Hybrid Cloud Workload Management

• US 20120204187A1
• Filed: 02/08/2011
• Published: 08/09/2012
• Est. Priority Date: 02/08/2011
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Breiter, Gerd, Lindquist, David B., Naik, Vijay K., Rajaraman, Bala, Reinhardt, Holger, Schmidt, Marc-Thomas H., Tan, Yih-Shin
• Application Number:
  US13/023,159
• Publication Number:
  US 20120204187A1
• Time in Patent Office: Days
• US Class Current: 718/105
• CPC Class Codes: G06F 2209/508 Monitor
• CPC Class Codes: G06F 2209/509 Offload
• CPC Class Codes: G06F 9/5072 Grid computing

Abstract

A method, apparatus, and computer program product for managing a workload in a hybrid cloud. It is determined whether first data processing resources processing a portion of a workload are overloaded. Responsive to a determination that the first data processing resources are overloaded, second data processing resources are automatically provisioned and the portion of the workload is automatically moved to the second data processing resources for processing. The second data processing resources are data processing resources that are provided as a service on the hybrid cloud. Processing of a first portion of a workload being processed on first data processing resources of a hybrid cloud are monitored simultaneously with monitoring processing of a second portion of the workload being processed on second data processing resources of the hybrid cloud. The workload may be allocated automatically between the first portion and the second portion responsive to the simultaneous monitoring.

Claims

1. A method for managing a workload, comprising:

determining, by a processor unit, whether first data processing resources processing a portion of a workload are overloaded;

responsive to a determination that the first data processing resources are overloaded, automatically provisioning, by the processor unit, second data processing resources, wherein the second data processing resources are provided as a service for the provisioning; and

automatically moving, by the processor unit, the portion of the workload from the first data processing resources to the second data processing resources for processing on the second data processing resources.

2. The method of claim 1, wherein the first data processing resources and the second data processing resources comprise a hybrid cloud selected from the group of hybrid clouds consisting of:

a hybrid cloud wherein the first data processing resources comprise a private cloud and wherein the second data processing resources comprise a public cloud;

a hybrid cloud wherein the first data processing resources comprise a private cloud and wherein the second data processing resources comprise a private cloud; and

a hybrid cloud wherein the first data processing resources comprise a public cloud and wherein the second data processing resources comprise a public cloud.

3. The method of claim 1, wherein automatically provisioning the second data processing resources comprises automatically invoking a plug-in in a software framework to provision the second data processing resources.

4. The method of claim 1, wherein determining whether the first data processing resources processing the portion of the workload are overloaded comprises:

defining a workload overload threshold;

monitoring the processing of the portion of the workload by the first data processing resources to obtain monitoring data; and

determining whether the monitoring data indicates that the workload overload threshold is exceeded.

5. A computer program product for managing a workload, the computer program product comprising:

a computer readable storage medium;

first program instructions to determine whether first data processing resources processing a portion of a workload are overloaded;

second program instructions to automatically provision second data processing resources responsive to a determination that the first data processing resources are overloaded, wherein the second data processing resources are provided as a service for the provisioning;

third program instructions to automatically move the portion of the workload from the first data processing resources to the second data processing resources for processing on the second data processing resources; and

wherein the first, second, and third program instructions are stored on the computer readable storage medium.

6. The computer program product of claim 5, wherein the first data processing resources and the second data processing resources comprise a hybrid cloud selected from the group of hybrid clouds consisting of:

a hybrid cloud wherein the first data processing resources comprise a private cloud and wherein the second data processing resources comprise a public cloud;

a hybrid cloud wherein the first data processing resources comprise a private cloud and wherein the second data processing resources comprise a private cloud; and

a hybrid cloud wherein the first data processing resources comprise a public cloud and wherein the second data processing resources comprise a public cloud.

7. The computer program product of claim 5, wherein the second program instructions comprise program instructions to invoke a plug-in in a software framework to provision the second data processing resources.

8. The computer program product of claim 5, wherein the first program instructions comprise:

program instructions to define a workload overload threshold;

program instructions to monitor the processing of the portion of the workload by the first data processing resources to obtain monitoring data; and

program instructions to determine whether the monitoring data indicates that the workload overload threshold is exceeded.

9. An apparatus, comprising:

a monitoring infrastructure configured to determine whether first data processing resources processing a portion of a workload are overloaded and to send a request responsive to a determination that the first data processing resources processing the portion of the workload are overloaded;

a workload manager configured to receive the request, to automatically provision second data processing resources responsive to receiving the request, wherein the second data processing resources are provided as a service for the provisioning, and to automatically move the portion of the workload from the first data processing resources to the second data processing resources for processing on the second data processing resources.

10. The apparatus of claim 9, wherein the first data processing resources and the second data processing resources comprise a hybrid cloud selected from the group of hybrid clouds consisting of:

a hybrid cloud wherein the first data processing resources comprise a private cloud and wherein the second data processing resources comprise a public cloud;

a hybrid cloud wherein the first data processing resources comprise a private cloud and wherein the second data processing resources comprise a private cloud; and

a hybrid cloud wherein the first data processing resources comprise a public cloud and wherein the second data processing resources comprise a public cloud.

11. The apparatus of claim 9, wherein the workload manager is configured to invoke a plug-in in a software framework to provision the second data processing resources.

12. The apparatus of claim 9, wherein the monitoring infrastructure is configured to monitor the processing of the portion of the workload by the first data processing resources to obtain monitoring data, to determine whether the monitoring data indicates that a workload overload threshold is exceeded, and to determine that the first data processing resources processing a portion of a workload are overloaded responsive to a determination that the workload overload threshold is exceeded.

