Dynamically resizing a networked computing environment to process a workload

• US 8,924,561 B2
• Filed: 05/13/2011
• Issued: 12/30/2014
• Est. Priority Date: 05/13/2011
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Brown, Gene L., Dawson, Christopher J., Harris, Clifford V., Coffey, Brendan F.
• Primary Examiner(s): Mejia, Anthony
• Assistant Examiner(s): SHAH, MEHULKUMAR J
• Application Number:
  US13/106,904
• Publication Number:
  US 20120290726A1
• Time in Patent Office: 1,327 Days
• Field of Search: 709/226
• US Class Current: 709/226
• CPC Class Codes: G06F 9/5072 Grid computing

Abstract

Embodiments of the present invention provide an approach for a networked computing environment (e.g., a cloud computing environment) to be dynamic in nature in that it may automatically be resized based on current/predicted workload and current/predicted resource availability. For example, when a workload is received, a data structure (e.g., a mapping) will be created on a computer storage device and populated with data related to a set of current resources of the networked computing environment that are allocated to the workload. It will then be determined whether a mismatch (e.g., a shortfall) exists between the set of current resources and resources required for processing the workload. If so, a set of peripheral resources will be identified to rectify the mismatch. The networked computing environment will then be resized to accommodate the set of peripheral resources, and the workload will be processed using the resized networked computing environment.

Claims

1. A computer-implemented method for dynamically resizing a cloud computing environment to optimally accommodate a workload, comprising:

creating a data structure on a computer storage device and populating the data structure with data related to a set of current resources of the cloud computing environment that are allocated to the workload, the cloud computing environment comprising a defined set of cloud computing resources, the data comprising a location of the set of current resources and a current status of the set of current resources;

analyzing current users and expected users of the cloud computing environment to determine a location of each of the current users and the expected users;

determining if a mismatch exists between the set of current resources and resources required for processing the workload based on the location of the set of current resources and the location of each of the current users and the expected users;

responsive to the existence of a mismatch, identifying, based on a required service level and cost minimization, a set of peripheral resources capable of alleviating the mismatch, the set of peripheral resources being resources initially outside of the defined set of cloud computing resources of the cloud computing environment;

resizing the cloud computing environment based upon the identification of the set of peripheral resources, the resizing comprising adding the set of peripheral resources to the defined set of cloud computing resources of the cloud computing environment to optimize a distance between the location of each of the current users and the expected users and the set of peripheral resources; and

processing the workload using the resized cloud computing environment.

2. The computer-implemented method of claim 1, further comprising resizing the networked computing environment to release the set of peripheral resources after the workload has been processed.

3. The computer-implemented method of claim 1, further comprising identifying potential latency inefficiencies occurring in the networked computing environment based on the location of the set of current resources and the location of each of the current and expected users, the set of peripheral resources being further identified to address the potential latency inefficiencies.

4. The computer-implemented method of claim 1, wherein the analyzing step further comprises analyzing the current and expected users of the networked computing environment to determine a priority of each of the current and expected users, and a service level of a cloud service that is being used by each of the current and expected users.

5. The computer-implemented method of claim 4, the workload being at least one of the following:

a current workload or an expected workload of the current and expected users.

6. The computer-implemented method of claim 1, the identifying of the set of peripheral resources comprising cross-referencing a database of resources, the database being stored on at least one computer storage device.

7. A system for dynamically resizing a cloud computing environment to optimally accommodate a workload, comprising:

a bus;

a processor coupled to the bus; and

a memory device coupled to the bus, the memory device comprising instructions to;

create a data structure on a computer storage device and populating the data structure with data related to a set of current resources of the cloud computing environment that are allocated to the workload, the cloud computing environment comprising a defined set of cloud computing resources, the data comprising a location of the set of current resources and a current status of the set of current resources;

analyze current users and expected users of the cloud computing environment to determine a location of each of the current users and the expected users;

determine if a mismatch exists between the set of current resources and resources required for processing the workload based on the location of the set of current resources and the location of each of the current users and the expected users;

responsive to the existence of a mismatch, identify, based on a required service level and cost minimization, a set of peripheral resources capable of alleviating the mismatch, the set of peripheral resources being resources initially outside of the defined set of cloud computing resources of the cloud computing environment;

resize the cloud computing environment based upon the identification of the set of peripheral resources, the resize comprising adding the set of peripheral resources to the defined set of cloud computing resources of the cloud computing environment to optimize a distance between the location of each of the current users and the expected users and the set of peripheral resources; and

process the workload using the resized cloud computing environment.

