System Monitoring Integration

Kategorie:: home_assistant
Unterkategorie:: integrations
Pfad:: templates/home-assistant/integrations/system-monitoring
Code kopieren & zu File Editor
Beschreibung & Dokumentation

Kurzbeschreibung

Umfassende Überwachung von Raspberry Pi, Servern, UPS und Netzwerk-Performance mit automatischen Alarmen bei kritischen Zuständen. - Hardware-Monitoring: CPU-Temperatur, RAM, Festplatte, Load Aver...
Vollständige Dokumentation

System Monitoring Integration

Zweck

Umfassende Überwachung von Raspberry Pi, Servern, UPS und Netzwerk-Performance mit automatischen Alarmen bei kritischen Zuständen.
Features

Hardware-Monitoring: CPU-Temperatur, RAM, Festplatte, Load Average
UPS-Überwachung: Batteriestatus, St...
Code-Vorschau

Haupt-Konfiguration
Tipp: Markieren & ⌘/Ctrl + C zum Kopieren
configuration.yaml
# System Monitoring Integration
# Überwacht Raspberry Pi, Server und UPS-Status über Command Line und SSH

# Command Line Sensoren für lokales System
sensor:
  # CPU Temperatur (Raspberry Pi)
  - platform: command_line
    name: "RPi CPU Temperature"
    command: 'cat /sys/class/thermal/thermal_zone0/temp'
    unit_of_measurement: "°C"
    value_template: "{{ value | multiply(0.001) | round(1) }}"
    scan_interval: 60
    icon: "mdi:thermometer"

  # CPU Auslastung
  - platform: command_line
    name: "RPi CPU Usage"
    command: "top -bn1 | grep 'Cpu(s)' | awk '{print $2}' | cut -d'%' -f1"
    unit_of_measurement: "%"
    value_template: "{{ value | float | round(1) }}"
    scan_interval: 30
    icon: "mdi:cpu-64-bit"

  # RAM Verwendung
  - platform: command_line
    name: "RPi Memory Usage"
    command: "free | grep Mem | awk '{printf \"%.1f\", $3/$2 * 100.0}'"
    unit_of_measurement: "%"
    scan_interval: 60
    icon: "mdi:memory"

  # Festplatten-Nutzung
  - platform: command_line
    name: "RPi Disk Usage"
    command: "df -h / | awk 'NR==2{print $5}' | cut -d'%' -f1"
    unit_of_measurement: "%"
    scan_interval: 300
    icon: "mdi:harddisk"

  # Freier Speicher in GB
  - platform: command_line
    name: "RPi Disk Free"
    command: "df -BG / | awk 'NR==2{print $4}' | cut -d'G' -f1"
    unit_of_measurement: "GB"
    scan_interval: 300
    icon: "mdi:harddisk"

  # Uptime in Tagen
  - platform: command_line
    name: "RPi Uptime"
    command: "awk '{print int($1/86400)}' /proc/uptime"
    unit_of_measurement: "Tage"
    scan_interval: 3600
    icon: "mdi:clock-outline"

  # Load Average
  - platform: command_line
    name: "RPi Load Average"
    command: "uptime | awk -F'load average:' '{print $2}' | awk '{print $1}' | cut -d',' -f1"
    scan_interval: 60
    icon: "mdi:gauge"

  # Netzwerk Traffic (Download MB/s)
  - platform: command_line
    name: "RPi Network Download"
    command: "cat /sys/class/net/eth0/statistics/rx_bytes"
    scan_interval: 10
    value_template: >
      {% if states('sensor.rpi_network_download') != 'unknown' %}
        {% set prev = states('sensor.rpi_network_download') | float %}
        {% set curr = value | float %}
        {% if curr > prev %}
          {{ ((curr - prev) / (1024*1024) / 10) | round(2) }}
        {% else %}
          0
        {% endif %}
      {% else %}
        0
      {% endif %}
    unit_of_measurement: "MB/s"
    icon: "mdi:download"

# UPS Monitoring (für APC UPS über apcupsd)
  - platform: command_line
    name: "UPS Status"
    command: 'apcaccess status | grep "STATUS" | cut -d":" -f2 | xargs'
    scan_interval: 60
    icon: "mdi:battery-charging"

  - platform: command_line
    name: "UPS Battery Level"
    command: 'apcaccess status | grep "BCHARGE" | cut -d":" -f2 | cut -d" " -f2'
    unit_of_measurement: "%"
    scan_interval: 60
    device_class: battery
    icon: "mdi:battery"

