SYSTEMS AND METHODS FOR CLOUD DEPLOYMENT ENGINE FOR SELECTIVE WORKLOAD MIGRATION OR FEDERATION BASED ON WORKLOAD CONDITIONS

• US 20120304191A1
• Filed: 05/27/2011
• Published: 11/29/2012
• Est. Priority Date: 05/27/2011
• Status: Active Grant

• Current Assignee: Red Hat, Inc. (International Business Machines Corporation)
• Original Assignee: Red Hat, Inc. (International Business Machines Corporation)
• Inventors: Morgan, Christopher Edwin
• Granted Patent: US 8,631,099 B2
• Time in Patent Office: Days
• US Class Current: 718/105
• CPC Class Codes: G06F 9/5088 involving task migration

Abstract

Embodiments relate to systems and methods for a cloud deployment engine for selective workload migration or federation based on workload conditions. A set of aggregate usage history data can record consumption of processor, software, or other resources subscribed to by one or more users in a or clouds. An entitlement engine can analyze the usage history data to identify a subscription margin and other trends or data reflecting short-term consumption trends. An associated deployment engine can analyze the short-term consumption trends, and generate a decision to either deploy any over-subscribed resources to a set of federated backup clouds, or to one or more new host clouds. In aspects, the decision to augment the capacity of the host cloud with either a cloud federation or a complete host cloud replacement can be based on a set of selection criteria, including the margin by which the resources are over-subscribed and/or whether the over-subscription is static, increasing or accelerating, among others.

Claims

1. A method of distributing cloud workloads, comprising:

accessing a set of usage history data for a set of resources consumed by a set of virtual machines executing a workload;

determining one or more over-subscription conditions based on the usage history of the set of virtual machines;

generating a projected cloud replacement outcome based on a potential migration of the workload to at least one replacement cloud;

generating a projected cloud federation outcome based on a potential migration of the over-subscribed portion of the workload to at least one set of federated backup clouds; and

selecting at least one of the at least one replacement cloud and the at least one set of federated backup clouds for migration of at least the over-subscribed portion of the workload based on at least a set of selection criteria, the projected cloud replacement outcome, and the projected cloud federation outcome.

2. The method of claim 1, wherein at least one of the projected cloud replacement outcome or the projected cloud federation outcome comprises a subscription cost for hosting of the at least over-subscribed portion of the workload.

3. The method of claim 1, wherein the selecting is based on a rate of resource consumption increase of the at least over-subscribed portion of the workload.

4. The method of claim 3, wherein the selecting comprises selecting the at least one replacement cloud when the rate of resource consumption increase exceeds a threshold set in the set of selection criteria.

5. The method of claim 1, wherein the set of selection criteria comprises an upper over-subscription limit for at least one of the resources consumed by the set of virtual machines.

6. The method of claim 5, wherein the selecting comprises selecting the set of federated backup clouds when the consumption of the at least one resource in the over-subscribed portion of the workload does not exceed the upper over-subscription limit.

7. The method of claim 5, wherein the selecting comprises selecting the at least one replacement cloud when the consumption of the at least one resource in the over-subscribed portion of the workload exceeds the upper over-subscription limit.

8. The method of claim 1, wherein the at least one set of federated backup clouds comprises a plurality of sets of federated backup clouds configured in layers based on time periods estimated in the projected cloud federation outcome.

9. The method of claim 1, wherein the set of selection criteria comprises at least one of available processor capacity, available memory capacity, available storage capacity, available operating system instances, available application instances, or a time period for which the over-subscribed portion of the workload can be hosted.

10. The method of claim 1, further comprising terminating the at least over-subscribed portion of the workload in the at least one replacement cloud or the set of federated backup clouds when the set of usage history data indicates the one or more over-subscription conditions have ended.

11. A system for distributing cloud workloads, comprising:

an interface to data store storing a set of usage history data for a set of virtual machines consuming a set of resources executing a workload; and

a processor, communicating with the data store via the interface and being configured to—

determine one or more over-subscription conditions based on the usage history of the set of virtual machines,

generate a projected cloud replacement outcome based on a potential migration of the workload to at least one replacement cloud,

generate a projected cloud federation outcome based on a potential migration of the over-subscribed portion of the workload to at least one set of federated backup clouds, and

select at least one of the at least one replacement cloud and the at least one set of federated backup clouds for migration of at least the over-subscribed portion of the workload based on at least a set of selection criteria, the projected cloud replacement outcome, and the projected cloud federation outcome.

12. The system of claim 11, wherein at least one of the projected cloud replacement outcome or the projected cloud federation outcome comprises a subscription cost for hosting of the at least over-subscribed portion of the workload.

13. The system of claim 11, wherein the selecting is based on a rate of resource consumption increase of the at least over-subscribed portion of the workload.

14. The system of claim 13, wherein the selecting comprises selecting the at least one replacement cloud when the rate of resource consumption increase exceeds a threshold set in the set of selection criteria.

15. The system of claim 11, wherein the set of selection criteria comprises an upper over-subscription limit for at least one of the resources consumed by the set of virtual machines.

16. The system of claim 15, wherein the selecting comprises selecting the set of federated backup clouds when the consumption of the at least one resource in the over-subscribed portion of the workload does not exceed the upper over-subscription limit.

17. The system of claim 15, wherein the selecting comprises selecting the at least one replacement cloud when the consumption of the at least one resource in the over-subscribed portion of the workload exceeds the upper over-subscription limit.

18. The system of claim 11, wherein the at least one set of federated backup clouds comprises a plurality of sets of federated backup clouds configured in layers based on time periods estimated in the projected cloud federation outcome.

19. The system of claim 11, wherein the set of selection criteria comprises at least one of available processor capacity, available memory capacity, available storage capacity, available operating system instances, available application instances, or a time period for which the over-subscribed portion of the workload can be hosted.

20. The system of claim 11, further comprising terminating the at least over-subscribed portion of the workload in the at least one replacement cloud or the set of federated backup clouds when the set of usage history data indicates the one or more over-subscription conditions have ended.