Dynamic pod priority inference utilizing service mesh telemetry data

Abstract

Dynamically calculating and re-calculating priority values for a set of microservices that are deployed and run in a containerized environment. Before new priority values are assigned to the microservices, an initial default priority value is assigned to a microservice of interest. When the microservice of interest is deployed and run in the containerized environment, the generated telemetry data is used, in part, as a basis to determine a frequency in which any given microservice is being utilized, and more particularly, the microservice of interest. Based upon the determined frequency, a role for the microservice of interest can be inferred. As a result, this inferred role for the microservice of interest is used to dynamically assign a current priority value for the microservice of interest.