  - platform: command_line
    name: "UPS Load"
    command: 'apcaccess status | grep "LOADPCT" | cut -d":" -f2 | cut -d" " -f2'
    unit_of_measurement: "%"
    scan_interval: 60
    icon: "mdi:flash"

  - platform: command_line
    name: "UPS Time Left"
    command: 'apcaccess status | grep "TIMELEFT" | cut -d":" -f2 | cut -d" " -f2'
    unit_of_measurement: "min"
    scan_interval: 60
    icon: "mdi:timer"

# Internet Speed Test (einmal täglich)
  - platform: command_line
    name: "Internet Speed Download"
    command: 'speedtest-cli --simple | grep "Download" | cut -d" " -f2'
    unit_of_measurement: "Mbit/s"
    scan_interval: 86400  # Einmal am Tag
    icon: "mdi:speedometer"

  - platform: command_line
    name: "Internet Speed Upload"
    command: 'speedtest-cli --simple | grep "Upload" | cut -d" " -f2'
    unit_of_measurement: "Mbit/s"
    scan_interval: 86400
    icon: "mdi:upload"

# SSH-basierte Remote Server Überwachung
  - platform: command_line
    name: "Server CPU Temperature"
    command: 'ssh user@192.168.1.100 "cat /sys/class/thermal/thermal_zone0/temp"'
    unit_of_measurement: "°C"
    value_template: "{{ value | multiply(0.001) | round(1) }}"
    scan_interval: 300
    icon: "mdi:thermometer"

  - platform: command_line
    name: "Server Disk Usage"
    command: 'ssh user@192.168.1.100 "df -h / | awk '\''NR==2{print \$5}'\'' | cut -d'\''%'\'' -f1"'
    unit_of_measurement: "%"
    scan_interval: 600
    icon: "mdi:harddisk"

# Docker Container Monitoring
  - platform: command_line
    name: "Docker Containers Running"
    command: 'docker ps -q | wc -l'
    scan_interval: 120
    icon: "mdi:docker"

  - platform: command_line
    name: "Docker Containers Total"
    command: 'docker ps -a -q | wc -l'
    scan_interval: 300
    icon: "mdi:docker"

# Home Assistant eigene Statistiken
  - platform: command_line
    name: "HA Database Size"
    command: 'du -sh /config/home-assistant_v2.db | cut -f1'
    scan_interval: 3600
    icon: "mdi:database"

  - platform: command_line
    name: "HA Log Size"
    command: 'du -sh /config/home-assistant.log | cut -f1'
    scan_interval: 1800
    icon: "mdi:file-document"

# Template Sensoren für erweiterte Berechnungen
  - platform: template
    sensors:
      rpi_cpu_temperature_status:
        friendly_name: "RPi CPU Status"
        value_template: >
          {% set temp = states('sensor.rpi_cpu_temperature') | float %}
          {% if temp < 50 %}Normal
          {% elif temp < 65 %}Warm
          {% elif temp < 80 %}Heiß
          {% else %}Kritisch
          {% endif %}
        icon_template: >
          {% set temp = states('sensor.rpi_cpu_temperature') | float %}
          {% if temp < 50 %}mdi:thermometer-low
          {% elif temp < 65 %}mdi:thermometer
          {% elif temp < 80 %}mdi:thermometer-high
          {% else %}mdi:thermometer-alert
          {% endif %}

      system_health_score:
        friendly_name: "System Health Score"
        unit_of_measurement: "%"
        value_template: >
          {% set cpu_temp = states('sensor.rpi_cpu_temperature') | float %}
          {% set cpu_usage = states('sensor.rpi_cpu_usage') | float %}
          {% set mem_usage = states('sensor.rpi_memory_usage') | float %}
          {% set disk_usage = states('sensor.rpi_disk_usage') | float %}
          
          {% set temp_score = 100 - ((cpu_temp - 30) * 2) if cpu_temp > 30 else 100 %}
          {% set cpu_score = 100 - cpu_usage %}
          {% set mem_score = 100 - mem_usage %}
          {% set disk_score = 100 - disk_usage %}
          
          {{ ((temp_score + cpu_score + mem_score + disk_score) / 4) | round(0) }}
        icon_template: >
          {% set score = states('sensor.system_health_score') | float %}
          {% if score > 80 %}mdi:heart
          {% elif score > 60 %}mdi:heart-half
          {% else %}mdi:heart-broken
          {% endif %}

