Method and apparatus for identifying a failure mechanism for a component in a computer system

• US 20070294591A1
• Filed: 05/11/2006
• Published: 12/20/2007
• Est. Priority Date: 05/11/2006
• Status: Active Grant

• Current Assignee: Oracle America, Inc. (Oracle Corporation)
• Original Assignee: Oracle America, Inc. (Oracle Corporation)
• Inventors: Urmanov, Aleksey, Gross, Kenny, Usynin, Alexander
• Granted Patent: US 7,890,813 B2
• Time in Patent Office: Days
• US Class Current: 714/45
• CPC Class Codes: G06F 1/30 Means for acting in the event of power-supply failure or interruption, e.g. power-supply fluctuations for resetting only G06F1/24
• CPC Class Codes: G06F 11/0748 in a remote unit communicating with a single-box computer node experiencing an error/fault remote testing G06F11/2294
• 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 11/2252 using fault dictionaries

Abstract

One embodiment of the present invention provides a system that identifies a failure mechanism for a component. The system first constructs a library of failure signatures from a set of components, wherein each failure signature in the library characterizes a known failure mechanism associated with a component in the set of components. Next, the system receives a telemetry signal which is measured from a component under surveillance. The system then determines if there is an anomaly in the telemetry signal. If so, the system performs pattern-matching operations between the telemetry signal and failure signatures in the library. Next, if a match is found, the system identifies the failure mechanism for the component under surveillance based on the matching failure signature.

Claims

1. A method for identifying a failure mechanism for a component, comprising:

constructing a library of failure signatures from a set of components, wherein each failure signature in the library characterizes a known failure mechanism associated with a component in the set of components;

receiving a telemetry signal which is measured from a component under surveillance;

determining if there is an anomaly in the telemetry signal, and if so;

performing pattern-matching operations between the telemetry signal and failure signatures in the library; and

if a match is found, identifying the failure mechanism for the component under surveillance based on the matching failure signature.

2. The method of claim 1, wherein constructing the library of failure signatures involves constructing a failure signature for each known failure mechanism of a component, which involves:

receiving one or more faulty specimens of the component, wherein the one or more faulty specimens are associated with a known failure mechanism;

collecting high-resolution, high-sampling-rate telemetry signals from the one or more faulty specimens, wherein the high-resolution, high-sampling-rate telemetry signals contain the failure signature of the known failure mechanism associated with the component; and

storing the failure signature for the known failure mechanism of the component in the library of failure signatures.

3. The method of claim 2, wherein storing the failure signatures in the library of failure mechanisms involves constructing one or more auto-associative memory matrices for the failure signatures.

4. The method of claim 1, wherein the telemetry signal measured from the component under surveillance can have:

low resolution;

or

low-sampling-rate.

5. The method of claim 3, wherein performing the pattern-matching operations between the telemetry signal and the failure signatures in the library involves using an auto-associative memory, which involves:

feeding the anomalous telemetry signal as an input vector into the auto-associative memory; and

allowing the auto-associative memory to restore a matching failure signature for the input vector from the auto-associative memory matrix.

6. The method of claim 5, wherein restoring the matching failure signature facilitates reconstructing a high-resolution, high-sampling-rate failure signature from a low-resolution, low-sampling-rate input telemetry signal.

7. A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for identifying a failure mechanism for a component, the method comprising:

constructing a library of failure signatures from a set of components, wherein each failure signature in the library characterizes a known failure mechanism associated with a component in the set of components;

receiving a telemetry signal which is measured from a component under surveillance;

determining if there is an anomaly in the telemetry signal, and if so;

performing pattern-matching operations between the telemetry signal and failure signatures in the library; and

if a match is found, identifying the failure mechanism for the component under surveillance based on the matching failure signature.

8. The computer-readable storage medium of claim 7, wherein constructing the library of failure signatures involves constructing a failure signature for each known failure mechanism of a component, which involves:

receiving one or more faulty specimens of the component, wherein the one or more faulty specimens are associated with a known failure mechanism;

collecting high-resolution, high-sampling-rate telemetry signals from the one or more faulty specimens, wherein the high-resolution, high-sampling-rate telemetry signals contain the failure signature of the known failure mechanism associated with the component; and

storing the failure signature for the known failure mechanism of the component in the library of failure signatures.

9. The computer-readable storage medium of claim 8, wherein storing the failure signatures in the library of failure mechanisms involves constructing one or more auto-associative memory matrices for the failure signatures.

10. The computer-readable storage medium of claim 7, wherein the telemetry signal measured from the component under surveillance can have:

low resolution;

or

low-sampling-rate.

11. The computer-readable storage medium of claim 10, wherein performing the pattern-matching operations between the telemetry signal and the failure signatures in the library involves using an auto-associative memory, which involves:

feeding the anomalous telemetry signal as an input vector into the auto-associative memory; and

allowing the auto-associative memory to restore a matching failure signature for the input vector from the auto-associative memory matrix.

12. The computer-readable storage medium of claim 11, wherein restoring the matching failure signature facilitates reconstructing a high-resolution, high-sampling-rate failure signature from a low-resolution, low-sampling-rate input telemetry signal.

13. An apparatus that identifies a failure mechanism for a component, comprising:

a construction mechanism configured to construct a library of failure signatures from a set of components, wherein each failure signature in the library characterizes a known failure mechanism associated with a component in the set of components;

a receiving mechanism configured to receive a telemetry signal which is measured from a component under surveillance;

a determination mechanism configured to determine if there is an anomaly in the telemetry signal,

wherein the determination mechanism is further configured to;

perform pattern-matching operations between the telemetry signal and failure signatures in the library; and

if a match is found, to identify a failure mechanism for the component under surveillance based on the matching failure signature.

14. The apparatus of claim 13, wherein the construction mechanism is further configured to construct a failure signature for each known failure mechanism of a component by:

receiving one or more faulty specimens of the component, wherein the one or more faulty specimens are associated with a known failure mechanism;

collecting high-resolution, high-sampling-rate telemetry signals from the one or more faulty specimens, wherein the high-resolution, high-sampling-rate telemetry signals contain the failure signature of the known failure mechanism associated with the component; and

storing the failure signature for the known failure mechanism of the component in the library of failure signatures.

15. The apparatus of claim 14, wherein the construction mechanism is further configured to store the failure signatures in the library of failure mechanisms by constructing one or more auto-associative memory matrices for the failure signatures.

16. The apparatus of claim 13, wherein the telemetry signal measured from the component under surveillance can have:

low resolution;

or

low-sampling-rate.

17. The apparatus of claim 15, wherein the determination mechanism is further configured to perform the pattern-matching operations between the telemetry signal and the failure signatures in the library by using an auto-associative memory, which involves:

feeding the anomalous telemetry signal as an input vector into the auto-associative memory; and

allowing the auto-associative memory to restore a matching failure signature for the input vector from the auto-associative memory matrix.

18. The apparatus of claim 17, wherein restoring the matching failure signature facilitates reconstructing a high-resolution, high-sampling-rate failure signature from a low-resolution, low-sampling-rate input telemetry signal.