Heartbeat und Überwachung eingeführt
This commit is contained in:
22
.env.example
Normal file
22
.env.example
Normal file
@@ -0,0 +1,22 @@
|
||||
# E-Mail Empfang (IMAP) - für Videos von der Kamera
|
||||
IMAP_SERVER=secureimap.t-online.de
|
||||
IMAP_PORT=993
|
||||
EMAIL_USER=deine-email@t-online.de
|
||||
EMAIL_PASS=dein-passwort
|
||||
|
||||
# Speicherort für Videos
|
||||
SAVE_DIR=/app/videospeicher
|
||||
|
||||
# E-Mail Versand (SMTP) - für Monitoring-Benachrichtigungen
|
||||
SMTP_SERVER=securesmtp.t-online.de
|
||||
SMTP_PORT=587
|
||||
SMTP_USER=deine-email@t-online.de
|
||||
SMTP_PASS=dein-passwort
|
||||
|
||||
# Alert-E-Mail (an wen sollen Benachrichtigungen gehen?)
|
||||
ALERT_EMAIL=deine-email@t-online.de
|
||||
|
||||
# Monitoring-Einstellungen (optional)
|
||||
# CHECK_INTERVAL=600 # Monitoring-Prüfung alle 10 Minuten
|
||||
# MAX_AGE=900 # Alarm wenn kein Heartbeat seit 15 Minuten
|
||||
# ALERT_COOLDOWN=3600 # Mindestens 1 Stunde zwischen Alarm-E-Mails
|
||||
@@ -10,6 +10,7 @@ RUN pip install --no-cache-dir -r requirements.txt
|
||||
|
||||
# Kopiere den Anwendungscode
|
||||
COPY main.py .
|
||||
COPY monitor.py .
|
||||
|
||||
# Erstelle Verzeichnis für Videospeicher
|
||||
RUN mkdir -p /app/videospeicher
|
||||
|
||||
@@ -5,6 +5,7 @@ services:
|
||||
restart: unless-stopped
|
||||
volumes:
|
||||
- ./videospeicher:/app/videospeicher
|
||||
- heartbeat:/app
|
||||
env_file:
|
||||
- .env
|
||||
environment:
|
||||
@@ -14,8 +15,32 @@ services:
|
||||
- EMAIL_USER=${EMAIL_USER}
|
||||
- EMAIL_PASS=${EMAIL_PASS}
|
||||
- SAVE_DIR=${SAVE_DIR}
|
||||
- HEARTBEAT_FILE=/app/heartbeat.txt
|
||||
# Führe das Skript alle 5 Minuten aus
|
||||
command: >
|
||||
sh -c "while true; do
|
||||
python main.py && echo \"CameraSave ausgeführt um \$$(date)\" && sleep 300;
|
||||
done"
|
||||
done"
|
||||
|
||||
monitor:
|
||||
build: .
|
||||
container_name: camerasave-monitor
|
||||
restart: unless-stopped
|
||||
volumes:
|
||||
- heartbeat:/app
|
||||
env_file:
|
||||
- .env
|
||||
environment:
|
||||
- HEARTBEAT_FILE=/app/heartbeat.txt
|
||||
- CHECK_INTERVAL=600 # Prüfung alle 10 Minuten
|
||||
- MAX_AGE=900 # Alarm nach 15 Minuten ohne Heartbeat
|
||||
- ALERT_COOLDOWN=3600 # 1 Stunde zwischen Alarm-E-Mails
|
||||
- SMTP_SERVER=${SMTP_SERVER:-securesmtp.t-online.de}
|
||||
- SMTP_PORT=${SMTP_PORT:-587}
|
||||
- SMTP_USER=${SMTP_USER:-${EMAIL_USER}}
|
||||
- SMTP_PASS=${SMTP_PASS:-${EMAIL_PASS}}
|
||||
- ALERT_EMAIL=${ALERT_EMAIL:-${EMAIL_USER}}
|
||||
command: python monitor.py
|
||||
|
||||
volumes:
|
||||
heartbeat:
|
||||
15
main.py
15
main.py
@@ -10,6 +10,17 @@ IMAP_PORT = int(os.getenv("IMAP_PORT", "993"))
|
||||
EMAIL_USER = os.getenv("EMAIL_USER", "dk2ge@t-online.de")
|
||||
EMAIL_PASS = os.getenv("EMAIL_PASS", "ETBjw65tf2")
|
||||
SAVE_DIR = os.getenv("SAVE_DIR", "./videospeicher")
|
||||
HEARTBEAT_FILE = os.getenv("HEARTBEAT_FILE", "/app/heartbeat.txt")
|
||||
|
||||
# === HEARTBEAT ===
|
||||
def update_heartbeat():
|
||||
"""Schreibt einen Heartbeat für das Monitoring."""
