Kubernetes monitoring cluster map widens workload observability  

Based in Tel Aviv, groundcover is a start-up focused on the cloud-native application monitoring domain with eBPF.

Built as an extension to BPF (Berkeley Packet Filter), a technology used in certain computer operating systems for programs that need to, among other things, analyze network traffic, eBPF (the e denoting extended) is a technology that can run sandboxed programs in a privileged context such as the operating system kernel.

In other words, groundcover is a Kubernetes (K8s) application monitoring solution that aims to reinvent the domain with eBPF. 

Built for modern production environments, it covers everything yet stores only what matters, allowing teams to scale away without worries. 

The groundcover team has now launched Caretta: an open source software (OSS) tool which helps teams create a visual network map of the services running in their cluster. 

Caretta uses eBPF technology to collect data in an efficient way and is equipped with a Grafana Node Graph dashboard to display the dynamic map of the cluster.

Workload inter-dependencies 

The main idea behind creating Caretta is gaining a clear understanding of the inter-dependencies between the different workloads running in the cluster, which is an otherwise very complicated task.

“Caretta maps all service interactions and their traffic rates, leveraging Kubernetes APIs to create a clean and informative map of any K8s cluster which can be used for on-demand granular observability, cost optimisation and security insights, allowing teams to quickly reach impactful insights such as identifying central points of failure or pinpointing security anomalies,” notes the company, in a product statement.

Caretta is part of the mission of cloud-environment observability tools – the team insist that no APM product is complete without network tracing capabilities and the aggregated data from these traces can help answer many critical questions. Carreta does that and fits those cases where developers want a minimal, fast and ad-hoc solution.

Image credit: groundwork

Data Center
Data Management