Andreas Wrede
0543266c92
- Restructuring of the project directory into client and server components - Renaming of modules and classes to better reflect their purpose and functionality - Moving common utilities and configurations to a shared location - Updating import statements to reflect the new structure - Adding new documentation files for better clarity on various aspects of the project - Removing deprecated or unused code to streamline the codebase - Ensuring that all existing functionality is preserved and that the codebase remains functional after the refactoring.
112 lines
3.5 KiB
YAML
112 lines
3.5 KiB
YAML
# Heartbeat Configuration Example with Nagios Plugin Runner
|
|
|
|
# This example shows how to configure the Nagios Runner plugin
|
|
# to execute existing Nagios-compatible monitoring plugins
|
|
|
|
# Basic server settings (existing config)
|
|
hb_port: 50003
|
|
hbd_port: 50004
|
|
interval: 20
|
|
grace: 2
|
|
|
|
# Plugin configuration
|
|
# Each plugin can have its own configuration section
|
|
|
|
# CPU Monitor Plugin
|
|
cpu_monitor:
|
|
interval: 300 # Collect every 5 minutes (default)
|
|
per_core: false # Set to true to get per-core CPU usage
|
|
|
|
# Nagios Runner Plugin
|
|
nagios_runner:
|
|
interval: 300 # Run Nagios plugins every 5 minutes (default)
|
|
timeout: 30 # Command execution timeout in seconds
|
|
shell: true # Execute commands via shell
|
|
|
|
# List of Nagios plugins to run
|
|
commands:
|
|
|
|
# Example 1: Check disk space
|
|
- name: check_disk_root
|
|
command: /usr/lib/nagios/plugins/check_disk -w 20% -c 10% -p /
|
|
|
|
# Example 2: Check disk space for /home
|
|
- name: check_disk_home
|
|
command: /usr/lib/nagios/plugins/check_disk -w 20% -c 10% -p /home
|
|
|
|
# Example 3: Check system load
|
|
- name: check_load
|
|
command: /usr/lib/nagios/plugins/check_load -w 5,4,3 -c 10,8,6
|
|
|
|
# Example 4: Check process count
|
|
- name: check_procs
|
|
command: /usr/lib/nagios/plugins/check_procs -w 250 -c 400
|
|
|
|
# Example 5: Check SSH service
|
|
- name: check_ssh
|
|
command: /usr/lib/nagios/plugins/check_ssh localhost
|
|
|
|
# Example 6: Check HTTP service
|
|
- name: check_http
|
|
command: /usr/lib/nagios/plugins/check_http -H localhost
|
|
|
|
# Example 7: Check swap usage
|
|
- name: check_swap
|
|
command: /usr/lib/nagios/plugins/check_swap -w 20% -c 10%
|
|
|
|
# Example 8: Custom script (Nagios plugin format)
|
|
- name: check_custom
|
|
command: /usr/local/bin/my_custom_check.sh
|
|
|
|
# Example 9: Check specific log file
|
|
- name: check_logs
|
|
command: /usr/lib/nagios/plugins/check_log -F /var/log/syslog -O /var/tmp/check_log.old -q "ERROR"
|
|
|
|
# Notes:
|
|
#
|
|
# 1. Nagios Plugin Output Format:
|
|
# - Single line: STATUS - Message | performance_data
|
|
# - Performance data format: 'label'=value[UOM];[warn];[crit];[min];[max]
|
|
#
|
|
# 2. Exit Codes:
|
|
# - 0 = OK
|
|
# - 1 = WARNING
|
|
# - 2 = CRITICAL
|
|
# - 3 = UNKNOWN
|
|
#
|
|
# 3. Performance Data:
|
|
# - Automatically parsed and included in heartbeat data
|
|
# - Metrics are stored as: {plugin_name}_{metric_name}
|
|
# - Example: check_disk_root_/ will contain the disk usage percentage
|
|
#
|
|
# 4. Overall Status:
|
|
# - The plugin reports the worst status from all commands
|
|
# - Useful for quick health checks
|
|
#
|
|
# 5. Plugin Paths:
|
|
# Common Nagios plugin directories:
|
|
# - Debian/Ubuntu: /usr/lib/nagios/plugins/
|
|
# - RHEL/CentOS: /usr/lib64/nagios/plugins/
|
|
# - Custom installs: /usr/local/nagios/libexec/
|
|
#
|
|
# 6. Installing Nagios Plugins:
|
|
# Debian/Ubuntu: sudo apt-get install nagios-plugins
|
|
# RHEL/CentOS: sudo yum install nagios-plugins-all
|
|
# Arch Linux: sudo pacman -S monitoring-plugins
|
|
#
|
|
# 7. Writing Custom Nagios Plugins:
|
|
# Any script can be a Nagios plugin if it:
|
|
# - Returns appropriate exit codes (0-3)
|
|
# - Prints status message to stdout
|
|
# - Optionally includes performance data after "|"
|
|
#
|
|
# Example custom plugin (save as /usr/local/bin/check_example.sh):
|
|
# #!/bin/bash
|
|
# if [ $(uptime | awk '{print $1}') -gt 50 ]; then
|
|
# echo "CRITICAL - Too many users | users=52;40;50;0"
|
|
# exit 2
|
|
# else
|
|
# echo "OK - Normal user count | users=25;40;50;0"
|
|
# exit 0
|
|
# fi
|