DevConf.US 2022

In this era of automation and streamlining systems by removing human involvement, GitHub makes it easy to automate all your software development workflows, now with world-class CI/CD. Build, test, and deploy your code right from GitHub. However, every new Pull Request to a repository with new code changes is subjected to an automated set of builds and tests before being merged. Some tests may run for longer durations than expected. Longer running tests are often painful as they can block the CI/CD process for lengthy periods of time. How can we optimize the running time of our tests and prevent bottlenecks in our CI/CD pipeline? By understanding the test failure times from historical data, we aim to predict an Optimal Stopping Point for a test/build to help developers and managers better allocate the development resources, and ensure efficiency, consistency, and transparency for manual and time-consuming processes. With the help of machine learning and statistical models, we can predict the optimal stopping point for a given test and build. In this talk, we will demonstrate how you can leverage Operate First, an open source cloud platform consisting of various tools to collect open CI/CD data from various sources such as GitHub, Prow, TestGrid, etc, analyze it, and visualize key performance indicator metrics on a Superset dashboard to gain greater insights into your software development process. We will use Jupyter notebooks to train an ML model for predicting the optimal stopping point for tests. Finally, we will see how to package our prediction pipeline and deploy it as a service using Seldon Core on OpenShift.