Automated resource management using perceptron prediction

• US 20040177245A1
• Filed: 03/05/2003
• Published: 09/09/2004
• Est. Priority Date: 03/05/2003
• Status: Active Grant

• Current Assignee: Oracle America, Inc. (Oracle Corporation)
• Original Assignee: Sun Microsystems Incorporated (Oracle Corporation)
• Inventors: Murphy, Richard C.
• Granted Patent: US 7,191,329 B2
• Time in Patent Office: Days
• US Class Current: 713/100
• CPC Class Codes: G06F 9/44505 Configuring for program initiating, e.g. using registry, configuration files

Abstract

A system and method for automatically identifying a desirable reconfiguration of computer system resources, using a perceptron to determine whether one resource configuration will likely be more efficient or more effective than a second configuration. An iterative solver identifies possible configurations or reconfigurations of the resources. A possible configuration is applied to the perceptron, which determines whether the new configuration is more attractive than an existing or baseline configuration, in terms of a predetermined objective function (e.g., cost, performance, resource utilization, throughput). If the new configuration improves the objective function, the new configuration may be automatically or manually applied through a dynamic reconfiguration operation.

Claims

1. A method of using a perceptron to facilitate dynamic reconfiguration of computer system resources, comprising:

receiving a resource dependency graph identifying resource dependencies within a set of resources;

executing an iterative solver to identify a first possible distribution of the resources among one or more containers, wherein each container comprises one or more resources allocated to a task; and

inputting said first possible distribution of the resources to a perceptron configured to predict the impact of said first possible distribution on a predetermined objective function for evaluating the resources.

2. The method of claim 1, further comprising:

receiving from the perceptron an indication of whether the objective function would be improved if said first possible distribution was applied.

3. The method of claim 1, further comprising:

receiving from the perceptron an indication of the extent to which the objective function would be improved if said first possible distribution was applied.

4. The method of claim 1, further comprising:

receiving from the perceptron an indication of whether the objective function would be maximized if said first possible distribution was applied.

5. The method of claim 1, further comprising:

applying said first possible distribution if the perceptron predicts that said first possible distribution would improve the predetermined objective function.

6. The method of claim 1, wherein the predetermined objective function is the cost of operating the set of resources.

7. The method of claim 1, wherein the predetermined objective function is the performance of the set of resources.

8. The method of claim 1, wherein the predetermined objective function is throughput.

9. The method of claim 1, wherein the predetermined objective function is resource utilization.

10. The method of claim 1, further comprising, prior to said inputting said possible distribution:

training the perceptron by;

inputting to the perceptron a previous distribution of the set of resources;

receiving a corresponding output; and

adjusting weights of the perceptron based on a difference between the corresponding output and a measure of the predetermined objective function at the time of the previous distribution of the set of resources.

11. The method of claim 1, wherein said executing an iterative solver comprises:

identifying one or more distributions of the set of resources, including said first possible distribution, different than a current distribution of the resources

12. The method of claim 11, further comprising:

for each of the one or more distributions, determining whether said distribution would violate any constraints on the set of resources.

13. The method of claim 11, further comprising:

determining which of the one or more distributions is optimal.

14. A computer readable storage medium storing instructions that, when executed by a computer, cause the computer to perform a method of using a perceptron to facilitate dynamic reconfiguration of computer system resources, the method comprising:

receiving a resource dependency graph identifying resource dependencies within a set of resources;

executing an iterative solver to identify a possible distribution of the resources among one or more containers, wherein each container comprises one or more resources allocated to a task; and

inputting said possible distribution of the resources to a perceptron configured to predict the impact of said possible distribution on a predetermined objective function for evaluating the resources.

15. A method of using a perceptron to facilitate the dynamic reconfiguration of computer system resources, comprising:

constructing a resource dependency graph for a collection of computer system resources, wherein each node of said graph represents one of;

a physical resource; and

a logical construct built upon a physical resource;

wherein each edge connecting two resources represents a dependency between the two resources;

from a given configuration of the collection of computer system resources, identifying a possible reconfiguration of the collection of computer system resources;

determining whether said possible reconfiguration violates any constraints; and

using a perceptron to predict a performance of said possible reconfiguration in terms of a predetermined objective function.

16. The method of claim 15, further comprising:

if said predicted performance is greater then a performance of said given configuration in terms of the predetermined objective function, initiating said possible reconfiguration.

17. The method of claim 15, wherein the objective function is a cost associated with the collection of computer system resources.

18. The method of claim 15, wherein the objective function is one of utilization and throughput of the collection of computer system resources.

19. The method of claim 15, wherein said configuration comprises a first distribution of the collection of system resources among a first plurality of logical containers.

20. The method of claim 19, wherein said possible reconfiguration comprises a second distribution of the collection of system resources among a second plurality of logical containers.

21. The method of claim 15, wherein each said constraint places a limitation or requirement upon the distribution of the collection of system resources among a plurality of containers.

22. The method of claim 21, wherein each said container is one of:

a domain of resources operating under one instance of an operating system; and

a set of resources operating under multiple instances of one or more operating systems, wherein the set of resources cooperate to provide a service.

23. A computer readable storage medium storing instructions that, when executed by a computer, cause the computer to perform a method of using a perceptron to facilitate the dynamic reconfiguration of computer system resources, the method comprising:

constructing a resource dependency graph for a collection of computer system resources, wherein each node of said graph represents one of;

a physical resource; and

a logical construct built upon a physical resource;

wherein each edge connecting two resources represents a dependency between the two resources;

from a given configuration of the collection of computer system resources, identifying a possible reconfiguration of the collection of computer system resources;

determining whether said possible reconfiguration violates any constraints; and

using a perceptron to predict a performance of said possible reconfiguration in terms of a predetermined objective function.

24. An apparatus for identifying a desirable reconfiguration of computer system resources, comprising:

one or more platforms comprising physical computer system resources, wherein one or more logical resources may be constructed upon each of the physical resources;

a graph module configured to facilitate the assembly of a resource dependency graph representing a first configuration of the physical resources and the logical resources, wherein the resource dependency graph comprises;

vertices representing each of the physical resources and each of the logical resources; and

edges, wherein each edge represents a dependency between a first physical or logical resource and a second physical or logical resource; and

a partitioner configured to identify a second configuration of the physical resources and the logical resources, wherein the second configuration provides greater value than the first configuration as measured by an objective function.

25. The apparatus of claim 24, wherein the objective function comprises one of:

a cost associated with the physical computer system resources; and

a performance of the physical computer system resources.

26. The apparatus of claim 24, wherein the objective function comprises one of:

a utilization of physical computer system resources; and

a throughput of the physical computer system resources.

27. The apparatus of claim 24, wherein said partitioner comprises:

an iterative solver configured to identify a possible configuration of the physical resources and the logical resources different from the first configuration; and

a perceptron configured to evaluate said possible configuration in terms of the objective function.

28. The apparatus of claim 27, wherein said partitioner is further configured to determine whether said possible configuration violates any of a set of constraints placed upon the physical resources and the logical resources.