# Binäre Sensoren für Alarme
binary_sensor:
  - platform: template
    sensors:
      rpi_high_temperature:
        friendly_name: "RPi Überhitzung"
        value_template: "{{ states('sensor.rpi_cpu_temperature') | float > 70 }}"
        device_class: heat
        delay_on: "00:02:00"

      rpi_high_cpu_usage:
        friendly_name: "RPi Hohe CPU Last"
        value_template: "{{ states('sensor.rpi_cpu_usage') | float > 80 }}"
        delay_on: "00:05:00"

      rpi_low_disk_space:
        friendly_name: "RPi Wenig Speicher"
        value_template: "{{ states('sensor.rpi_disk_usage') | float > 85 }}"
        device_class: problem
        delay_on: "00:30:00"

      ups_battery_low:
        friendly_name: "UPS Batterie schwach"
        value_template: "{{ states('sensor.ups_battery_level') | float < 20 }}"
        device_class: battery
        delay_on: "00:02:00"

      ups_on_battery:
        friendly_name: "UPS im Batteriebetrieb"
        value_template: "{{ states('sensor.ups_status') == 'ONBATT' }}"
        device_class: power
        delay_on: "00:00:30"

      internet_slow:
        friendly_name: "Langsames Internet"
        value_template: "{{ states('sensor.internet_speed_download') | float < 25 }}"
        delay_on: "00:10:00"

# Automatisierungen für System-Alerts
automation:
  - alias: "System Überhitzung Warnung"
    trigger:
      platform: state
      entity_id: binary_sensor.rpi_high_temperature
      to: "on"
    action:
      - service: notify.mobile_app
        data:
          title: "🌡️ System Überhitzung"
          message: "RPi CPU: {{ states('sensor.rpi_cpu_temperature') }}°C"
          data:
            tag: "system_temp"
            color: "red"

  - alias: "UPS Stromausfall"
    trigger:
      platform: state
      entity_id: binary_sensor.ups_on_battery
      to: "on"
    action:
      - service: notify.mobile_app
        data:
          title: "⚡ Stromausfall erkannt"
          message: "UPS im Batteriebetrieb - {{ states('sensor.ups_time_left') }} min verbleibend"
          data:
            tag: "power_outage"
            color: "red"
            sound: "alarm.wav"

  - alias: "Wenig Speicherplatz"
    trigger:
      platform: state
      entity_id: binary_sensor.rpi_low_disk_space
      to: "on"
    action:
      - service: notify.mobile_app
        data:
          title: "💾 Speicher knapp"
          message: "Nur noch {{ states('sensor.rpi_disk_free') }}GB frei ({{ states('sensor.rpi_disk_usage') }}% belegt)"

  - alias: "System Health Check"
    trigger:
      platform: time
      at: "09:00:00"
    action:
      - service: notify.mobile_app
        data:
          title: "📊 Täglicher System Report"
          message: >
            Health Score: {{ states('sensor.system_health_score') }}%
            CPU: {{ states('sensor.rpi_cpu_temperature') }}°C
            Uptime: {{ states('sensor.rpi_uptime') }} Tage
            UPS: {{ states('sensor.ups_battery_level') }}%

# Script für manuellen Speed Test
script:
  run_speed_test:
    alias: "Internet Speed Test starten"
    sequence:
      - service: notify.persistent_notification
        data:
          title: "Speed Test"
          message: "Internet Speed Test wird durchgeführt..."
      - service: homeassistant.update_entity
        target:
          entity_id: 
            - sensor.internet_speed_download
            - sensor.internet_speed_upload
      - delay: 60
      - service: notify.mobile_app
        data:
          title: "🌐 Speed Test Ergebnis"
          message: >
            Download: {{ states('sensor.internet_speed_download') }} Mbit/s
            Upload: {{ states('sensor.internet_speed_upload') }} Mbit/s

# Input Helper für Konfiguration
input_number:
  system_alert_cpu_threshold:
    name: "CPU Alarm Schwelle"
    min: 60
    max: 95
    step: 5
    initial: 80
    unit_of_measurement: "%"
    icon: "mdi:cpu-64-bit"

  system_alert_temp_threshold:
    name: "Temperatur Alarm Schwelle"
    min: 60
    max: 85
    step: 1
    initial: 70
    unit_of_measurement: "°C"
    icon: "mdi:thermometer"

input_boolean:
  system_monitoring_enabled:
    name: "System Monitoring aktiviert"
    initial: true
    icon: "mdi:monitor-dashboard"

  system_notifications_enabled:
    name: "System Benachrichtigungen"
    initial: true
    icon: "mdi:bell"