Cloud independent tuning service for autonomously managed workloads

• US 10,009,292 B2
• Filed: 10/03/2014
• Issued: 06/26/2018
• Est. Priority Date: 10/03/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Dunbar, Anthony M., Fall, James J., Hanson, Andrew L., Matzek, Samuel D., Romano, George J., Van Hove, Tammy L.
• Primary Examiner(s): Chea, Philip
• Assistant Examiner(s): Ahmed, Mohammed
• Application Number:
  US14/505,799
• Publication Number:
  US 20160099887A1
• Time in Patent Office: 1,362 Days
• CPC Class Codes: H04L 47/76 using dynamic resource allocation, e.g. in-call renegotiation requested by the user or requested by the network in response to changing network conditions
• CPC Class Codes: H04L 47/827 Aggregation of resource allocation or reservation requests
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30

Abstract

Systems, methods, and computer program products to perform an operation comprising receiving, from a workload in a cloud computing environment, an abstract request to modify resources allocated to the workload, translating, by a tuning service, the abstract request to a set of requirements to fulfill the abstract request, identifying, by the tuning service, a resource configuration suitable to satisfy the set of requirements, and providing, by the tuning service, the resource configuration to fulfill the abstract request.

Claims

1. A system, comprising:

a computer processor; and

a memory containing a program, which when executed by the processor, performs an operation comprising;

receiving, by a tuning service from a workload in a first cloud computing environment based on a performance measurement criteria comprising a level of energy utilization realized by executing the workload on a host machine in the first cloud computing environment, an abstract request generated by the workload specifying to modify resources allocated to the workload, wherein the abstract request does not specify a modified quantity of a first resource required to fulfill the abstract request;

translating, by the tuning service, the abstract request to a set of requirements to fulfill the abstract request, wherein the set of requirements specifies to modify the first resource to reduce the level of energy utilization below a energy utilization threshold;

identifying, by the tuning service based on a current resource configuraton of the workload, a modified resource configuration suitable to provide the modified quantity of the first resource required to fulfill the abstract request;

generating, by the tuning service based on the modified resource configuration, a specific request compatible with a representational state transfer (REST) application programming interface (API) of a resource management component of the first cloud computing environment; and

providing, by the tuning service, the specific request to the REST API of the resource management component of the first cloud computing environment, wherein the resource management component of the first cloud computing environment generates the modified resource configuration including the modified quantity of the first resource responsive to the specific request to fulfill the abstract request.

2. The system of claim 1, wherein the tuning service is external to the first cloud computing environment, wherein the specific request specifies the quantity of the first resource in a format comptaible with the the REST API of the resource management component, wherein the current resource configuration specifies a current quantity of the first resource allocated to the workload, wherein the modified resource configuration further comprises a second computing resource, wherein the first and second computing resources respectively comprise at least one of:

(i) a hardware resource, (ii) a quality of service, and (iii) a software resource provided to the workload.

3. The system of claim 1, wherein the modified resource configuration specifies to move the workload to a different cloud computing environment.

4. The system of claim 1, wherein the modified resource configuration specifies to clone the workload.

5. The system of claim 1, wherein the abstract request comprises a generic request that is agnostic relative to the REST API of the resource management component of the first cloud computing environment.

6. The system of claim 4, wherein a resource utilization of the workload is monitored by:

(i) the workload, and (ii) the tuning service.

7. The system of claim 4, wherein the first cloud computing environment provides a baseline level of resources to the workload upon deployment, wherein the workload and the tuning service are configured to modify the baseline level of resources independent of the configuration of the first cloud computing environment.

14. The system of claim 1, wherein the performance measurement criteria further comprise:

(i) an allocation level for each of a plurality of hardware resources including the first resource, (ii) a utilization level for each of the plurality of hardware resources including the first resource, and (iii) a cost of executing the workload in the cloud computing environment.

15. The system of claim 14, wherein the workload generates the request upon determining that the level of energy utilization exceeds the energy utilization threshold.

16. The system of claim 15, wherein the modified resource configuration specifies to move the workload to a second cloud computing environment, the operation further comprising:

moving, by the tuning service, the workload from the first cloud computing environment to the second cloud computing environment.

17. The system of claim 16, the operation further comprising:

receiving, from the workload in the second cloud computing environment, a second abstract request specifying to modify resources allocated to the workload in the second cloud computing environment, wherein the second abstract request does not specify a modified quantity of a second resource required to fulfill the second abstract request;

translating, by the tuning service, the second abstract request to a set of requirements to fulfill the second abstract request in the second cloud computing environment, wherein the set of requirements to fulfill the second abstract request specifies to modify the second resource;

identifying, by the tuning service based on a current resource configuraton of the workload in the second cloud computing environment, a second modified resource configuration suitable to provide the modified quantity of the second resource in the second cloud computing environment;

generating, by the tuning service based on the second modified resource configuration, a second specific request compatible with a representational state transfer (REST) application programming interface (API) of a resource management component of the second cloud computing environment;

providing, by the tuning service, the second specific request to the REST API of the resource management component of the second cloud computing environment, wherein the resource management component of the second cloud computing environment generates the second modified resource configuration including the modified quantity of the second resource responsive to the second specific request to fulfill the second abstract request.

8. A computer program product, comprising:

a non-transitory computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to perform an operation comprising;

receiving, by a tuning service from a workload in a first cloud computing environment based on a performance measurement criteria comprising a level of energy utilization realized by executing the workload on a host machine in the first cloud computing environment, an abstract request generated by the workload specifying to modify resources allocated to the workload, wherein the abstract request does not specify a modified quantity of a first resource required to fulfill the abstract request;

translating, by the tuning service, the abstract request to a set of requirements to fulfill the abstract request, wherein the set of requirements specifies to modify the first resource to reduce the level of energy utilization below a energy utilization threshold;

identifying, by the tuning service based on a current resource configuraton of the workload, a modified resource configuration suitable to provide the modified quantity of the first resource required to fulfill the abstract request;

generating, by the tuning service based on the modified resource configuration, a specific request compatible with a representational state transfer (REST) application programming interface (API) of a resource management component of the first cloud computing environment; and

providing, by the tuning service, the specific request to the REST API of the resource management component of the first cloud computing environment, wherein the resource management component of the first cloud computing environment generates the the modified resource configuration including the modified quantity of the first resource responsive to the specific request to fulfill the abstract request.

9. The computer program product of claim 8, wherein the tuning service is external to the first cloud computing environment, wherein the specific request specifies the quantity of the first resource in a format comptaible with the the REST API of the resource management component, wherein the current resource configuration specifies a current quantity of the first resource allocated to the workload, wherein the modified resource configuration further comprises a second computing resource, wherein the first and second computing resources respectively comprise at least one of:

(i) a hardware resource, (ii) a quality of service, and (iii) a software resource provided to the workload.

10. The computer program product of claim 8, wherein the modified resource configuration specifies to move the workload to a different cloud computing environment.

11. The computer program product of claim 8, wherein the modified resource configuration specifies to clone the workload.

12. The computer program product of claim 8, wherein the abstract request comprises a generic request that is agnostic relative to the first cloud computing environment.

13. The computer program product of claim 8, wherein a resource utilization of the workload is monitored by:

(i) the workload, and (ii) the tuning service.