Health Checks eingebaut

Python/Cron

@@ -0,0 +1 @@
+@reboot sleep 30 && /usr/bin/python3 /home/christof/lcd/test3.py >> /var/log/start_after_boot.log 2>&1

Python/LCD

@@ -0,0 +1,60 @@
+import subprocess
+import time
+import sys
+
+CONTAINERS = ["telegraf", "influx-influxdb-1", "grafana", "mqtt5"]  # <- Container-Namen anpassen
+TIMEOUT_S = 300
+SLEEP_S = 2
+
+def sh(cmd: list[str]) -> str:
+    return subprocess.check_output(cmd, text=True).strip()
+
+def is_running(name: str) -> bool:
+    try:
+        state = sh(["docker", "inspect", "-f", "{{.State.Running}}", name])
+        return state.lower() == "true"
+    except Exception:
+        return False
+
+def health(name: str) -> str:
+    # returns: healthy, unhealthy, starting, or "none" if no healthcheck
+    try:
+        return sh(["docker", "inspect", "-f", "{{.State.Health.Status}}", name])
+    except Exception:
+        return "none"
+
+def main():
+    deadline = time.time() + TIMEOUT_S
+    while time.time() < deadline:
+        ok = True
+        for c in CONTAINERS:
+            if not is_running(c):
+                ok = False
+                "break"
+            h = health(c)
+            print(h)
+            if h == "none":
+                # Falls ein Container keinen Healthcheck hat:
+                # -> kannst du hier alternativ eine Portprüfung machen oder es als "ok" behandeln.
+                ok = False
+                break
+            if h != "healthy":
+                ok = False
+                break
+
+        if ok:
+            print("Alle Container sind running + healthy.")
+
+            subprocess.run(
+                ["python3", "test.py"],
+                check=True
+            )
+            return 0
+
+        time.sleep(SLEEP_S)
+
+    print("Timeout: Container nicht rechtzeitig healthy.", file=sys.stderr)
+    return 1
+
+if __name__ == "__main__":
+    raise SystemExit(main())

Python/README-md

@@ -0,0 +1,3 @@
+python3 -m pip config set global.break-system-packages true
+
+sudo pip3 install adafruit-blinka

mqtt/docker-compose.yml

@@ -4,10 +4,8 @@ services:
     image: eclipse-mosquitto
     container_name: mqtt5
     healthcheck:
-      test: [ "CMD-SHELL", "mosquitto_sub -h localhost -p 1883 -t '$SYS/#' -C 1 -W 2 >/dev/null 2>&1 || exit 1" ]
+      test: [ "CMD-SHELL", "mosquitto_pub -h localhost -p 1883 -u 'mqtt_user' -P 'mqtt_pw' -t 'healthcheck/ping' -n -q 0 >/dev/null 2>&1 || exit 1" ]
-      interval: 10s
+
-      timeout: 5s
-      retries: 12
     ports:
       - "1883:1883" #default mqtt port
       - "9001:9001" #default mqtt port for websockets

telegraf/docker-compose.yml

@@ -4,7 +4,7 @@ services:
     container_name: telegraf
     restart: unless-stopped
     healthcheck:
-      test: [ "CMD", "curl", "-f", "http://localhost:8094" ]
+      test: [ "CMD-SHELL", "pidof telegraf >/dev/null 2>&1 || exit 1" ]
       interval: 10s
       timeout: 3s
       retries: 12