SYSTEM AND METHOD FOR ALLOCATING A CLUSTER OF NODES FOR A CLOUD COMPUTING SYSTEM BASED ON HARDWARE CHARACTERISTICS

• US 20140047342A1
• Filed: 08/07/2012
• Published: 02/13/2014
• Est. Priority Date: 08/07/2012
• Status: Abandoned Application

• Current Assignee: Advanced Micro Devices, Inc.
• Original Assignee: Advanced Micro Devices, Inc.
• Inventors: Breternitz, Mauricio, Lowery, Keith A., Kaminski, Patryk, Chernoff, Anton
• Application Number:
  US13/568,395
• Publication Number:
  US 20140047342A1
• Time in Patent Office: Days
• US Class Current: 715/735
• CPC Class Codes: G06F 9/5061 Partitioning or combining of resources

Abstract

The present disclosure relates to a method and system for configuring a computing system, such as a cloud computing system. A method includes initiating a hardware performance assessment test on a group of available nodes to obtain actual hardware performance characteristics of the group of available nodes. The method further includes selecting a subset of nodes for the computing system from the group of available nodes based on a comparison of the actual hardware performance characteristics of the group of available nodes and desired hardware performance characteristics.

Claims

1. A method of configuring a computing system carried out by one or more computing devices, the method comprising:

initiating a hardware performance assessment test on a group of available nodes to obtain actual hardware performance characteristics of the group of available nodes; and

selecting a subset of nodes for the computing system from the group of available nodes based on a comparison by the one or more computing devices of the actual hardware performance characteristics of the group of available nodes and desired hardware performance characteristics, the subset of nodes being operative to share processing of a workload.

2. The method of claim 1, further comprising

receiving a user request via a user interface requesting a cluster of nodes for the computing system having the desired hardware performance characteristics;

and

selecting the group of available nodes for initiating the hardware performance assessment test based on the user request of the cluster of nodes, the number of nodes of the group of available nodes being greater than the number of nodes of the cluster of nodes requested with the user request.

3. The method of claim 2, wherein the group of available nodes comprises a first group of available nodes and the subset of nodes comprises a first subset of nodes, further comprising

selecting a second group of available nodes different from the first group of available nodes;

initiating the hardware performance assessment test on the second group of available nodes to obtain actual hardware performance characteristics of the second group of available nodes; and

selecting a second subset of nodes for the computing system from the second group of available nodes based on a comparison by the one or more computing devices of the actual hardware performance characteristics of the second group of available nodes and the desired hardware performance characteristics.

4. The method of claim 3, wherein the combined number of nodes of the first and second subsets of nodes is less than or equal to the number of nodes of the cluster of nodes requested with the user request.

5. The method of claim 1, further comprising aggregating hardware performance data resulting from the hardware performance assessment test on each node of the group of available nodes to obtain the actual hardware performance characteristics.

6. The method of claim 1, wherein each node of the group of available nodes comprises at least one processor and memory accessible by the at least one processor, and wherein the desired hardware performance characteristics and the actual hardware performance characteristics comprise at least one of:

an operating frequency of the at least one processor of a node, a computer architecture of the at least one processor of a node, a manufacturer of the at least one processor of a node, and a read/write performance of the at least one processor of a node.

7. The method of claim 1, further comprising providing a user interface comprising selectable hardware configuration data, wherein the desired hardware performance characteristics are identified based on at least one user selection of the selectable hardware configuration data.

8. The method of claim 1, further comprising

selecting, based on at least one user selection of selectable workload data provided with a user interface, a workload for execution by the subset of nodes;

and

configuring the subset of nodes with the selected workload such that the subset of nodes share processing of the workload.

9. A computing configuration system comprising:

a data monitor configurator operative to initiate a hardware performance assessment test on a group of available nodes to obtain actual hardware performance characteristics of the group of available nodes, and

a node configurator operative to select a subset of nodes for a computing system that are operative to share processing of a workload, the subset of nodes being selected from the group of available nodes based on a comparison by the node configurator of the actual hardware performance characteristics of the group of available nodes and desired hardware performance characteristics.

10. The system of claim 9, wherein the node configurator is further operative to:

receive a user request via a user interface requesting a cluster of nodes for the computing system having the desired hardware performance characteristics, and

select the group of available nodes for initiating the hardware performance assessment test based on the user request of the cluster of nodes, the number of nodes of the group of available nodes being greater than the number of nodes of the cluster of nodes requested with the user request.

