RESOURCE MANAGEMENT FOR CLOUD COMPUTING PLATFORMS

• US 20120330711A1
• Filed: 06/27/2011
• Published: 12/27/2012
• Est. Priority Date: 06/27/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Jain, Navendu, Menache, Ishai
• Granted Patent: US 9,595,054 B2
• Time in Patent Office: Days
• US Class Current: 705/7.23
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: G06Q 30/04 Billing or invoicing

Abstract

A system for managing allocation of resources based on service level agreements between application owners and cloud operators. Under some service level agreements, the cloud operator may have responsibility for managing allocation of resources to the software application and may manage the allocation such that the software application executes within an agreed performance level. Operating a cloud computing platform according to such a service level agreement may alleviate for the application owners the complexities of managing allocation of resources and may provide greater flexibility to cloud operators in managing their cloud computing platforms.

Claims

1. A method for operating a cloud computing platform to execute a software application, the software application being associated with an application owner and the cloud computing platform being operated by a cloud operator, the software application comprising a first logical part and a second logical part, the method comprising:

via an interface of the cloud computing platform, receiving a specification of at least one term of a service-level agreement (SLA) between the application owner and the cloud operator, the at least one term of the SLA comprising at least one performance level for execution of the software application by the cloud computing platform, the at least one performance level comprising an upper limit on acceptable execution times for an operation of the software application;

executing the software application via resources of the cloud computing platform;

comparing an execution time for the operation of the software application to the upper limit on acceptable execution times under the SLA, wherein the comparing comprises comparing a first value for a first actual operational characteristic of the first logical part to a first expected operational characteristic for the first logical part and comparing a second value for a second actual operational characteristic of the second logical part to a second expected operational characteristics for the second logical part; and

billing the application owner for execution of the software application an amount determined based at least in part on a result of the comparing.

2. The method of claim 1, wherein the billing comprises, when the execution time exceeds the upper limit on acceptable execution times under the SLA:

when either the first value deviates from the first expected operational characteristic or the second value deviates from the second expected operational characteristic, billing the application owner for execution of the software application at a first billing rate; and

when the first value does not deviate from the first expected operational characteristic and the second value does not deviates from the second expected operational characteristic, billing the application owner for execution of the software application at a second billing rate lower than the first billing rate.

3. The method of claim 2, wherein the billing further comprises, when the execution time does not exceed the upper limit on acceptable execution times, billing the application owner for execution of the software application at the first rate.

4. The method of claim 1, further comprising:

analyzing functionality of the software application to identify the first logical part and the second logical part, the first logical part comprising a first portion of the functionality of the software application and the second logical part comprising a second portion of the functionality of the software application, the first portion being different from the second portion and being independently executable from the second portion.

5. The method of claim 1, wherein:

the resources of the cloud computing platform comprise a plurality of resource containers, each resource container being associated with hardware and/or software resources, and

the method further comprises determining at least one expected operational characteristic for the first logical part at least in part by configuring a single resource container to act as the first logical part and executing the first logical part on the single resource container, the at least one operational characteristic comprising a first expected execution time.

6. The method of claim 5, further comprising:

based on the at least one expected operational characteristic, determining an amount of resources to be used by the first logical part for the software application to execute in accordance with the at least one performance level of the SLA.

7. The method of claim 6, wherein:

the resources of the cloud computing platform comprise a plurality of resource containers, each resource container comprising hardware and/or software resources and being configurable to act as a logical part of the software application, and

the determining the amount of resources to be used by the first logical part for the software application to execute in accordance with the at least one performance level comprises;

determining a number of operations per unit time that the single resource container is able to carry out when configured to act as the first logical part; and

determining a number of resource containers to allocate to the first logical part so as to meet the at least one performance level of the SLA.

8. The method of claim 7, further comprising:

determining a first cost to the cloud operator of operating resource containers as the first logical part and a second cost to the cloud operator of operating resource containers as the second logical part; and

determining a price to charge the application owner for execution of the software application based at least in part on the first cost and the second cost.

9. The method of claim 5, wherein:

at least one first resource container of the plurality of resource containers is associated with utility resources, and

executing the software application via the resources of the cloud computing platform comprises executing the software application via the at least one first resource container associated with the utility resources.

10. A method for configuring a cloud computing platform to allocate resources of the cloud computing platform to a software application, the software application being associated with an application owner and the cloud computing platform being operated by a cloud operator, the method comprising:

analyzing functionality of the software application to identify a first logical part and a second logical part of the software application, the first logical part comprising a first portion of the functionality of the software application and the second logical part comprising a second portion of the functionality of the software application, the first portion being different from the second portion and being independently executable from the second portion;

receiving a specification of at least one term of a service-level agreement (SLA) between the application owner and the cloud operator, the at least one term of the SLA identifying at least one performance level for execution of the software application by the cloud computing platform and at least one condition, the at least one performance level comprising a first expected execution time of the first logical part and a second expected execution time of the second logical part, the at least one condition comprising a load to be imposed on the cloud computing platform by the software application;

configuring the cloud computing platform, based on the SLA between the application owner and the cloud operator, to allocate the resources of the cloud computing platform to the first logical part and the second logical part of software application so as to meet the at least one performance level specified in the SLA when the at least one condition is met.

