Granted Patent B2

US 12,517,773 · App. 18/473,410 · Granted Jan 6, 2026

Inventors: Bijan Kumar Mohanty (Austin, TX); Rajiv Popat (Kolkata, IN); Hung Dinh (Austin, TX)

Assignee: Dell Products L.P.

G06F11/006G06F11/0709G06F11/0787G06F2201/86

Abstract

Claims (56)

1 . A method comprising:

analyzing, using one or more machine learning algorithms, parameters corresponding to at least one microservice operation processed by a first instance of a microservice, wherein operation of the first instance of the microservice is logged at a first level of granularity;

predicting, based at least in part on the analyzing, whether the at least one microservice operation is anomalous;

designating the first instance of the microservice as being in an anomalous state responsive to predicting that the at least one microservice operation is anomalous;

routing one or more requests for the microservice to a second instance of the microservice responsive to the anomalous state designation;

causing logging of information corresponding to operation of the second instance of the microservice to be enabled at a higher second level of granularity; and

verifying the anomalous state designation of the first instance of the microservice, wherein the verifying comprises:

routing at least one request for the microservice to the first instance of the microservice instead of the second instance of the microservice;

collecting additional parameters corresponding to processing by the first instance of the microservice of a microservice operation associated with the at least one request;

analyzing the additional parameters using the one or more machine learning algorithms; and

predicting, based at least in part on the analyzing, whether the microservice operation associated with the at least one request is anomalous;

wherein the steps of the method are executed by a processing device operatively coupled to a memory.

2 . The method of claim 1 further comprising creating the second instance of the microservice in a container with code to enable the logging of the information corresponding to the operation of the second instance of the microservice at the higher second level of granularity.

3 . The method of claim 1 wherein the higher second level of granularity comprises at least one of a trace logging level, a debug logging level and an info logging level.

4 . The method of claim 1 further comprising determining whether a threshold number of microservice operations of a plurality of microservice operations processed by the first instance of the microservice have been predicted as anomalous before designating the first instance of the microservice as being in an anomalous state.

5 . The method of claim 4 wherein the threshold number of microservice operations comprises a consecutive number of microservice operations processed by the first instance of the microservice.

6 . The method of claim 1 wherein the parameters comprise at least one of a microservice identifier, a request time of the at least one microservice operation, a response time of the at least one microservice operation, latency of the at least one microservice operation and a number of errors associated with the at least one microservice operation.

7 . The method of claim 6 wherein the errors associated with the at least one microservice operation comprise non-retriable errors.

8 . The method of claim 1 wherein the first instance of the microservice is hosted in a first container and the second instance of the microservice is hosted in a second container.

9 . The method of claim 8 wherein the first container is a component of a first host device and the second container is a component of a second host device.

10 . The method of claim 8 further comprising creating the second instance of the microservice in the second container with code to enable the logging of the information corresponding to the operation of the second instance of the microservice at the higher second level of granularity.

11 . The method of claim 1 wherein the one or more machine learning algorithms utilize an unsupervised learning technique to detect one or more outlier parameters of the parameters.

12 . The method of claim 1 wherein the one or more machine learning algorithms are trained with training data comprising historical parameter data.

13 . The method of claim 1 further comprising:

maintaining the anomalous state designation of the first instance of the microservice responsive to predicting that the microservice operation associated with the at least one request is anomalous; and

changing the anomalous state designation of the first instance of the microservice to a normal state designation responsive to predicting that the microservice operation associated with the at least one request is not anomalous.

14 . The method of claim 13 further comprising routing subsequent requests for the microservice to the first instance of the microservice responsive to the normal state designation.

15 . An apparatus comprising:

a processing device operatively coupled to a memory and configured:

to analyze, using one or more machine learning algorithms, parameters corresponding to at least one microservice operation processed by a first instance of a microservice, wherein operation of the first instance of the microservice is logged at a first level of granularity;

to predict, based at least in part on the analyzing, whether the at least one microservice operation is anomalous;

to designate the first instance of the microservice as being in an anomalous state responsive to predicting that the at least one microservice operation is anomalous;

to route one or more requests for the microservice to a second instance of the microservice responsive to the anomalous state designation;

to cause logging of information corresponding to operation of the second instance of the microservice to be enabled at a higher second level of granularity; and

to verify the anomalous state designation of the first instance of the microservice, wherein the verifying comprises:

routing at least one request for the microservice to the first instance of the microservice instead of the second instance of the microservice;

collecting additional parameters corresponding to processing by the first instance of the microservice of a microservice operation associated with the at least one request;

analyzing the additional parameters using the one or more machine learning algorithms; and

predicting, based at least in part on the analyzing, whether the microservice operation associated with the at least one request is anomalous.

16 . The apparatus of claim 15 wherein the processing device is further configured to create the second instance of the microservice in a container with code to enable the logging of the information corresponding to the operation of the second instance of the microservice at the higher second level of granularity.

17 . The apparatus of claim 15 wherein the higher second level of granularity comprises at least one of a trace logging level, a debug logging level and an info logging level.

18 . The apparatus of claim 15 , wherein the processing device is further configured to:

maintain the anomalous state designation of the first instance of the microservice responsive to predicting that the microservice operation associated with the at least one request is anomalous; and

change the anomalous state designation of the first instance of the microservice to a normal state designation responsive to predicting that the microservice operation associated with the at least one request is not anomalous.

19 . An article of manufacture comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes said at least one processing device to perform the steps of:

analyzing, using one or more machine learning algorithms, parameters corresponding to at least one microservice operation processed by a first instance of a microservice, wherein operation of the first instance of the microservice is logged at a first level of granularity;

predicting, based at least in part on the analyzing, whether the at least one microservice operation is anomalous;

designating the first instance of the microservice as being in an anomalous state responsive to predicting that the at least one microservice operation is anomalous;

routing one or more requests for the microservice to a second instance of the microservice responsive to the anomalous state designation;

causing logging of information corresponding to operation of the second instance of the microservice to be enabled at a higher second level of granularity; and

verifying the anomalous state designation of the first instance of the microservice, wherein the verifying comprises:

routing at least one request for the microservice to the first instance of the microservice instead of the second instance of the microservice;

collecting additional parameters corresponding to processing by the first instance of the microservice of a microservice operation associated with the at least one request;

analyzing the additional parameters using the one or more machine learning algorithms; and

predicting, based at least in part on the analyzing, whether the microservice operation associated with the at least one request is anomalous.

20 . The article of manufacture of claim 19 wherein the program code further causes said at least one processing device to perform the step of creating the second instance of the microservice in a container with code to enable the logging of the information corresponding to the operation of the second instance of the microservice at the higher second level of granularity.

Assignments (1)

Continuity (1)

References Cited (15)