stuff
This commit is contained in:
parent
c8754e1bdc
commit
fbbeb59c0e
GPG key ID:
883EDBAA726BD96C
28 changed files with 907 additions and 995 deletions
316
ansible/infra/430_cpu_temp_alerts.yml
Normal file
316
ansible/infra/430_cpu_temp_alerts.yml
Normal file
|
|
@ -0,0 +1,316 @@
|
|||
- name: Deploy CPU Temperature Monitoring
|
||||
hosts: nodito
|
||||
become: yes
|
||||
vars_files:
|
||||
- ../infra_vars.yml
|
||||
- ../services_config.yml
|
||||
- ../infra_secrets.yml
|
||||
|
||||
vars:
|
||||
temp_threshold_celsius: 80
|
||||
temp_check_interval_minutes: 1
|
||||
monitoring_script_dir: /opt/nodito-monitoring
|
||||
monitoring_script_path: "{{ monitoring_script_dir }}/cpu_temp_monitor.sh"
|
||||
log_file: "{{ monitoring_script_dir }}/cpu_temp_monitor.log"
|
||||
systemd_service_name: nodito-cpu-temp-monitor
|
||||
uptime_kuma_api_url: "https://{{ subdomains.uptime_kuma }}.{{ root_domain }}"
|
||||
ntfy_topic: "{{ service_settings.ntfy.topic }}"
|
||||
|
||||
tasks:
|
||||
- name: Validate Uptime Kuma configuration
|
||||
assert:
|
||||
that:
|
||||
- uptime_kuma_api_url is defined
|
||||
- uptime_kuma_api_url != ""
|
||||
- uptime_kuma_username is defined
|
||||
- uptime_kuma_username != ""
|
||||
- uptime_kuma_password is defined
|
||||
- uptime_kuma_password != ""
|
||||
fail_msg: "uptime_kuma_api_url, uptime_kuma_username and uptime_kuma_password must be set"
|
||||
|
||||
- name: Get hostname for monitor identification
|
||||
command: hostname
|
||||
register: host_name
|
||||
changed_when: false
|
||||
|
||||
- name: Set monitor name and group based on hostname
|
||||
set_fact:
|
||||
monitor_name: "cpu-temp-{{ host_name.stdout }}"
|
||||
monitor_friendly_name: "CPU Temperature: {{ host_name.stdout }}"
|
||||
uptime_kuma_monitor_group: "{{ host_name.stdout }} - infra"
|
||||
|
||||
- name: Create Uptime Kuma CPU temperature monitor setup script
|
||||
copy:
|
||||
dest: /tmp/setup_uptime_kuma_cpu_temp_monitor.py
|
||||
content: |
|
||||
#!/usr/bin/env python3
|
||||
import sys
|
||||
import json
|
||||
from uptime_kuma_api import UptimeKumaApi
|
||||
|
||||
def main():
|
||||
api_url = sys.argv[1]
|
||||
username = sys.argv[2]
|
||||
password = sys.argv[3]
|
||||
group_name = sys.argv[4]
|
||||
monitor_name = sys.argv[5]
|
||||
monitor_description = sys.argv[6]
|
||||
interval = int(sys.argv[7])
|
||||
ntfy_topic = sys.argv[8] if len(sys.argv) > 8 else "alerts"
|
||||
|
||||
api = UptimeKumaApi(api_url, timeout=60, wait_events=2.0)
|
||||
api.login(username, password)
|
||||
|
||||
monitors = api.get_monitors()
|
||||
notifications = api.get_notifications()
|
||||
|
||||
ntfy_notification = next((n for n in notifications if n.get('name') == f'ntfy ({ntfy_topic})'), None)
|
||||
notification_id_list = {}
|
||||
if ntfy_notification:
|
||||
notification_id_list[ntfy_notification['id']] = True
|
||||
|
||||
group = next((m for m in monitors if m.get('name') == group_name and m.get('type') == 'group'), None)
|
||||
if not group:
|
||||
api.add_monitor(type='group', name=group_name)
|
||||
monitors = api.get_monitors()
|
||||
group = next((m for m in monitors if m.get('name') == group_name and m.get('type') == 'group'), None)
|
||||
|
||||
