OPTIMIZING A CLOUD-COMPUTING ENVIRONMENT

20160050108

14/458403

August 13, 2014

A method and associated systems for optimizing a computing platform. A processor joins sets of configurable parameters into groups that each identifies a configuration of the computing environment or of a component or subsystem of the computing environment. The processor generates a set of variations of each group, where each variation identifies a candidate configuration of the component, subsystem, or platform, and where each candidate configuration identifies a distinct set of values of the group of parameters associated with that component, subsystem, or platform. Each configuration of this first generation of configurations undergoes a massively parallel iterative procedure that generates a next generation of configurations by performing operations upon the first generation that are similar to those of a natural-selection process. The procedure repeats until successive generations converge, within resource constraints, to a fittest generation that represents an optimal or most nearly optimal configuration of the computing platform.

1. A method for optimizing a cloud-computing environment, the method comprising: a processor of a computer system receiving extrinsic data that describes a set of virtual resources of the cloud-computing environment; the processor selecting a set of candidate resource configurations, wherein every virtual resource of the set of virtual resources is associated with a plurality of candidate resource configurations of the set of candidate resource configurations in a one-to-many relationship; the processor further selecting a set of candidate environment configurations, wherein each candidate environment configuration of the set of candidate environment configurations comprises at least one candidate resource configuration of the set of candidate resource configurations; the processor provisioning a virtual test environment, wherein the virtual test environment simulates the cloud-computing environment, and wherein the virtual test environment comprises a virtual representation of each virtual resource of the set of virtual resources of the cloud-computing environment; the processor configuring the virtual test environment by successively loading the virtual test environment with combinations of a configuration of at least two candidate environment configurations of the set of candidate environment configurations and a configuration of at least two candidate resource configurations of the set of candidate resource configurations, wherein the at least two candidate resource configurations are associated with a same tested resource of the set of virtual resources; the processor evaluating a first resource-fitness characteristic of a first loaded resource configuration of the at least two candidate resource configurations, wherein the first loaded resource configuration is associated with the same tested resource of the set of virtual resources, and wherein the first resource-fitness characteristic is assigned a value as a function of an operation of the same tested resource within the virtual test environment while the virtual test environment is loaded with the first loaded resource configuration; the processor deriving a value of an environment-fitness characteristic of a first loaded environment configuration of the at least two candidate environment configurations as a function of an operation of the virtual test environment while the virtual test environment is loaded with the first loaded environment configuration; the processor ranking the at least two candidate resource configurations as a function of the evaluating and of the deriving; the processor further ranking the at least two candidate environment configurations as a function of the evaluating and of the deriving; the processor revising at least one candidate resource configuration of the set of candidate resource configurations and at least one candidate environment configuration of the set of candidate environment configurations as a function of the ranking and of the further ranking; the processor repeating the configuring, the evaluating, the deriving, the ranking, the further ranking, and the revising until a termination condition is satisfied; and the processor identifying an optimal environment configuration as a function of the further ranking.

2. The method of claim 1, wherein a first virtual resource of the set of virtual resources comprises a first set of functional blocks, wherein a first functional block of the first set of functional blocks comprises a first set of configurable parameters, and wherein a first configuration of the first virtual resource comprises a first set of values of the first set of configurable parameters.

3. The method of claim 2, further comprising: the processor organizing the set of virtual resources, the functional blocks comprised by each virtual resource of the set of virtual resources, and the sets of configurable parameters associated with each virtual resource of the set of virtual resources into a hierarchical structure, wherein the organizing is performed as a function of the extrinsic data.

4. The method of claim 1, wherein the virtual test environment is provisioned as a function of resource constraints, projected loads, and user requirements further described by the extrinsic data.

5. The method of claim 1, further comprising: the processor identifying a plurality of distinct subsets of a union of the at least two candidate environment configurations and the at least two candidate resource configurations; and the processor performing multiple iterations of the loading, evaluating, and deriving, wherein each iteration of the multiple iterations comprises loading the virtual test environment with a different subset of the plurality of distinct subsets.

6. The method of claim 2, further comprising: the processor organizing the set of all functional blocks comprised by all virtual resources of the set of virtual resources into a set of groups, wherein a first group of the set of groups comprises all functional blocks that comprise one or more configurable parameters associated with a first resource of the set of virtual resources, wherein a configuration of the set of first-resource configurations, of the set of candidate resource configurations, that identifies a configuration of the first resource and comprises the first group of the set of groups, and wherein a distinct candidate configuration of the first resource is identified by a distinct set of one or more values of the one or more configurable parameters comprised by a resource configuration of the set of first-resource configurations.

