Cloud environments and Open Source software lowered the bar for anyone to implement software solutions at scale. However, as software becomes more complex and at scale, the task of monitoring it is becoming increasingly difficult to manage.
Complex relationships between system components are frequently missed by the human eye, and small but important changes are neglected. This, along with the sheer amount of monitoring data, call for a new approach.
In this talk we’ll present how Machine Learning powered log analytics can be used to automatically uncover correlations between system components, recognize ranges for normal behaviors and alert about anomalies.