System and method for predictive failure detection
First Claim
Patent Images
1. A method of predicting failure of an information handling system, comprising:
- determining an error period;
determining that an error has occurred;
incrementing an error count;
if the error is the first error of the error count, waiting until a next error;
if the error is not the first error of the error count, such that there is a previous error determining a time difference between the error and the previous error;
if the time difference is less than the error period, generating data representing a predicted failure;
if the time difference is greater than the error period, calculating the product of the error period and the error count;
if the time difference is greater than the product of the error period and the error count, clearing the error count;
if the time difference is less than the product of the error period and the error count, decrementing the error count by a leak value representing the time difference divided by the error period; and
repeating the above steps for each new error.
14 Assignments
0 Petitions
Accused Products
Abstract
A method of predicting failure of an information handling device, such as a server, by monitoring an error rate, i.e., n errors per error period. Errors are reported only if the error rate is exceeded. An error count is kept, and errors are leaked from the count if the time difference between errors is more than the error period.
-
Citations
16 Claims
-
1. A method of predicting failure of an information handling system, comprising:
-
determining an error period; determining that an error has occurred; incrementing an error count; if the error is the first error of the error count, waiting until a next error; if the error is not the first error of the error count, such that there is a previous error determining a time difference between the error and the previous error; if the time difference is less than the error period, generating data representing a predicted failure; if the time difference is greater than the error period, calculating the product of the error period and the error count; if the time difference is greater than the product of the error period and the error count, clearing the error count; if the time difference is less than the product of the error period and the error count, decrementing the error count by a leak value representing the time difference divided by the error period; and repeating the above steps for each new error. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A computer-readable medium having computer-executable instructions that when executed predict failure of an information handling system, comprising:
- instructions that when executed perform the following operations;
determining an error period; determining that an error has occurred; incrementing an error count; if the error is the first error of the error count, waiting until a next error; if the error is not the first error of the error count, such that there is a previous error, determining a time difference between the error and the previous error; if the time difference is less than the error period, generating data representing a predicted failure; if the time difference is greater than the error period, determining calculating the product of the error period and the error count; if the time difference is greater than the product of the error period and the error count, clearing the error count; if the time difference is less than the product of the error period and the error count, decrementing the error count by a leak value representing the time difference divided by the error period; and repeating the above steps for each new error. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
- instructions that when executed perform the following operations;
Specification