7. The method of claim 2, wherein revising a first candidate resource configuration comprises revising one or more values of one or more configurable parameters comprised by the first candidate configuration, wherein the first candidate resource configuration is selected from the set of candidate resource configurations by an application of a first statistical function, wherein the one or more configurable parameters are selected from a set of all configurable parameters comprised by the first candidate resource configuration by an application of a second statistical function, and wherein the revised one or more values are selected by an application of a third statistical function.

8. The method of claim 7, wherein the first, second, or third statistical function comprises a random selection.

9. The method of claim 2, wherein the revising at least one candidate resource configuration comprises producing and adding two new configurations to the set of candidate resource configurations by crossing two existing configurations of the set of candidate resource configurations, wherein the two existing configurations each identify a distinct configuration of a same crossover resource of the set of virtual resources, and wherein crossing a first configuration of the two existing configurations with a second configuration of the two existing configurations comprises: the processor selecting one or more configurable parameters common to both of the two existing configurations; and the processor swapping a first set of values of the selected one or more configurable parameters comprised by the first configuration with a second set of values of the selected one or more configurable parameters comprised by the second configuration, wherein the two existing configurations are selected from the set of candidate resource configurations by an application of a first statistical function, and wherein the selected one or more configurable parameters are selected from a set of all configurable parameters comprised by the two existing configurations by an application of a second statistical function.

10. The method of claim 9, wherein the first statistical function or the second statistical function comprises a random selection.

11. The method of claim 1, wherein the termination condition is satisfied when one repetition of the configuring, the evaluating, the deriving, the ranking, the further ranking, and the revising does not substantially alter the set of candidate resource configurations and the set of candidate environment configurations, wherein the substantially altering comprises producing a difference in one or more values of one or more configurable parameters comprised by the set of candidate resource configurations or by the set of set of candidate environment configurations, such that the produced difference exceeds a predetermined threshold level.

12. The method of claim 1, wherein the termination condition is selected from a group comprising: repeating the provisioning, the configuring, the evaluating, the deriving, the ranking, the further ranking, and the revising a predetermined number of times; consuming an amount or number of resources that exceeds a predetermined threshold level; and exceeding a time limit.

13. The method of claim 1, wherein the identifying an optimal environment configuration is a further function of the revising.

14. The method of claim 1, further comprising providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer-readable program code in the computer system, wherein the computer-readable program code in combination with the computer system is configured to implement the receiving, selecting, further selecting, provisioning, configuring, evaluating, deriving, ranking, further ranking, revising, repeating, and identifying.

15. A computer program product, comprising a computer-readable hardware storage device having a computer-readable program code stored therein, said program code configured to be executed by a processor of a computer system to implement a method for optimizing a cloud-computing environment, the method comprising: the processor receiving extrinsic data that describes a set of virtual resources of the cloud-computing environment; the processor selecting a set of candidate resource configurations, wherein every virtual resource of the set of virtual resources is associated with a plurality of candidate resource configurations of the set of candidate resource configurations in a one-to-many relationship; the processor further selecting a set of candidate environment configurations, wherein each candidate environment configuration of the set of candidate environment configurations comprises at least one candidate resource configuration of the set of candidate resource configurations; the processor provisioning a virtual test environment, wherein the virtual test environment simulates the cloud-computing environment, and wherein the virtual test environment comprises a virtual representation of each virtual resource of the set of virtual resources of the cloud-computing environment; the processor configuring the virtual test environment by successively loading the virtual test environment with combinations of a configuration of at least two candidate environment configurations of the set of candidate environment configurations and a configuration of at least two candidate resource configurations of the set of candidate resource configurations, wherein the at least two candidate resource configurations are associated with a same tested resource of the set of virtual resources; the processor evaluating a first resource-fitness characteristic of a first loaded resource configuration of the at least two candidate resource configurations, wherein the first loaded resource configuration is associated with the same tested resource of the set of virtual resources, and wherein the first resource-fitness characteristic is assigned a value as a function of an operation of the same tested resource within the virtual test environment while the virtual test environment is loaded with the first loaded resource configuration; the processor deriving a value of an environment-fitness characteristic of a first loaded environment configuration of the at least two candidate environment configurations as a function of an operation of the virtual test environment while the virtual test environment is loaded with the first loaded environment configuration; the processor ranking the at least two candidate resource configurations as a function of the evaluating and of the deriving; the processor further ranking the at least two candidate environment configurations as a function of the evaluating and of the deriving; the processor revising at least one candidate resource configuration of the set of candidate resource configurations and at least one candidate environment configuration of the set of candidate environment configurations as a function of the ranking and of the further ranking; the processor repeating the configuring, the evaluating, the deriving, the ranking, the further ranking, and the revising until a termination condition is satisfied; and the processor identifying an optimal environment configuration as a function of the further ranking.

