Flowmill is a network observability solution purpose-built for the world of distributed applications. By automatically tracing every connection between hosts, containers, and processes, Flowmill helps SRE teams discover every service dependency, identify when and how network and infrastructure problems impact services, and collect rate, error, and duration metrics between every pair of services.
Flowmill was designed to be deployed fleet wide in minutes with no changes to the application code, runtime, or container images. It requires no developer instrumentation or manual per-service configuration. Flowmill consists of an extremely high performance agent on each host (VM / bare metal) that sends a detailed summary of communication collected directly from the operating system to the cloudbased Flowmill service. The agent leverages eBPF, an interface exposed by the Linux kernel, to automatically instrument the network stack and collect real-time data on every socket, along with associated process and container metadata. This targeted approach allows the Flowmill agent to operate with negligible overhead, typically 0.25% / CPU core.