Peeking Under the Hood: Observability of Kubernetes gRPC Internals - A. Chaudhuri & S. Agrawalla

Don't miss out! Join us at our next Flagship Conference: KubeCon + CloudNativeCon events in Amsterdam, The Netherlands (23-26 March, 2026). Connect with our current graduated, incubating, and sandbox projects as the community gathers to further the education and advancement of cloud native computing. Learn more at https://kubecon.io

Peeking Under the Hood: Observability of Kubernetes gRPC Internals - Abhijeet Chaudhuri & Sanskar Agrawalla, Quartic.ai

Kubernetes hides a lot of its magic behind internal gRPC calls—from the kubelet talking to the container runtime (CRI) to pulling images, creating pods, or mounting volumes. But when something fails at this layer, engineers are often left guessing, with logs that only tell half the story.

In this talk, we’ll open up this “black box” by showing how we instrumented and traced these internal gRPC calls without modifying Kubernetes code. Using a mix of eBPF, OpenTelemetry, and gRPC interceptors, we built fine-grained visibility into kubelet → containerd communication. This let us trace failures in image pulls, container start latency, and volume mounts at the gRPC level—right where the kubelet and CRI talk.

The audience will walk away with a practical blueprint for bringing distributed tracing into Kubernetes’ own internals, closing one of the last gaps in observability. If you’ve ever debugged mysterious pod startup delays or node-level runtime issues, this talk is for you.

Видео Peeking Under the Hood: Observability of Kubernetes gRPC Internals - A. Chaudhuri & S. Agrawalla канала CNCF [Cloud Native Computing Foundation]