Skip to main content

Network health on the service map: per-edge RTT and connection failures

avuru obs team
Maintainers

The service map now shows connection-level health on its edges: per-edge TCP RTT and failed/reset connections, measured in the kernel by OBI — no traces, no SDKs, no app changes. A link that's slow or refusing connections is now visible on the same topology you already watch.

  • On the edge. Hover an edge for its call volume plus RTT p95 and failed connections; an edge turns amber (dashed) when RTT is high or connections are failing, with trace-error red taking precedence.
  • From OBI's TCP stats. Sourced from obi.stat.tcp.rtt and obi.stat.tcp.failed.connections, keyed to the same service endpoints as the network-flow edges. Enable with the sensor's OBI network feature (requires the infra-metrics module).
  • No new storage. RTT (a histogram) and failures (a counter) land in the existing metric tables and are read at query time — no migration.
  • Scope note. OBI does not emit TCP retransmissions, so those are not shown.