Imagine this: You are an engineer at a startup. You are responsible for keeping all the applications running smoothly and safely in production. At first, you have things under control, but soon enough things start getting more complex.

Today we are excited to launch one of our flagship ML assisted troubleshooting features in Netdata – the Anomaly Advisor. The Anomaly Advisor builds on earlier work to introduce unsupervised anomaly detection capabilities into the Netdata Agent from v1.32.0 onwards.

In the Kubernetes (K8s) community, there is a huge misconception about CPU allocation and utilization. Even highly experienced SREs find themselves struggling with the way Kubernetes allocates CPU resources, leading to misconfigured CPU allocations and extremely negative outcomes. For starters, this results in significant quality degradation on important service components, introduced by behind-the-scenes CPU limiting (or throttling).

At Netdata, we love two things more than anything else: Our goal is to make troubleshooting and monitoring as seamless as possible with the open-source Agent. This includes giving you pre-configured alerts so that you get notified immediately when a disruption occurs. The Netdata Agent comes with over 250 pre-configured and optimized alerts.

Our Analytics & ML lead Andrew Maguire recently had a chance to share our new Anomaly Advisor feature with the wider CNCF community. In his demonstration he did some light chaos engineering (using Gremlin and stress-ng) to generate some real anomalies on his infrastructure and watch how it all played out in the Anomaly Advisor in Netdata Cloud. There were also some great questions and discussion from the audience around ML in general and in the observability space itself.