13. A method for managing a workload, comprising:

simultaneously monitoring, by a processor unit, processing of a first portion of a workload being processed on first data processing resources and monitoring processing of a second portion of a workload being processed on second data processing resources, wherein at least one of the first data processing resources and the second data processing resources comprise data processing resources provided as a service; and

responsive to monitoring processing of the first portion of the workload and monitoring processing of the second portion of the workload, allocating, by the processor unit, the workload between the first portion and the second portion.

14. The method of claim 13, wherein the first data processing resources and the second data processing resources comprise a hybrid cloud selected from the group of hybrid clouds consisting of:

a hybrid cloud wherein the first data processing resources comprise a private cloud and wherein the second data processing resources comprise a public cloud;

a hybrid cloud wherein the first data processing resources comprise a private cloud and wherein the second data processing resources comprise a private cloud; and

a hybrid cloud wherein the first data processing resources comprise a public cloud and wherein the second data processing resources comprise a public cloud.

15. The method of claim 13, wherein simultaneously monitoring processing of the first portion of the workload being processed on the first data processing resources and monitoring processing of the second portion of a workload being processed on the second data processing resources comprises invoking, by the processor unit, a plug-in in a software framework to monitor either processing of the first portion of the workload being processed on the first data processing resources or to monitor processing of the second portion of a workload being processed on the second data processing resources.

16. The method of claim 13, further comprising:

responsive to monitoring processing of the first portion of the workload and monitoring processing of the second portion of the workload, determining, by the processor unit, whether either the first data processing resources are overloaded while processing the first portion of the workload or the second data processing resources are overloaded while processing the second portion of the workload; and

responsive to a determination that either the first data processing resources are overloaded while processing the first portion of the workload or the second data processing resources are overloaded while processing the second portion of the workload, reallocating, by the processor unit, the workload between the first portion and the second portion.

17. The method of claim 16, further comprising:

responsive to a determination that either the first data processing resources are overloaded while processing the first portion of the workload or the second data processing resources are overloaded while processing the second portion of the workload, invoking, by the processor unit, a plug-in in a software framework to provision services for processing the workload.

18. The method of claim 13, further comprising:

responsive to monitoring processing of the first portion of the workload and monitoring processing of the second portion of the workload, determining, by the processor unit, whether either the first data processing resources are underloaded while processing the first portion of the workload or the second data processing resources are underloaded while processing the second portion of the workload; and

responsive to a determination that either the first data processing resources are underloaded while processing the first portion of the workload or the second data processing resources are underloaded while processing the second portion of the workload, reallocating, by the processor unit the workload between the first portion and the second portion.

19. The method of claim 18, further comprising, responsive to a determination that either the first data processing resources are underloaded while processing the first portion of the workload or the second data processing resources are underloaded while processing the second portion of the workload, releasing, by the processor unit, a portion of either the first data processing resources or the second data processing resources.

20. An apparatus, comprising:

a monitoring infrastructure configured to monitor simultaneously processing of a first portion of a workload being processed on first data processing resources and processing of a second portion of a workload being processed on second data processing resources, wherein at least one of the first data processing resources and the second data processing resources comprise data processing resources provided as a service; and

a workload manager configured to allocate automatically the workload between the first portion and the second portion responsive to the simultaneous monitoring of processing of the first portion of the workload and monitoring of processing of the second portion of the workload.

21. The apparatus of claim 20, wherein the first data processing resources and the second data processing resources comprise a hybrid cloud selected from the group of hybrid clouds consisting of:

a hybrid cloud wherein the first data processing resources comprise a private cloud and wherein the second data processing resources comprise a public cloud;

a hybrid cloud wherein the first data processing resources comprise a private cloud and wherein the second data processing resources comprise a private cloud; and

a hybrid cloud wherein the first data processing resources comprise a public cloud and wherein the second data processing resources comprise a public cloud.

22. The apparatus of claim 20, wherein the monitoring infrastructure is configured to invoke a plug-in in a software framework to monitor either processing of the first portion of the workload being processed on the first data processing resources or to monitor processing of the second portion of the workload being processed on the second data processing resources.

23. The apparatus of claim 20, wherein:

the monitoring infrastructure is configured to determine, responsive to monitoring processing of the first portion of the workload and monitoring processing of the second portion of the workload, whether either the first data processing resources are overloaded while processing the first portion of the workload or the second data processing resources are overloaded while processing the second portion of the workload; and

the workload manager is configured to reallocate the workload between the first portion and the second portion, responsive to a determination that either the first data processing resources are overloaded while processing the first portion of the workload or the second data processing resources are overloaded while processing the second portion of the workload.

24. The apparatus of claim 23, wherein the workload manager is configured to invoke a plug-in in a software framework to provision services for processing the workload responsive to a determination that either the first data processing resources are overloaded while processing the first portion of the workload or the second data processing resources are overloaded while processing the second portion of the workload.

25. The apparatus of claim 20, wherein:

the monitoring infrastructure is configured to determine whether either the first data processing resources are underloaded while processing the first portion of the workload or the second data processing resources are underloaded while processing the second portion of the workload, responsive to monitoring processing of the first portion of the workload and monitoring processing of the second portion of the workload; and

the workload manager is configured to reallocate the workload between the first portion and the second portion, responsive to a determination that either the first data processing resources are underloaded while processing the first portion of the workload or the second data processing resources are underloaded while processing the second portion of the workload.