add check_systemd_service, update service files, other minor adjustments

check_mysql_slave.py

@@ -12,7 +12,7 @@ from checker.types import try_int
 ## MySQL User Setup ##
 
 Attention: The DB-user you type in must have CLIENT REPLICATION rights on the DB-server. Example:
-    GRANT REPLICATION CLIENT on *.* TO 'nagios'@'monitoringhost' IDENTIFIED BY 'secret';
+    GRANT REPLICATION CLIENT,SLAVE MONITOR on *.* TO 'nagios'@'monitoringhost' IDENTIFIED BY 'secret';
 
 If you use MariaDB 10.5 or newer, the DB user must have REPLICA MONITOR rights:
     GRANT REPLICA MONITOR ON *.* TO 'nagios'@'monitoringhost' IDENTIFIED BY 'secret';
@@ -25,7 +25,7 @@ Warning deviation = 10%
 Critical deviation = 15%
 
 This will set the warning levels to 330 and 270 seconds, if the delay is greater or less than these values it will return WARNING.
-The critical levels will be 345 and 255 seconds. 
+The critical levels will be 345 and 255 seconds.
 """
 
 

check_pve_guest_metrics.py

@@ -13,6 +13,7 @@ from proxmoxer import ProxmoxAPI, ResourceException
 
 import checker.nagios as nagios
 from checker.markdown import list_to_markdown_table
+from checker.result import quit_check
 from checker.units import filesize
 
 parser = argparse.ArgumentParser(description='Check the Proxmox API for network traffic for a host.')
@@ -142,6 +143,9 @@ def main():
             continue
         check_data[metric]['value'] = avg
 
+        if not avg:
+            quit_check('no data', nagios.STATE_UNKNOWN)
+
         if metrics_levels[metric]['type'] == 'filesize':
             check_data[metric]['value_str'] = filesize(avg)
             check_data[metric]['value'] = f'{int(avg)}B'

check_systemd_service.sh

@@ -0,0 +1,61 @@
+#!/bin/bash
+
+function usage {
+  echo "Usage:
+  -u [UNIT name]
+  -t Service is triggered by a timer and is allowed to be inactive"
+}
+
+# Initialize variables
+UNIT=""
+IS_TIMER=false
+
+# Parse command line arguments
+while getopts "u:t" opt; do
+  case ${opt} in
+    u )
+      UNIT=$OPTARG
+      ;;
+    t )
+      IS_TIMER=true
+      ;;
+    \? )
+      echo "Invalid option: $OPTARG" 1>&2
+      exit 1
+      ;;
+    : )
+      echo "Invalid option: $OPTARG requires an argument" 1>&2
+      exit 1
+      ;;
+  esac
+done
+shift $((OPTIND -1))
+
+# Check if UNIT name is provided
+if [ -z "$UNIT" ]; then
+    usage
+    exit -1
+fi
+
+# Check if the unit is enabled
+enabled=$(systemctl is-enabled "$UNIT")
+if [ "$enabled" != "enabled" ]; then
+    echo "CRITICAL - $UNIT is not enabled"
+    exit 2
+fi
+
+# Check if the unit is active
+active=$(systemctl is-active "$UNIT")
+substate=$(systemctl show "$UNIT" --property=SubState --value)
+
+if [ "$active" != "active" ] || { [ "$substate" = "exited" ] && [ "$IS_TIMER" = false ]; }; then
+    echo "CRITICAL - $UNIT is not active"
+    exit 2
+fi
+
+if [ "$IS_TIMER" = true ] && [ "$substate" = "exited" ]; then
+    echo "OK - $UNIT is active (exited) and enabled"
+else
+    echo "OK - $UNIT is active and enabled"
+fi
+exit 0

services/failoverdue.service

@@ -7,7 +7,8 @@ Requires=icinga2.service icinga-director.service
 User=flask
 ExecStart=/opt/venvs/icinga2/icinga2_checks/bin/python3 /opt/icinga2-checks/Other/fail-overdue.py --password XXXXX --insecure
 SyslogIdentifier=failoverdue
-Restart=always
+Restart=on-failure
+RestartSec=5s
 
 [Install]
 WantedBy=multi-user.target

services/icinga2kuma.service

@@ -9,7 +9,8 @@ Environment="ICINGA2KUMA_ICINGA2_PW=[your icinga2 API password]"
 WorkingDirectory=/opt/icinga2-checks/Other
 ExecStart=/opt/venvs/icinga2/icinga2_checks/bin/gunicorn -b 0.0.0.0:8081 -w 4 icinga2kuma:app
 SyslogIdentifier=icinga2kuma
-Restart=always
+Restart=on-failure
+RestartSec=5s
 
 [Install]
 WantedBy=multi-user.target