8. The system of claim 7, the memory device further comprising instructions to resize the networked computing environment to release the set of peripheral resources after the workload has been processed.

9. The system of claim 7, the memory device further comprising instructions to identify potential latency inefficiencies occurring in the networked computing environment based on the location of the set of current resources and the location of each of the current and expected users, the set of peripheral resources being further identified to address the potential latency inefficiencies.

10. The system of claim 7, the memory device further comprising instructions to analyze the current and expected users of the networked computing environment to determine a priority of each of the current and expected users, and a service level of a cloud service that is being used by each of the current and expected users.

11. The system of claim 10, the workload being at least one of the following:

a current workload or an expected workload of the current and expected users.

12. The system of claim 7, the memory device further comprising instructions to cross-reference a database of resources, the database being stored on at least one computer storage device.

13. A computer program product for dynamically resizing a cloud computing environment to optimally accommodate a workload, the computer program product comprising;

a memory device, and program instructions stored on the memory device to;

create a data structure on a computer storage device and populating the data structure with data related to a set of current resources of the cloud computing environment that are allocated to the workload, the cloud computing environment comprising a defined set of cloud computing resources, the data comprising a location of the set of current resources and a current status of the set of current resources;

analyze current users and expected users of the cloud computing environment to determine a location of each of the current users and the expected users;

determine if a mismatch exists between the set of current resources and resources required for processing the workload based on the location of the set of current resources and the location of each of the current users and the expected users;

responsive to the existence of a mismatch, identify, based on a required service level and cost minimization, a set of peripheral resources capable of alleviating the mismatch, the set of peripheral resources being resources initially outside of the defined set of cloud computing resources of the cloud computing environment;

resize the cloud computing environment based upon the identification of the set of peripheral resources, the resize comprising adding the set of peripheral resources to the defined set of cloud computing resources of the cloud computing environment to optimize a distance between the location of each of the current users and the expected users and the set of peripheral resources; and

process the workload using the resized cloud computing environment.

14. The computer program product of claim 13, further comprising program instructions stored on the computer readable storage media to resize the networked computing environment to release the set of peripheral resources after the workload has been processed.

15. The computer program product of claim 13, further comprising program instructions stored on the computer readable storage media to identify potential latency inefficiencies occurring in the networked computing environment based on the location of the set of current resources and the location of each of the current and expected users, the set of peripheral resources being further identified to address the potential latency inefficiencies.

16. The computer program product of claim 13, further comprising program instructions stored on the computer readable storage media to analyze the current and expected users of the networked computing environment to determine a priority of each of the current and expected users, and a service level of a cloud service that is being used by each of the current and expected users.

17. The computer program product of claim 16, the workload being at least one of the following:

a current workload or an expected workload of the current and expected users.

18. The computer program product of claim 13, further comprising program instructions stored on the computer readable storage media to cross-reference a database of resources, the database being stored on at least one computer storage device.

19. A method for deploying a system for dynamically resizing a cloud computing environment to optimally accommodate a workload, comprising:

providing a computer infrastructure being operable to;

create a data structure on a computer storage device and populating the data structure with data related to a set of current resources of the cloud computing environment that are allocated to the workload, the cloud computing environment comprising a defined set of cloud computing resources, the data comprising a location of the set of current resources and a current status of the set of current resources;

analyze current users and expected users of the cloud computing environment to determine a location of each of the current users and the expected users;

determine if a mismatch exists between the set of current resources and resources required for processing the workload based on the location of the set of current resources and the location of each of the current users and the expected users;

responsive to the existence of a mismatch, identify, based on a required service level and cost minimization, a set of peripheral resources capable of alleviating the mismatch, the set of peripheral resources being resources initially outside of the defined set of cloud computing resources of the cloud computing environment;

resize the cloud computing environment based upon the identification of the set of peripheral resources, the resize comprising adding the set of peripheral resources to the defined set of cloud computing resources of the cloud computing environment to optimize a distance between the location of each of the current users and the expected users and the set of peripheral resources; and

process the workload using the resized cloud computing environment.