|
||||
try:
|
||||
with open(HEARTBEAT_FILE, "w") as f:
|
||||
f.write(datetime.now().isoformat())
|
||||
print(f"💓 Heartbeat aktualisiert: {HEARTBEAT_FILE}")
|
||||
except Exception as e:
|
||||
print(f"⚠️ Fehler beim Heartbeat-Update: {e}")
|
||||
|
||||
# === ALTE DATEIEN LÖSCHEN (älter als 1 Jahr) ===
|
||||
def cleanup_old_files(base_dir, days=365):
|
||||
@@ -84,5 +95,7 @@ def process_mails():
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
update_heartbeat() # Heartbeat zu Beginn
|
||||
cleanup_old_files(SAVE_DIR, days=365)
|
||||
process_mails()
|
||||
process_mails()
|
||||
update_heartbeat() # Heartbeat nach erfolgreicher Ausführung
|
||||
|
||||
142
monitor.py
Normal file
142
monitor.py
Normal file
@@ -0,0 +1,142 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Monitoring-Script für CameraSave
|
||||
Prüft, ob das Programm regelmäßig läuft und sendet E-Mail-Benachrichtigungen bei Problemen.
|
||||
"""
|
||||
|
||||
import os
|
||||
import smtplib
|
||||
import time
|
||||
from datetime import datetime, timedelta
|
||||
from email.mime.text import MIMEText
|
||||
from email.mime.multipart import MIMEMultipart
|
||||
|
||||
# === KONFIGURATION ===
|
||||
HEARTBEAT_FILE = os.getenv("HEARTBEAT_FILE", "/app/heartbeat.txt")
|
||||
CHECK_INTERVAL = int(os.getenv("CHECK_INTERVAL", "600")) # 10 Minuten
|
||||
MAX_AGE = int(os.getenv("MAX_AGE", "900")) # 15 Minuten - danach Alarm
|
||||
|
||||
# E-Mail Konfiguration für Benachrichtigungen
|
||||
SMTP_SERVER = os.getenv("SMTP_SERVER", "securesmtp.t-online.de")
|
||||
SMTP_PORT = int(os.getenv("SMTP_PORT", "587"))
|
||||
SMTP_USER = os.getenv("SMTP_USER", os.getenv("EMAIL_USER", ""))
|
||||
SMTP_PASS = os.getenv("SMTP_PASS", os.getenv("EMAIL_PASS", ""))
|
||||
ALERT_EMAIL = os.getenv("ALERT_EMAIL", SMTP_USER) # Standard: an sich selbst
|
||||
|
||||
last_alert_time = None
|
||||
ALERT_COOLDOWN = int(os.getenv("ALERT_COOLDOWN", "3600")) # 1 Stunde zwischen Alarmen
|
||||
|
||||
|
||||
def send_alert_email(subject, message):
|
||||
"""Sendet eine E-Mail-Benachrichtigung."""
