein a specification of the resources associated with the request is one of fully explicit, partially explicit, and fully implicit based on workload;

establishing, at a first time, a reservation of resources for consumption at a second time later than the first time and within the on-demand compute environment to yield reserved resources; and

transferring workload, submitted for processing on the local compute environment, transparently to the on-demand compute environment to yield transferred workload, wherein the transferred workload consumes the reserved resources in the on-demand compute environment at the second time.

14. The method of claim 13 , wherein the resource need event is one of a current resource need and a predicted resource need.

15. A system for managing resources between a local compute environment and an on-demand compute environment, the system comprising:

a processor; and

a computer readable storage medium storing instructions which, when executed by the processor, cause the processor to perform operations comprising:

detecting an event in the local compute environment having multiple resources available to process workload under common management and separate from the on-demand compute environment, the local compute environment configured to process workload;

based on the event, receiving a request for resources in an on-demand compute environment, the resources comprising at least one of a server, memory, network bandwidth, a processor, and a virtual resource, wherein a specification of the resources associated with the request is one of fully explicit, partially explicit, and fully implicit based on workload;

establishing a communication between the local compute environment and the on-demand compute environment;

reserving resources, at a first time, within the on-demand compute environment to yield reserved resources for use at a second time later than the first time; and

transferring workload, submitted for processing on the local compute environment, transparently to the on-demand compute environment to yield transferred workload, wherein the transferred workload consumes the reserved resources in the on-demand compute environment at the second time.

16. A non-transitory computer readable storage medium storing instruction for controlling a computing device to manage resources in a local compute environment and an on-demand compute environment, the instructions causing the computing device to perform operations comprising:

detecting an event in a local compute environment under common management separate from the on-demand compute environment, the local compute environment having a plurality of resources configured to process workload;

based on the event, receiving a request for resources in the on-demand compute environment, the resources comprising at least one of a server, memory, network bandwidth, a processor, and a virtual resource, wherein a specification of the resources associated with the request is one of fully explicit, partially explicit, and fully implicit based on workload;

establishing communication between the local compute environment and the on-demand compute environment;

reserving, at a first time, resources within the on-demand compute environment to yield reserved resources for use at a second time which is later than the first time; and

transferring, workload submitted for processing on the local compute environment, transparently to the on-demand compute environment to yield transferred workload, wherein the transferred workload consumes the reserved resources in the on-demand compute environment at the second time.

17. The method of claim 1 , further comprising provisioning the reserved resources.

18. The method of claim 13 , further comprising provisioning the reserved resources.

19. The system of claim 15 , further comprising a fifth module configured to control the processor to provision the reserved resources.

20. The non-transitory computer-readable storage medium of claim 16 , the instructions further comprising provisioning the reserved resources.

Assignments (8)