Anomaly Detection in DevOps Toolchain

Anomaly Detection in DevOps Toolchain

연구 분야: Software Development

학회: International Workshop on Software Engineering Aspects of Continuous Development and New Paradigms of Software Production and Deployment

The tools employed in the DevOps Toolchain generates a large quantity of data that is typically ignored or inspected only on particular occasions, at most. However, the analysis of such data could enable the extraction of useful information about the status and evolution of the project. For example, metrics like the “lines of code added since the last release” or “failures detected in the staging environment” are good indicators for predicting potential risks in the incoming release. In order to prevent problems appearing in later stages of production, an anomaly detection system can operate in the staging environment to compare the current incoming release with previous ones according to predefined metrics. The analysis is conducted before going into production to identify anomalies which should be addressed by human operators that address false-positive and negatives that can appear. In this paper, we describe a prototypical implementation of the aforementioned idea in the form of a “proof of concept”. The current study effectively demonstrates the feasibility of the approach for a set of implemented functionalities.