16. The computer program product of claim 15, wherein a first virtual resource of the set of virtual resources comprises a first set of functional blocks, wherein a first functional block of the first set of functional blocks comprises a first set of configurable parameters, and wherein a first configuration of the first virtual resource comprises a first set of values of the first set of configurable parameters.

17. The computer program product of claim 15, wherein the termination condition is satisfied when one repetition of the configuring, the evaluating, the deriving, the ranking, the further ranking, and the revising does not substantially alter the set of candidate resource configurations and the set of candidate environment configurations, wherein the substantially altering comprises producing a difference in one or more values of one or more configurable parameters comprised by the set of candidate resource configurations or by the set of set of candidate environment configurations, such that the produced difference exceeds a predetermined threshold level.

18. A computer system comprising a processor, a memory coupled to said processor, and a computer-readable hardware storage device coupled to said processor, said storage device containing program code configured to be run by said processor via the memory to implement a method for optimizing a cloud-computing environment, the method comprising: the processor receiving extrinsic data that describes a set of virtual resources of the cloud-computing environment; the processor selecting a set of candidate resource configurations, wherein every virtual resource of the set of virtual resources is associated with a plurality of candidate resource configurations of the set of candidate resource configurations in a one-to-many relationship; the processor further selecting a set of candidate environment configurations, wherein each candidate environment configuration of the set of candidate environment configurations comprises at least one candidate resource configuration of the set of candidate resource configurations; the processor provisioning a virtual test environment, wherein the virtual test environment simulates the cloud-computing environment, and wherein the virtual test environment comprises a virtual representation of each virtual resource of the set of virtual resources of the cloud-computing environment; the processor configuring the virtual test environment by successively loading the virtual test environment with combinations of a configuration of at least two candidate environment configurations of the set of candidate environment configurations and a configuration of at least two candidate resource configurations of the set of candidate resource configurations, wherein the at least two candidate resource configurations are associated with a same tested resource of the set of virtual resources; the processor evaluating a first resource-fitness characteristic of a first loaded resource configuration of the at least two candidate resource configurations, wherein the first loaded resource configuration is associated with the same tested resource of the set of virtual resources, and wherein the first resource-fitness characteristic is assigned a value as a function of an operation of the same tested resource within the virtual test environment while the virtual test environment is loaded with the first loaded resource configuration; the processor deriving a value of an environment-fitness characteristic of a first loaded environment configuration of the at least two candidate environment configurations as a function of an operation of the virtual test environment while the virtual test environment is loaded with the first loaded environment configuration; the processor ranking the at least two candidate resource configurations as a function of the evaluating and of the deriving; the processor further ranking the at least two candidate environment configurations as a function of the evaluating and of the deriving; the processor revising at least one candidate resource configuration of the set of candidate resource configurations and at least one candidate environment configuration of the set of candidate environment configurations as a function of the ranking and of the further ranking; the processor repeating the configuring, the evaluating, the deriving, the ranking, the further ranking, and the revising until a termination condition is satisfied; and the processor identifying an optimal environment configuration as a function of the further ranking.

19. The computer system of claim 18, wherein a first virtual resource of the set of virtual resources comprises a first set of functional blocks, wherein a first functional block of the first set of functional blocks comprises a first set of configurable parameters, and wherein a first configuration of the first virtual resource comprises a first set of values of the first set of configurable parameters.

20. The computer system of claim 18, wherein the termination condition is satisfied when one repetition of the configuring, the evaluating, the deriving, the ranking, the further ranking, and the revising does not substantially alter the set of candidate resource configurations and the set of candidate environment configurations, wherein the substantially altering comprises producing a difference in one or more values of one or more configurable parameters comprised by the set of candidate resource configurations or by the set of set of candidate environment configurations, such that the produced difference exceeds a predetermined threshold level.

04; 04

edspap.20160050108