System for allocating resources in a distributed computing system

• US 8,005,956 B2
• Filed: 01/22/2008
• Issued: 08/23/2011
• Est. Priority Date: 01/22/2008
• Status: Active Grant

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: Raytheon Company (Rtx Corporation)
• Inventors: Williams, Michael L., Forsman, Michael L., Mays, James J.
• Primary Examiner(s): Osman, Ramy M
• Application Number:
  US12/018,021
• Publication Number:
  US 20090187658A1
• Time in Patent Office: 1,309 Days
• Field of Search: 709/223, 709/224, 709/225, 709/226, 709/229, 709/203, 718/102, 718/104, 370/252
• US Class Current: 709/226
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/60 Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources admission control or resource allocation H04L47/70

Abstract

According to one embodiment, a distributed computing system includes a resource control system coupled to a web server. The web server configured in a service oriented architecture and operable to provide a business application by executing a plurality of services on a plurality of computers configured in the distributed computing system. The resource control system is operable to determine a performance parameter of the business application, and provision or un-provision one of the plurality of computers according to the determined performance parameter.

Claims

1. A distributed computing system comprising:

a computer-implemented resource control system communicatively coupled to a web server, the web server configured in a service oriented architecture and operable to provide a business application by executing a plurality of services on a plurality of grid nodes configured in a computing grid, the resource control system operable to;

receive a performance parameter of the business application;

dynamically provision or un-provision one of the plurality of grid nodes according to the received performance parameter while the other grid nodes in the plurality of grid nodes remain operational; and

provision or un-provision one of the plurality of services according to the received performance parameter independent of dynamically provisioning or un-provisioning any of the plurality of grid nodes according to the received performance parameter.

2. The distributed computing system of claim 1, wherein the resource control system is operable to provision or un-provision one of the plurality of computers instantaneously in response to the received performance parameter exceeding a threshold value.

3. The distributed computing system of claim 1, wherein the resource control system is operable to provision or un-provision one of the plurality of computers according to a periodic schedule.

4. The distributed computing system of claim 1, wherein the resource control system is operable to provision or un-provision one of the plurality of computers according an heuristically assessed resource demand.

5. A distributed computing system comprising:

a resource control system communicatively coupled to a web server, the web server configured in a service oriented architecture and operable to provide a business application by executing a plurality of services on a plurality of computers configured in the distributed computing system, the resource control system operable to;

determine a performance parameter of the business application, the determined performance parameter indicating a level of performance at which the business application is operating;

provision or un-provision one of the plurality of computers according to the determined performance parameter; and

provision or un-provision one of the plurality of services according to the determined performance parameter independent of provisioning or un-provisioning any of the plurality of computers according to the determined performance parameter.

6. The distributed computing system of claim 5, wherein the resource control system is operable to provision or un-provision one of the plurality of services according to the determined performance parameter.

7. The distributed computing system of claim 5, wherein the resource control system comprises a virtualization engine, the virtualization engine operable to dynamically provision or un-provision one of the plurality of computers while the other plurality of computers are operating.

8. The distributed computing system of claim 5, wherein the plurality of computers comprise a plurality of grid nodes, the resource control system operable to provision or un-provision one of the plurality of grid nodes according to the determined performance parameter.

9. The distributed computing system of claim 5, wherein the resource control system is operable to provision or un-provision one of the plurality of computers instantaneously in response to the determined performance parameter exceeding a threshold value.

10. The distributed computing system of claim 5, wherein the resource control system is operable to provision or un-provision one of the plurality of computers according to a periodic schedule.

11. The distributed computing system of claim 5, wherein the resource control system is operable to provision or un-provision one of the plurality of computers according an heuristically assessed resource demand.

12. The distributed computing system of claim 5, wherein the resource control system comprises a service registry for storage of configuration information of the plurality of computers and the plurality of component services, the service registry comprising a universal description and discovery identification (UDDI) protocol.

13. A method comprising:

determining a performance parameter of a business application provided by a plurality of services, the plurality of services operable to be executed on a plurality of computers configured in the distributed computing system, the determined performance parameter indicating a level of performance at which the business application is operating;

provisioning or un-provisioning one of the plurality of computers according to the determined performance parameter; and

provisioning or un-provisioning one of the plurality of services according to the determined performance parameter independent of provisioning or un-provisioning any of the plurality of computers according to the determined performance parameter.

14. The method of claim 13, further comprising provisioning or un-provisioning one of the plurality of services according to the determined performance parameter.

15. The method of claim 13, further comprising dynamically provisioning or un-provisioning one of the plurality of computers while the other plurality of computers are operating.

16. The method of claim 13, wherein provisioning or un-provisioning one of the plurality of computers according to the determined performance parameter further comprises provisioning or un-provisioning one of the plurality of computers instantaneously in response to the determined performance parameter exceeding a threshold value.

17. The method of claim 13, wherein provisioning or un-provisioning one of the plurality of computers according to the determined performance parameter further comprises provisioning or un-provisioning one of the plurality of computers according to a periodic schedule.

18. The method of claim 13, wherein provisioning or un-provisioning one of the plurality of computers according to the determined performance parameter further comprises provisioning or un-provisioning one of the plurality of computers according an heuristically assessed resource demand.

19. The method of claim 13, further comprising provisioning or un-provisioning one of a plurality of grid nodes according to the determined performance parameter, the plurality of the plurality of computers comprising the plurality of grid nodes.

20. The method of claim 13, further comprising storing references to the plurality of computers and the plurality of services in a registry using a universal description and discovery identification (UDDI) protocol.

21. A distributed computing system comprising:

a computer-implemented resource control system for managing resources of a business application, the business application provided by executing a plurality of services on a plurality of grid nodes, the resource control system operable to;

receive a performance parameter of the business application;

determine whether to dynamically provision or un-provision one of the plurality of grid nodes based on the performance parameter while the remaining grid nodes in the plurality of grid nodes remain operational for executing the plurality of services that provide the business application;

dynamically provision or un-provision one of the plurality of grid nodes based on the determination to dynamically provision or un-provision one of the plurality of grid nodes;

determine whether to provision or un-provision one of the plurality of services based on the performance parameter independent of the determination to dynamically provision or un-provision any of the plurality of grid nodes based on the performance parameter; and

provision or un-provision one of the plurality of services based on the determination to provision or un-provision one of the plurality of services.

22. The distributed computing system of claim 21, wherein the resource control system operable to determine whether to dynamically provision or un-provision one of the plurality of grid nodes based on the performance parameter is operable to determine whether to provision or un-provision one of the plurality of grid nodes instantaneously in response to the performance parameter exceeding a threshold value.

23. The distributed computing system of claim 21, wherein the resource control system is operable to dynamically provision or un-provision one of the plurality of grid nodes according to a periodic schedule.

24. The distributed computing system of claim 21, wherein the resource control system is operable to dynamically provision or un-provision one of the plurality of grid nodes according an heuristically assessed resource demand.