|
||||
global last_alert_time
|
||||
|
||||
# Cooldown prüfen - nicht zu oft E-Mails senden
|
||||
if last_alert_time:
|
||||
time_since_last = (datetime.now() - last_alert_time).total_seconds()
|
||||
if time_since_last < ALERT_COOLDOWN:
|
||||
print(f"⏳ Cooldown aktiv. Nächste E-Mail möglich in {int(ALERT_COOLDOWN - time_since_last)}s")
|
||||
return
|
||||
|
||||
try:
|
||||
msg = MIMEMultipart()
|
||||
msg['From'] = SMTP_USER
|
||||
msg['To'] = ALERT_EMAIL
|
||||
msg['Subject'] = subject
|
||||
|
||||
body = f"""
|
||||
CameraSave Monitoring Alert
|
||||
==========================
|
||||
|
||||
{message}
|
||||
|
||||
Zeit: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}
|
||||
Server: {os.uname().nodename if hasattr(os, 'uname') else 'Unknown'}
|
||||
|
||||
Diese Nachricht wurde automatisch vom Monitoring-System generiert.
|
||||
"""
|
||||
msg.attach(MIMEText(body, 'plain'))
|
||||
|
||||
server = smtplib.SMTP(SMTP_SERVER, SMTP_PORT)
|
||||
server.starttls()
|
||||
server.login(SMTP_USER, SMTP_PASS)
|
||||
server.send_message(msg)
|
||||
server.quit()
|
||||
|
||||
last_alert_time = datetime.now()
|
||||
print(f"✅ Alert-E-Mail gesendet an {ALERT_EMAIL}")
|
||||
|
||||
except Exception as e:
|
||||
print(f"❌ Fehler beim E-Mail-Versand: {e}")
|
||||
|
||||
|
||||
def check_heartbeat():
|
||||
"""Prüft, ob die Heartbeat-Datei aktuell ist."""
|
||||
if not os.path.exists(HEARTBEAT_FILE):
|
||||
return False, "Heartbeat-Datei existiert nicht"
|
||||
|
||||
try:
|
||||
mtime = os.path.getmtime(HEARTBEAT_FILE)
|
||||
age = time.time() - mtime
|
||||
|
||||
if age > MAX_AGE:
|
||||
return False, f"Heartbeat zu alt: {int(age)}s (max {MAX_AGE}s)"
|
||||
|
||||
return True, f"OK - Heartbeat vor {int(age)}s"
|
||||
|
||||
except Exception as e:
|
||||
return False, f"Fehler beim Lesen der Heartbeat-Datei: {e}"
|
||||
|
||||
|
||||
def send_recovery_email():
|
||||
"""Sendet eine E-Mail, wenn das System sich erholt hat."""
|
||||
send_alert_email(
|
||||
"✅ CameraSave: System wiederhergestellt",
|
||||
"Das CameraSave-Programm läuft wieder normal."
|
||||
)
|
||||
|
||||
|
||||
def main():
|
||||
"""Hauptschleife des Monitoring."""
|
||||
print("🔍 CameraSave Monitor gestartet")
|
||||
print(f" Heartbeat-Datei: {HEARTBEAT_FILE}")
|
||||
print(f" Prüfintervall: {CHECK_INTERVAL}s")
|
||||
print(f" Max Alter: {MAX_AGE}s")
|
||||
print(f" Alert E-Mail: {ALERT_EMAIL}")
|
||||
print()
|
||||
|
||||
was_down = False
|
||||
|
||||
while True:
|
||||
try:
|
||||
is_healthy, status = check_heartbeat()
|
||||
timestamp = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
|
||||
|
||||
if is_healthy:
|
||||
print(f"[{timestamp}] ✅ {status}")
|
||||
if was_down:
|
||||
# System ist wieder online
|
||||
send_recovery_email()
|
||||
was_down = False
|
||||
else:
|
||||
print(f"[{timestamp}] ❌ {status}")
|
||||
if not was_down:
|
||||
# Erster Fehler - Alarm senden
|
||||
send_alert_email(
|
||||
"⚠️ CameraSave: Programm läuft nicht mehr!",
|
||||
f"Das CameraSave-Programm antwortet nicht mehr.\n\nStatus: {status}"
|
||||
)
|
||||
was_down = True
|
||||
|
||||
time.sleep(CHECK_INTERVAL)
|
||||
|
||||
except KeyboardInterrupt:
|
||||
print("\n🛑 Monitor gestoppt")
|
||||
break
|
||||
except Exception as e:
|
||||
print(f"❌ Unerwarteter Fehler: {e}")
|
||||
time.sleep(CHECK_INTERVAL)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user