Automated defect and optimization discovery

• US 9,235,802 B1
• Filed: 06/27/2013
• Issued: 01/12/2016
• Est. Priority Date: 06/27/2013
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: Chamness, Mark, Schnegelberger, Eric
• Primary Examiner(s): Chen, Alan
• Application Number:
  US13/928,810
• Time in Patent Office: 929 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/0751 Error or fault detection not based on redundancy power supply failures G06F1/30; network fault management H04L41/06
• CPC Class Codes: G06F 11/08 Error detection or correction by redundancy in data representation, e.g. by using checking codes
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 11/3476 Data logging G06F11/14, G06F11/2205 take precedence
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/08 Learning methods

Abstract

A method, article of manufacture, and apparatus for identifying defects and resolutions is discussed. Computer systems may be grouped into clusters, and their health may be determined based on these groupings. System optimizations or defect solutions may be distributed to systems in unhealthy clusters, bringing them into a healthy cluster.

Claims

1. A method for identifying defects and optimizations in a computer system, the method comprising:

receiving system data from a plurality of computer systems, said system data comprising system configuration data having configuration attributes and system performance data having performance attributes;

storing the system data on a non-transitory computer readable storage medium;

clustering the computer systems based on at least a portion of the system data;

using a processor to identify a system characteristic from a cluster, wherein the characteristic is selected from a group comprising a system defect and a system optimization; and

distributing a solution to a defect when the system characteristic is the system defect, wherein the solution is only distributed to computer systems that are not in the cluster.

2. The method as recited in claim 1, wherein the performance attributes include CPU utilization, memory utilization, non-transitory computer readable medium capacity, and network bandwidth.

3. The method as recited in claim 1, wherein the configuration attributes include network topology data.

4. The method as recited in claim 1, wherein clustering the computer systems comprises applying a k-means algorithm to the system data.

5. The method as recited in claim 1, further comprising distributing an optimized configuration when the system characteristic is the system optimization.

6. The method of claim 5, wherein the optimized configuration is only distributed to computer systems that are not in the cluster.

7. The method as recited in claim 1, wherein distributing includes:

determining, for each computer system that is not in the cluster, a distance from a healthiest cluster; and

distributing the solution to the defect in descending distance order, such that the solution to the defect is sent first to the cluster that is furthest from the healthiest cluster.

8. The method as recited in claim 1, wherein distributing includes:

determining, for each cluster, a number of computer systems in that cluster; and

distributing the solution to the defect in descending number of computer systems order, such that the solution to the defect is sent first to the cluster having the largest number of computer systems.

9. A system for identifying defects and optimizations in a computer system, the system comprising:

a repository configured to receive system data from a plurality of computer systems, said system data comprising system configuration data and system performance data, wherein the repository comprises a computer readable storage medium and a processor configured to;

store the system data on the computer readable storage medium;

cluster the computer systems based on configuration attributes from the system configuration data and performance attributes from the system performance data;

identify a system characteristic from a cluster, wherein the characteristic is selected from a group comprising a system defect and a system optimization; and

distribute a solution to a defect when the system characteristic is the system defect, wherein the solution is only distributed to computer systems that are not in the cluster.

10. The system of claim 9, wherein clustering the computer systems comprises applying a k-means algorithm to the system data.

11. The system of claim 9, the processor further configured to distribute an optimized configuration when the system characteristic is the system optimization.

12. The system of claim 11, wherein the optimized configuration is only distributed to computer systems that are not in the cluster.

13. The system of claim 9, wherein distributing includes:

determining, for each cluster, a distance from a healthiest cluster; and

distributing the solution to the defect in descending distance order, such that the solution to the defect is sent first to the cluster that is furthest from the healthiest cluster.

14. The system of claim 9, wherein distributing includes:

determining, for each cluster, a number of computer systems in that cluster; and

distributing the solution to the defect in descending number of computer systems order, such that the solution to the defect is sent first to the cluster having the largest number of computer systems.

15. A computer program product for identifying defects and optimizations in a computer system, comprising a non-transitory computer readable storage medium having program instructions embodied therein for:

receiving system data from a plurality of computer systems, said system data comprising system configuration data and system performance data;

storing the system data on a non-transitory computer readable storage medium;

clustering the computer systems based on configuration attributes from the system configuration data and performance attributes from the system performance data;

identifying a system characteristic from a cluster, wherein the characteristic is selected from a group comprising a system defect and a system optimization; and

distributing a solution to a defect when the system characteristic is the system defect, wherein the solution is only distributed to computer systems that are not in the cluster.

16. The computer program product of claim 15, wherein clustering the computer systems comprises applying a k-means algorithm to the system data.

17. The computer program product of claim 15, further comprising distributing an optimized configuration when the system characteristic is the system optimization.

18. The computer program product of claim 17, wherein the optimized configuration is only distributed to computer systems that are in the cluster.

19. The computer program product of claim 15, wherein distributing includes:

determining, for each cluster, a distance from a healthiest cluster; and

distributing the solution to the defect in descending distance order, such that the solution to the defect is sent first to the cluster that is furthest from the healthiest cluster.

20. The computer program product of claim 15, wherein distributing includes:

determining, for each cluster, a number of computer systems in that cluster; and

distributing the solution to the defect in descending number of computer systems order, such that the solution to the defect is sent first to the cluster having the largest number of computer systems.