Failure analysis based on time-varying failure rates

• US 8,024,609 B2
• Filed: 06/03/2009
• Issued: 09/20/2011
• Est. Priority Date: 06/03/2009
• Status: Active Grant

• Current Assignee: Lenovo International Limited (Lenovo Group Ltd.)
• Original Assignee: International Business Machines Corporation
• Inventors: Suffern, Edward S.
• Primary Examiner(s): Beausoliel, Jr.; Robert W
• Assistant Examiner(s): Lottich; Joshua P
• Application Number:
  US12/477,199
• Publication Number:
  US 20100313072A1
• Time in Patent Office: 839 Days
• Field of Search: 714/25, 714/26, 714/47, 714/48, 714/37, 714/47.1
• US Class Current: 714/25
• CPC Class Codes: G06F 11/0706 the processing taking place on a specific hardware platform or in a specific software environment
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40

Abstract

Failure analysis method and apparatus using failure rate data in coordination with the power on hours to more efficiently resolve computer system failures without occupying system memory or processor bandwidth. In response to a system failure, a baseboard management controller (BMC) notes the time of failure and the elapsed operating time of system components. In response to a failure of the computer system, the BMC accesses industry standard failure rate data correlating the elapsed operating time with the probability of failure for each component. By cross-referencing the time of failure with the failure rate data, the BMC automatically determines the probability of failure of each component at the time of failure of the computer system. The BMC generates a component replacement list identifying the component that currently has the highest probability of failure.

Claims

1. A method comprising:

obtaining failure rate data correlating the elapsed operating time with the probability of failure for each of a plurality of components of a computer system;

tracking the elapsed operating time of each component of the computer system, wherein the step of tracking is performed by a baseboard management controller independently of an operating system or a central processing unit; and

in response to a failure of the computer system, automatically determining the probability of failure of each component at the time of failure of the computer system from the failure rate data, and generating a component replacement list indicating the component having the highest probability of failure at the time of failure.

2. The method of claim 1, further comprising:

narrowing the cause of failure of the computer system to a subset of two or more but fewer than all of the components; and

thereafter automatically determining the probability of failure of each component in the subset at the time of failure from the failure rate data, and generating a component replacement list indicating which component of the subset has the highest probability of failure at the time of failure.

3. The method of claim 1, further comprising:

automatically generating a visible or audible alert in response to the component replacement list using the baseboard management controller and sending the alert using the baseboard management controller to a system administrator over a network.

4. The method of claim 3, further comprising:

generating a visible or audible alert on or near the component having the highest determined probability of failure in response to the component replacement signal.

5. The method of claim 1, further comprising:

storing the component replacement list in a system event log.

6. The method of claim 1, further comprising:

ranking the components according to their respective probabilities of failure and visually displaying the ranking.

7. The method of claim 6, further comprising:

replacing the components in order of decreasing probability of failure until the failure of the computer system is resolved.

8. A computer program product including computer usable code embodied on a non-transitory computer readable medium, the computer usable code for performing failure analysis on components of a computer system, the computer usable program code including:

computer usable program code for obtaining failure rate data correlating the elapsed operating time with the probability of failure for each component;

computer usable program code for tracking the elapsed operating time of each component without using an operating system or a central processing unit of the computer system; and

computer usable program code for, in response to a failure of the computer system, automatically determining the probability of failure of each component at the time of failure of the computer system from the failure rate data, and generating a component replacement list indicating the component having the highest probability of failure at the time of failure.

9. The computer program product of claim 8, further comprising:

computer usable program code embodying a maintenance analysis procedure for narrowing the cause of failure of the computer system to a subset of two or more but fewer than all of the components; and

computer usable program code for thereafter automatically determining the probability of failure of each component in the subset at the time of failure from the failure rate data, and generating a component replacement signal indicating which component of the subset has the highest probability of failure at the time of failure.

10. The computer program product of claim 8, further comprising:

computer usable program code for causing a visible or audible alert to be automatically generated in response to the component replacement list using a baseboard management controller; and

computer usable program code for sending the alert using the baseboard management controller to a system administrator over a network.

11. The computer program product of claim 8, further comprising:

computer usable program code for generating a visible or audible alert on or near the component having the highest determined probability of failure in response to the component replacement list.

12. The computer program product of claim 8, further comprising:

computer usable program code for ranking the components according to their respective probabilities of failure and visually displaying the ranking.

13. A computer system comprising:

a plurality of components; and

a baseboard management controller containing computer usable program code for performing failure analysis, the computer usable program code including computer usable program code for obtaining failure rate data correlating the elapsed operating time with the probability of failure for each component, computer usable program code for tracking the elapsed operating time of each component without using an operating system or a central processing unit of the computer system, and computer usable program code for, in response to a failure of the computer system, automatically determining the probability of failure of each component at the time of failure of the computer system from the failure rate data, and generating a component replacement list indicating the component having the highest probability of failure at the time of failure.

14. A method comprising:

obtaining failure rate data correlating the elapsed operating time with the probability of failure for each of a plurality of components of a computer system;

tracking the elapsed operating time of each component of the computer system; and

in response to a failure of the computer system, automatically determining the probability of failure of each component at the time of failure of the computer system from the failure rate data, generating a component replacement list indicating the component having the highest probability of failure at the time of failure, and storing the component replacement list in a system event log.

15. The method of claim 14, wherein the step of tracking the elapsed operating time of each component is performed by a baseboard management controller of the computer system, wherein the elapsed operating time is tracked independently of an operating system or a central processing unit.

16. The method of claim 14, further comprising:

narrowing the cause of failure of the computer system to a subset of two or more but fewer than all of the components; and

thereafter automatically determining the probability of failure of each component in the subset at the time of failure from the failure rate data, and generating a component replacement list indicating which component of the subset has the highest probability of failure at the time of failure.

17. The method of claim 14, further comprising:

automatically generating a visible or audible alert in response to the component replacement list using a baseboard management controller and sending the alert using a baseboard management controller to a system administrator over a network.

18. The method of claim 17, further comprising:

generating a visible or audible alert on or near the component having the highest determined probability of failure in response to the component replacement signal.

19. The method of claim 14, further comprising:

ranking the components according to their respective probabilities of failure and visually displaying the ranking.

20. The method of claim 19, further comprising:

replacing the components in order of decreasing probability of failure until the failure of the computer system is resolved.