11. The system of claim 10, wherein the group of available nodes comprises a first group of available nodes and the subset of nodes comprises a first subset of nodes, wherein the data monitor configurator is further operative to initiate the hardware performance assessment test on a second group of available nodes selected by the node configurator to obtain actual hardware performance characteristics of the second group of available nodes, the second group of available nodes being different from the first group of available nodes, and wherein the node configurator is further operative to select a second subset of nodes for the computing system from the second group of available nodes based on a comparison by the node configurator of the actual hardware performance characteristics of the second group of available nodes and the desired hardware performance characteristics.

12. The system of claim 11, wherein the combined number of nodes of the first and second subsets of nodes is less than or equal to the number of nodes of the cluster of nodes requested with the user request.

13. The system of claim 9, further comprising a data aggregator operative to aggregate hardware performance data resulting from the hardware performance assessment test on each node of the group of available nodes to obtain the actual hardware performance characteristics.

14. The system of claim 9, wherein each node of the group of available nodes comprises at least one processor and memory accessible by the at least one processor, and wherein the desired hardware performance characteristics and the actual hardware performance characteristics comprise at least one of:

an operating frequency of the at least one processor of a node, a computer architecture of the at least one processor of a node, a manufacturer of the at least one processor of a node, and a read/write performance of the at least one processor of a node.

15. The system of claim 9, further comprising at least one processor and memory containing executable instructions that when executed by the at least one processor cause the at least one processor to provide a graphical user interface comprising selectable hardware configuration data, wherein the desired hardware performance characteristics are identified by the node configurator based on at least one user selection of the selectable hardware configuration data.

16. The system of claim 9, further comprising a workload configurator operative to select, based on at least one user selection of selectable workload data provided with a user interface, a workload for execution by the subset of nodes, and to configure the subset of nodes with the selected workload such that the subset of nodes share processing of the workload.

17. A non-transitory computer-readable medium comprising:

executable instructions such that when executed by at least one processor cause the at least one processor to;

initiate a hardware performance assessment test on a group of available nodes to obtain actual hardware performance characteristics of the group of available nodes; and

select a subset of nodes for a computing system that are operative to share processing of a workload, the subset of nodes being selected from the group of available nodes based on a comparison by the at least one processor of the actual hardware performance characteristics of the group of available nodes and desired hardware performance characteristics.

18. The non-transitory computer-readable medium of claim 17, wherein the executable instructions further cause the at least one processor to:

receive a user request via a user interface requesting a cluster of nodes for the computing system having the desired hardware performance characteristics; and

select the group of available nodes for initiating the hardware performance assessment test based on the user request of the cluster of nodes, the number of nodes of the group of available nodes being greater than the number of nodes of the cluster of nodes requested with the user request.

19. The non-transitory computer-readable medium of claim 18, wherein the group of available nodes comprises a first group of available nodes and the subset of nodes comprises a first subset of nodes, wherein the executable instructions further cause the at least one processor to:

select a second group of available nodes different from the first group of available nodes;

initiate the hardware performance assessment test on the second group of available nodes to obtain actual hardware performance characteristics of the second group of available nodes; and

select a second subset of nodes for the computing system from the second group of available nodes based on a comparison by the at least one processor of the actual hardware performance characteristics of the second group of available nodes and the desired hardware performance characteristics.

20. The non-transitory computer-readable medium of claim 19, wherein the combined number of nodes of the first and second subsets of nodes is less than or equal to the number of nodes of the cluster of nodes requested with the user request.

21. The non-transitory computer-readable medium of claim 17, wherein the executable instructions further cause the at least one processor to aggregate hardware performance data resulting from the hardware performance assessment test on each node of the group of available nodes to obtain the actual hardware performance characteristics.

22. The non-transitory computer-readable medium of claim 17, wherein each node of the group of available nodes comprises at least one processor and memory accessible by the at least one processor, and wherein the desired hardware performance characteristics and the actual hardware performance characteristics comprise at least one of:

an operating frequency of the at least one processor of a node, a computer architecture of the at least one processor of a node, a manufacturer of the at least one processor of a node, and a read/write performance of the at least one processor of a node.

23. The non-transitory computer-readable medium of claim 17, wherein the executable instructions further cause the at least one processor to provide a graphical user interface comprising selectable hardware configuration data, wherein the desired hardware performance characteristics are identified by the at least one processor based on at least one user selection of the selectable hardware configuration data.

24. The non-transitory computer-readable medium of claim 17, wherein the executable instructions further cause the at least one processor to:

select, based on at least one user selection of selectable workload data provided with a user interface, a workload for execution by the subset of nodes; and

configure the subset of nodes with the selected workload such that the subset of nodes share processing of the workload.