mirror of
https://github.com/jmcorgan/fips.git
synced 2026-10-05 19:18:25 +00:00
The resolver ran as a detached task whose error was only logged, so a gateway whose DNS port was taken stayed up with .fips resolution dead and every health check passing. The listener is now bound before the address pool, NAT table and routes are created, and a bind failure exits with status 1. When the port is already in use, the error names the service most likely to hold it and how to find the holder with ss or netstat. A resolver task that stops while the gateway runs also ends the process, after NAT and routes are torn down, so systemd or procd restarts it or shows it failed. The resolver now forwards to the upstream address the startup probe resolved, so an upstream written as a hostname no longer passes the probe and then kills the resolver. The dns-resolver harness gains a check that a gateway configured on the daemon's DNS port exits with the hint before it creates the pool or the NAT table. The troubleshooting guide describes the new failure, and the exit-code table no longer lists a control-socket bind failure, which only warns.