infra/deploy/forgejo/docker-stack.yml

@@ -53,7 +53,19 @@ services:
           cpus: "${FORGEJO_DB_CPUS:-1}"
           memory: ${FORGEJO_DB_MEMORY:-1g}
       restart_policy:
-        condition: on-failure
+        # `any`, NOT `on-failure`. This took Forgejo down for 27 hours on 2026-07-29:
+        # Postgres hit an invalid data-directory lock file ("could not open file
+        # postmaster.pid ... performing immediate shutdown") and exited **0**. A clean
+        # exit is not a failure, so Swarm considered the task Complete, dropped the
+        # service to 0/1 replicas, and never rescheduled it. Forgejo itself stayed Up
+        # and served its homepage while every repo page, the API and all CI returned
+        # 500 with `dial tcp: lookup db ... no such host`.
+        #
+        # `on-failure` is the wrong policy for any always-on stateful service: it
+        # cannot distinguish "finished successfully" from "shut itself down and should
+        # be restarted", and Postgres does the latter with status 0 on several paths.
+        condition: any
+        delay: 5s
 
   forgejo:
     image: codeberg.org/forgejo/forgejo:9-rootless