Computer-implemented method, system and program product for approximating resource consumption of computer system

• US 7,844,441 B2
• Filed: 03/27/2006
• Issued: 11/30/2010
• Est. Priority Date: 03/27/2006
• Status: Expired due to Fees

• Current Assignee: GlobalFoundries, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Lemberg, Volodimir F., Kozakov, Lev, Grabarnik, Genady, Shwartz, Larisa, Kim, Moon Ju
• Primary Examiner(s): NEURAUTER, GEORGE C
• Application Number:
  US11/390,527
• Publication Number:
  US 20070226348A1
• Time in Patent Office: 1,709 Days
• Field of Search: 703/2, 703/13, 703/21, 706/17, 708/274, 708/422, 708/520
• US Class Current: 703/21
• CPC Class Codes: G06F 2209/5019 Workload prediction
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system

Abstract

In general, the present invention provides a method, system and program product for approximating/estimating computer resource consumption of a computer system. Specifically, under the present invention, a more efficient or reduced computer work gradient matrix (hereinafter “matrix”) is first built. This occurs by creating load measurements for a set of computer resource metrics of the computer system to analyze dependencies between different computer resource metrics. Then, a correlation matrix between the set of computer resource metrics is created based on the dependencies. The set of computer system resource metrics in the correlation matrix is thereafter clustered into a set of clusters, and a reduced matrix is built based thereon. Once the reduced matrix is built, it can be restored to a “full” matrix using linear transformation or the like.

Claims

1. A computer-implemented method for approximating resource consumption of a computer system, comprising:

creating load measurements for a set of computer resource metrics of the computer system to analyze dependencies between different computer resource metrics;

creating a correlation matrix between the set of computer resource metrics;

clustering the set of computer resource metrics in the correlation matrix into a set of clusters;

building a reduced computer work gradient matrix based on the set of clusters;

constructing a set of task work paths that characterize consumption levels of a set of resources in response to a computing task applied to the computer system at a particular background loading level; and

approximating consumption levels of the set of resources for the computing task at any background loading level using the reduced computer work gradient matrix and the set of task work paths.

2. The method of claim 1, further comprising:

restoring the reduced computer work gradient matrix to a full computer work gradient matrix; and

approximating consumption levels of the set of resources for the computing task at any background loading level using the restored computer work gradient matrix and a set of task work paths.

3. The method of claim 1, wherein the clustering is a Markov clustering.

4. The method of claim 1, wherein the building step comprises:

identifying a set of most informative metrics in the set of clusters; and

building the reduced computer work gradient matrix based on the set of most informative metrics.

5. The method of claim 1, further comprising selecting a threshold value for the reduced computer work gradient matrix, wherein the threshold value is based on an uncertainty measure.

6. A system for approximating resource consumption of a computer system, comprising:

a memory;

a system for creating load measurements for a set of computer resource metrics of the computer system to analyze dependencies between different computer resource metrics;

a system for creating a correlation matrix between the set of computer resource metrics;

a system for clustering the set of computer resource metrics in the correlation matrix into a set of clusters;

a system for building a reduced computer work gradient matrix based on the set of clusters;

a system for constructing a set of task work paths that characterize consumption levels of a set of resources in response to a computing task applied to the computer system at a particular background loading level; and

a system for approximating consumption levels of the set of resources for the computing task at any background loading level using the reduced computer work gradient matrix and the set of task work paths.

7. The system of claim 6, further comprising a system for restoring the reduced computer work gradient matrix to a full computer work gradient matrix.

8. The system of claim 6, wherein the clustering is a Markov clustering.

9. The system of claim 6, wherein the system for building identifies a set of most informative metrics in the set of clusters, and builds the reduced computer work gradient matrix based on the set of most informative metrics.

10. The system of claim 6, further comprising a system for selecting a threshold value for the reduced computer work gradient matrix, wherein the threshold value is based on an uncertainty measure.

11. A program product stored on a computer useable storage medium including hardware for approximating resource consumption of a computer system, the computer useable medium comprising program code for causing a computer system to perform the following steps:

creating load measurements for a set of computer resource metrics of the

computer system to analyze dependencies between different computer resource metrics;

creating a correlation matrix between the set of computer resource metrics;

clustering the set of computer resource metrics in the correlation matrix into a set of clusters;

building a reduced computer work gradient matrix based on the set of clusters;

constructing a set of task work paths that characterize consumption levels of a set of resources in response to a computing task applied to the computer system at a particular background loading level; and

approximating consumption levels of the set of resources for the computing task at any background loading level using the reduced computer work gradient matrix and the set of task work paths.

12. The program product of claim 11, wherein the computer useable storage medium including hardware further comprises program code for causing the computer system to perform the following step:

restoring the reduced computer work gradient matrix.

13. The program product of claim 11, wherein the clustering is a Markov clustering.

14. The program product of claim 11, wherein the computer useable storage medium including hardware further comprises program code for causing the computer system to perform the following steps:

identifying a set of most informative metrics in the set of clusters; and

building the reduced computer work gradient matrix based on the set of most informative metrics.

15. The program product of claim 11, wherein the computer useable storage medium including hardware further comprises program code for causing the computer system to perform the following step:

selecting a threshold value for the reduced computer work gradient matrix, wherein the threshold value is based on an uncertainty measure.

16. A method for deploying an application for approximating resource consumption of a computer system, comprising:

providing a computer infrastructure being operable to;

create load measurements for a set of computer resource metrics of the computer system to analyze dependencies between different computer resource metrics;

create a correlation matrix between the set of computer resource metrics;

cluster the set of computer resource metrics in the correlation matrix into a set of clusters;

build a reduced computer work gradient matrix based on the set of clusters

construct a set of task work paths that characterize consumption levels of a set of resources in response to a computing task applied to the computer system at a particular background loading level; and

approximate consumption levels of the set of resources for the computing task at any background loading level using the reduced computer work gradient matrix and the set of task work paths.