[client] Fix flaky TestServiceLifecycle/Restart on FreeBSD (#5786)

client/cmd/service_test.go

@@ -4,7 +4,9 @@ import (
 	"context"
 	"fmt"
 	"os"
+	"os/signal"
 	"runtime"
+	"syscall"
 	"testing"
 	"time"
 
@@ -13,6 +15,22 @@ import (
 	"github.com/stretchr/testify/require"
 )
 
+// TestMain intercepts when this test binary is run as a daemon subprocess.
+// On FreeBSD, the rc.d service script runs the binary via daemon(8) -r with
+// "service run ..." arguments. Since the test binary can't handle cobra CLI
+// args, it exits immediately, causing daemon -r to respawn rapidly until
+// hitting the rate limit and exiting. This makes service restart unreliable.
+// Blocking here keeps the subprocess alive until the init system sends SIGTERM.
+func TestMain(m *testing.M) {
+	if len(os.Args) > 2 && os.Args[1] == "service" && os.Args[2] == "run" {
+		sig := make(chan os.Signal, 1)
+		signal.Notify(sig, syscall.SIGTERM, os.Interrupt)
+		<-sig
+		return
+	}
+	os.Exit(m.Run())
+}
+
 const (
 	serviceStartTimeout = 10 * time.Second
 	serviceStopTimeout  = 5 * time.Second
@@ -79,6 +97,34 @@ func TestServiceLifecycle(t *testing.T) {
 	logLevel = "info"
 	daemonAddr = fmt.Sprintf("unix://%s/netbird-test.sock", tempDir)
 
+	// Ensure cleanup even if a subtest fails and Stop/Uninstall subtests don't run.
+	t.Cleanup(func() {
+		cfg, err := newSVCConfig()
+		if err != nil {
+			t.Errorf("cleanup: create service config: %v", err)
+			return
+		}
+		ctxSvc, cancel := context.WithCancel(context.Background())
+		defer cancel()
+		s, err := newSVC(newProgram(ctxSvc, cancel), cfg)
+		if err != nil {
+			t.Errorf("cleanup: create service: %v", err)
+			return
+		}
+
+		// If the subtests already cleaned up, there's nothing to do.
+		if _, err := s.Status(); err != nil {
+			return
+		}
+
+		if err := s.Stop(); err != nil {
+			t.Errorf("cleanup: stop service: %v", err)
+		}
+		if err := s.Uninstall(); err != nil {
+			t.Errorf("cleanup: uninstall service: %v", err)
+		}
+	})
+
 	ctx := context.Background()
 
 	t.Run("Install", func(t *testing.T) {

infrastructure_files/getting-started.sh

@@ -532,14 +532,13 @@ render_docker_compose_traefik_builtin() {
     traefik_dynamic_volume="      - ./traefik-dynamic.yaml:/etc/traefik/dynamic.yaml:ro"
     proxy_service="
   # NetBird Proxy - exposes internal resources to the internet
-  # Uses host network so it can listen on arbitrary ports for TCP/UDP services
   proxy:
     image: $NETBIRD_PROXY_IMAGE
     container_name: netbird-proxy
     ports:
     - 51820:51820/udp
     restart: unless-stopped
-    network_mode: host
+    networks: [netbird]
     depends_on:
       - netbird-server
     env_file:
@@ -647,7 +646,6 @@ $traefik_dynamic_volume
     networks: [netbird]
     ports:
       - '$NETBIRD_STUN_PORT:$NETBIRD_STUN_PORT/udp'
-$(if [[ "$ENABLE_PROXY" == "true" ]]; then echo "      - '$MANAGEMENT_HOST_PORT:80'"; fi)
     volumes:
       - netbird_data:/var/lib/netbird
       - ./config.yaml:/etc/netbird/config.yaml
@@ -768,8 +766,8 @@ render_proxy_env() {
   cat <<EOF
 # NetBird Proxy Configuration
 NB_PROXY_DEBUG_LOGS=false
-# Proxy runs in host network mode for L4 port binding, connect to management via localhost
-NB_PROXY_MANAGEMENT_ADDRESS=http://localhost:$MANAGEMENT_HOST_PORT
+# Use internal Docker network to connect to management (avoids hairpin NAT issues)
+NB_PROXY_MANAGEMENT_ADDRESS=http://netbird-server:80
 # Allow insecure gRPC connection to management (required for internal Docker network)
 NB_PROXY_ALLOW_INSECURE=true
 # Public URL where this proxy is reachable (used for cluster registration)