11. The method of claim 10, wherein:

the resources of the cloud computing platform comprise a plurality of resource containers, each resource container being associated with hardware and/or software resources, and

the method further comprises determining at least one first operational characteristic for the first logical part at least in part by configuring a single resource container to act as the first logical part and executing the first logical part on the single resource container, the at least one first operational characteristic comprising the first expected execution time.

12. The method of claim 11, further comprising:

based on the at least one first operational characteristic, determining an amount of resources to be used by the first logical part for the software application to execute in accordance with the at least one agreed performance level of the SLA,

wherein the configuring comprises configuring the cloud computing platform to manage allocation of resources based on the amount of resources.

13. The method of claim 12, wherein the configuring comprises configuring the cloud computing platform to, when the amount of resources determined to be used by the first logical part is allocated to the first logical part and a first current execution time for the first logical part deviates from the first expected execution time, notify the application owner that the first current execution time deviates from the first expected execution time.

14. The method of claim 12, wherein the configuring comprises configuring the cloud computing platform to, when less than the amount of resources determined to be used by the first logical part is allocated to the first logical part, a first current execution time for the first logical part exceeds the first expected execution time, and a current load imposed by the software application satisfies the at least one condition, allocating additional resources to the first logical part.

15. The method of claim 10, further comprising:

when a current load imposed by the software application satisfies the at least one condition, comparing an execution time of the software application to the upper limit on acceptable execution times under the SLA, wherein the comparing comprises comparing a first execution time of the first logical part to the first expected execution time of the first logical part and comparing a second execution time of the second logical part to the second expected execution time of the second logical part; and

adjusting billing of the application owner for execution of the software application based at least in part on a result of the comparing.

16. At least one computer-readable storage medium having encoded thereon computer-executable instructions that, when executed by a computer, cause the computer to carry out a method for allocating resources of the cloud computing platform to a software application, the software application being associated with an application owner and the cloud computing platform being operated by a cloud operator, the software application comprising a first logical part and a second logical part, the method comprising:

monitoring execution of the first logical part and the second logical part to determine at least one first value for at least one first actual operational characteristic for the first logical part and at least one second value for at least one second actual operational characteristic for the second logical part;

comparing the at least one first value and the at least one second value to at least one expected operational characteristic for the software application; and

based on the comparing, managing an allocation of the resources of the cloud computing platform to the first logical part or the second logical part.

17. The at least one computer-readable storage medium of claim 16, wherein:

the at least one first value comprises a first execution time for the first logical part and the at least one second value comprises a second execution time for the second logical part,

the at least one expected operational characteristic comprises a first expected operational characteristic for the first logical part and a second expected operational characteristic for the second logical part, and

managing, based on the comparing, comprises refraining from adjusting the allocation when the comparing indicates that the at least one first value is compliant with the at least one first expected operational characteristic or the at least one second value is compliant with the at least one second expected operational characteristic.

18. The at least one computer-readable storage medium of claim 16, wherein:

the resources of the cloud computing platform comprise a plurality of resource containers, each resource container being associated with hardware and/or software resources, and

the comparing further comprises comparing a current allocation of resources to the first logical part to an amount of resources to be used by the first logical part of the software application to execute in accordance with at least one agreed performance level, and

the managing, based on the comparing, comprises, when the comparing indicates that the amount of resources is allocated to the first logical part, refraining from allocating additional resources to the first logical part.

19. The at least one computer-readable storage medium of claim 18, wherein:

the at least one agreed performance level comprises an upper limit on acceptable execution times for an operation of the software application, and

managing the allocation of resources comprises adjusting the allocation of resources to the first logical part or the second logical part such that an execution time of operation of the software application is below the upper limit.

20. The at least one computer-readable storage medium of claim 16, wherein the method further comprises:

receiving a specification of at least one term of a service-level agreement (SLA) between the application owner and the cloud operator, the at least one term of the SLA identifying at least one agreed performance level for execution of the software application by the cloud computing platform and at least one condition, the at least one condition comprising the at least one expected operational characteristic; and

configuring the cloud computing platform, based on the SLA between the application owner and the cloud operator, to allocate the resources of the cloud computing platform to the first logical part and the second logical part of software application so as to meet the at least one agreed performance level specified in the SLA when the at least one condition is met.