초록 ▼

A system that detects the onset of degradation for interconnections in a component within a computer system. During operation, the system monitors inferential variables associated with the interconnections during operation of the computer system. Next, the system determines a present state of the co

A system that detects the onset of degradation for interconnections in a component within a computer system. During operation, the system monitors inferential variables associated with the interconnections during operation of the computer system. Next, the system determines a present state of the component from the monitored inferential variables. The system then compares the present state of the component with an initial state of the component. If the comparison indicates that the interconnections in the component have reached or will reach a limited operating state (LOS), the system performs a remedial action.

대표청구항 ▼

What is claimed is: 1. A method for detecting the onset of degradation for interconnections in a component within a computer system, comprising: monitoring inferential variables associated with the interconnections within the computer system during operation of the computer system, wherein the infe

What is claimed is: 1. A method for detecting the onset of degradation for interconnections in a component within a computer system, comprising: monitoring inferential variables associated with the interconnections within the computer system during operation of the computer system, wherein the inferential variables can include one or more of: voltage; current; resistance; capacitance; inductance; a signal-to-noise ratio; a bit-error rate; the number of times an operation in the component is retried; and the size of an eye-diagram opening; determining a present state of the component from the monitored inferential variables; comparing the present state of the component with an initial state of the component; and if the comparison indicates that the interconnections in the component have reached or will reach a limited operating state (LOS), performing a remedial action. 2. The method of claim 1, wherein performing the remedial action involves servicing or replacing the component. 3. The method of claim 1, wherein determining if the interconnections in the component have reached or will reach the LOS involves: determining an operational trend for the state of the component based on data gathered during the monitoring process; and using the operational trend to estimate when the interconnections in the component will reach the LOS. 4. The method of claim 1, wherein prior to monitoring the inferential variables, the method further comprises determining the initial state of component system by: monitoring the inferential variables during an initial period of normal operation; and determining the initial state from the monitored inferential variables. 5. The method of claim 1, wherein the LOS is a state wherein the amount of degradation that has occurred since the initial state makes further operation of the component unacceptable. 6. The method of claim 5, further comprising calculating a remaining life for the component by: calculating an amount of degradation which has occurred in the interconnections in the component since the initial state; and normalizing the amount of degradation to a range between the initial state and the LOS to generate an estimate for the remaining life of the component. 7. The method of claim 5, further comprising calculating a remaining life for the component by using a model of a degradation mechanism for the interconnections. 8. The method of claim 1, wherein a state of an inferential variable can include: a present value of the inferential variable; a mean of the inferential variable; a variance of the inferential variable; a skewness of the inferential variable; a kurtosis of the inferential variable; and a derivative of the inferential variable. 9. A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for detecting the onset of degradation for interconnections in a component within a computer system, wherein the method comprises: monitoring inferential variables associated with the interconnections within the computer system during operation of the computer system, wherein the inferential variables can include one or more of: voltage; current; resistance; capacitance; inductance; a signal-to-noise ratio; a bit-error rate; the number of times an operation in the component is retried; and the size of an eve-diagram opening; determining a present state of the component from the monitored inferential variables; comparing the present state of the component with an initial state of the component; and if the comparison indicates that the interconnections in the component have reached or will reach a limited operating state (LOS), performing a remedial action. 10. The computer-readable storage medium of claim 9, wherein performing the remedial action involves servicing or replacing the component. 11. The computer-readable storage medium of claim 9, wherein determining if the interconnections in the component have reached or will reach the LOS involves: determining an operational trend for the state of the component based on data gathered during the monitoring process; and using the operational trend to estimate when the interconnections in the component will reach the LOS. 12. The computer-readable storage medium of claim 9, wherein prior to monitoring the inferential variables, the method further comprises determining the initial state of the component by: monitoring the inferential variables during an initial period of normal operation; and determining the initial state from the monitored inferential variables. 13. The computer-readable storage medium of claim 9, wherein the LOS is a state wherein the amount of degradation that has occurred since the initial state makes further operation of the component unacceptable. 14. The computer-readable storage medium of claim 13, wherein the method further comprises calculating a remaining life for the component by: calculating an amount of degradation which has occurred in the interconnections in the component since the initial state; and normalizing the amount of degradation to a range between the initial state and the LOS to generate an estimate for the remaining life of the component. 15. The computer-readable storage medium of claim 13, wherein the method further comprises calculating a remaining life for the component by using a model of a degradation mechanism for the interconnections. 16. The computer-readable storage medium of claim 9, wherein a state of an inferential variable can include: a present value of the inferential variable; a mean of the inferential variable; a variance of the inferential variable; a skewness of the inferential variable; a kurtosis of the inferential variable; and a derivative of the inferential variable. 17. An apparatus that detects the onset of degradation for interconnections in a component within a computer system, comprising: a monitoring mechanism configured to monitor inferential variables associated with the interconnections within the computer system during operation of the computer system, wherein the inferential variables can include one or more of: voltage; current; resistance; capacitance; inductance; a signal-to-noise ratio; a bit-error rate; the number of times an operation in the component is retried; and the size of an eve-diagram opening; a degradation-detection mechanism configured to: determine a present state of the component from the monitored inferential variables; compare the present state of the component with an initial state of the component; and if the comparison indicates that the interconnections in the component have reached or will reach a limited operating state (LOS), to perform a remedial action. 18. The apparatus of claim 17, further comprising a service mechanism wherein while performing the remedial action, the service mechanism is configured to service or to replace the component.