Method and apparatus to identify a problem area in an information handling system based on latencies
An information handling system may obtain timing information for processing among layers of a first client-side information handling system, and compare the timing information to threshold values to provide a comparison. The information handling system may use the comparison to identify an area of the first client-side information handling system in which a problem exists, and initiate remedial action directed to the problem.
1. A method comprising:
measuring timing information for processing among layers of a first client-side information handling system (IHS), wherein the timing information includes a first time period representing a first latency of a first request from a software application to an operating system (OS) and a second time period representing a second latency of a second request from the OS to a hardware component;
comparing the timing information to threshold values to provide a comparison;
in response to determining that there are differences between the timing information and the threshold values, using the comparison to identify an area of the first client-side IHS in which a problem exists, wherein the identification of the area of the first client-side IHS in which the problem exists includes calculating a first probability that the problem exists in the OS and a second probability that the problem exists in the hardware component, wherein the first probability is calculated based on the first time period and the second probability is calculated based on the second time period;
dispatching of the problem to a problem resolution entity; and
initiating, by the problem resolution entity, remedial action directed to the problem in the area of the first client-side IHS, wherein the problem exists in the area with a higher probability between the first probability and the second probability.
2. The method of claim 1 , wherein the area is selected from a group consisting of the software application, the (OS), and the hardware component of the first client-side IHS.
3. The method of claim 2 , wherein the first probability is calculated based on a difference between the first time period and a first threshold value, and wherein the difference is divided by the first threshold value.
4. The method of claim 2 , wherein the timing information comprises a third time period representing a latency of a first response from the hardware component to the OS and a fourth time period representing another latency of a second response from the OS to the software application.
5. The method of claim 1 , wherein the threshold values are generic default threshold values generated from processing of the timing information obtained from a plurality of client-side IHSs.
6. The method of claim 1 , wherein the threshold values are user-specific threshold values generated by modifying generic default threshold values generated from processing of the timing information obtained from a plurality of client-side IHSs, wherein the modifying comprises adjusting the generic default threshold values based on specific information of the first client-side IHS.
7. The method of claim 1 , wherein the initiating of the remedial action directed to the problem in the area of the first client-side IHS is performed using machine learning (ML).
8. An information handling system (IHS) comprising:
a memory; and
a processor in communication with the memory, the processor configured to obtain timing information for processing among layers of a first client-side information handling system (IHS), wherein the timing information includes a first time period representing a first latency of a first request from a software application to an operating system (OS) and a second time period representing a second latency of a second request from the OS to a hardware component, to compare the timing information to threshold values to provide a comparison, in response to determining that there are differences between the timing information and the threshold values, to use the comparison to identify an area of the first client-side IHS in which a problem exists, wherein the identification of the area of the first client-side IHS in which the problem exists includes calculating a first probability that the problem exists in the OS and a second probability that the problem exists in the hardware component, wherein the first probability is calculated based on the first time period and the second probability is calculated based on the second time period, to dispatch the problem to a problem resolution entity; and to initiate remedial action, by the problem resolution entity, directed to the problem in the area of the first client-side IHS, wherein the problem exists in the area with a higher probability between the first probability and the second probability.
9. The IHS of claim 8 , wherein the area is selected among the layers of the first client-side IHS consisting of the software application, the (OS), and the hardware component of the first client-side IHS.
10. The IHS of claim 9 , wherein the first probability is calculated based on a difference between the first time period and a first threshold value, and wherein the difference is divided by the first threshold value.
11. The IHS of claim 9 , wherein the timing information comprises a third time period representing a latency of a first response from the hardware component to the OS and a fourth time period representing another latency of a second response from the OS to the software application.
12. The IHS of claim 8 , wherein the threshold values are generic default threshold values generated from processing of the timing information obtained from a plurality of client-side IHSs.
13. The IHS of claim 8 , wherein the threshold values are user-specific threshold values generated by modifying generic default threshold values generated from processing of the timing information obtained from a plurality of client-side IHSs, wherein the modifying comprises adjusting the generic default threshold values based on specific information of the first client-side IHS.
14. The IHS of claim 8 , wherein the initiating of the remedial action directed to the problem in the area of the first client-side IHS is performed using machine learning (ML).
15. A method comprising:
obtaining timing information for processing among layers of a first client-side information handling system (IHS), the timing information including at least two of a first time period representing a first latency of a first request from a software application of the first client-side IHS to an operating system (OS) of the first client-side IHS, a second time period representing a second latency of a second request from the OS to a hardware component of the first client-side IHS, a third time period representing a third latency of a first response from the hardware component to the OS, and a fourth time period representing a fourth latency of a second response from the OS to the software application;
comparing the timing information to threshold values to provide a comparison;
in response to determining that there are differences between the timing information and the threshold values, using the comparison to identify an area in which a problem exists in the first client-side IHS, wherein the identification of the area of the first client-side IHS in which the problem exists includes calculating a first probability that the problem exists in the OS and a second probability that the problem exists in the hardware component, wherein the first probability is calculated based on the first time period and the second probability is calculated based on the second time period;
dispatching of the problem to a problem resolution entity; and
initiating, by the problem resolution entity, remedial action directed to the problem in the area of the first client-side IHS, wherein the problem exists in the area with a higher probability between the first probability and the second probability.
16. The method of claim 15 , wherein the area is selected from a group consisting of the software application, the OS, and the hardware component of the first client-side IHS.
17. The method of claim 15 , wherein the threshold values are generic default threshold values generated from processing of the timing information obtained from a plurality of first client-side IHSs.
18. The method of claim 15 , wherein the threshold values are user-specific threshold values generated by modifying generic default threshold values generated from processing of the timing information obtained from a plurality of client-side IHSs, wherein the modifying comprises adjusting the generic default threshold values based on specific information of the first client-side IHS.
19. The method of claim 15 , wherein the initiating of the remedial action directed to the problem in the area of the first client-side IHS is performed using machine learning (ML).
20. The method of claim 17 , wherein the generic default threshold values are downloaded to the first client-side IHS.