existing_monitor = next((m for m in monitors if m.get('name') == monitor_name), None)
|
||||
|
||||
monitor_data = {
|
||||
'type': 'push',
|
||||
'name': monitor_name,
|
||||
'parent': group['id'],
|
||||
'interval': interval,
|
||||
'upsideDown': True,
|
||||
'description': monitor_description,
|
||||
'notificationIDList': notification_id_list
|
||||
}
|
||||
|
||||
if existing_monitor:
|
||||
api.edit_monitor(existing_monitor['id'], **monitor_data)
|
||||
else:
|
||||
api.add_monitor(**monitor_data)
|
||||
|
||||
monitors = api.get_monitors()
|
||||
monitor = next((m for m in monitors if m.get('name') == monitor_name), None)
|
||||
|
||||
result = {
|
||||
'monitor_id': monitor['id'],
|
||||
'push_token': monitor['pushToken'],
|
||||
'group_name': group_name,
|
||||
'group_id': group['id'],
|
||||
'monitor_name': monitor_name
|
||||
}
|
||||
print(json.dumps(result))
|
||||
|
||||
api.disconnect()
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
mode: '0755'
|
||||
delegate_to: localhost
|
||||
become: no
|
||||
|
||||
- name: Run Uptime Kuma monitor setup script
|
||||
command: >
|
||||
{{ ansible_playbook_python }}
|
||||
/tmp/setup_uptime_kuma_cpu_temp_monitor.py
|
||||
"{{ uptime_kuma_api_url }}"
|
||||
"{{ uptime_kuma_username }}"
|
||||
"{{ uptime_kuma_password }}"
|
||||
"{{ uptime_kuma_monitor_group }}"
|
||||
"{{ monitor_name }}"
|
||||
"{{ monitor_friendly_name }} - Alerts when temperature exceeds {{ temp_threshold_celsius }}°C"
|
||||
"{{ (temp_check_interval_minutes * 60) + 60 }}"
|
||||
"{{ ntfy_topic }}"
|
||||
register: monitor_setup_result
|
||||
delegate_to: localhost
|
||||
become: no
|
||||
changed_when: false
|
||||
|
||||
- name: Parse monitor setup result
|
||||
set_fact:
|
||||
monitor_info_parsed: "{{ monitor_setup_result.stdout | from_json }}"
|
||||
|
||||
- name: Set push URL and monitor ID as facts
|
||||
set_fact:
|
||||
uptime_kuma_cpu_temp_push_url: "{{ uptime_kuma_api_url }}/api/push/{{ monitor_info_parsed.push_token }}"
|
||||
uptime_kuma_monitor_id: "{{ monitor_info_parsed.monitor_id }}"
|
||||
|
||||
- name: Install required packages for temperature monitoring
|
||||
package:
|
||||
name:
|
||||
- lm-sensors
|
||||
- curl
|
||||
- jq
|
||||
- bc
|
||||
state: present
|
||||
|
||||
- name: Create monitoring script directory
|
||||
file:
|
||||
path: "{{ monitoring_script_dir }}"
|
||||
state: directory
|
||||
owner: root
|
||||
group: root
|
||||
mode: '0755'
|
||||
|
||||
- name: Create CPU temperature monitoring script
|
||||
copy:
|
||||
dest: "{{ monitoring_script_path }}"
|
||||
content: |
|
||||
#!/bin/bash
|
||||
|
||||
# CPU Temperature Monitoring Script
|
||||
# Monitors CPU temperature and sends alerts to Uptime Kuma
|
||||
|
||||
LOG_FILE="{{ log_file }}"
|
||||
TEMP_THRESHOLD="{{ temp_threshold_celsius }}"
|
||||
UPTIME_KUMA_URL="{{ uptime_kuma_cpu_temp_push_url }}"
|
||||
|
||||
log_message() {
|
||||
echo "$(date '+%Y-%m-%d %H:%M:%S') - $1" >> "$LOG_FILE"
|
||||
}
|
||||
|
||||
get_cpu_temp() {
|
||||
local temp=""
|
||||
|
||||
if command -v sensors >/dev/null 2>&1; then
|
||||
temp=$(sensors 2>/dev/null | grep -E "Core 0|Package id 0|Tdie|Tctl" | head -1 | grep -oE '[0-9]+\.[0-9]+°C' | grep -oE '[0-9]+\.[0-9]+')
|
||||
fi
|
||||
|
||||
if [ -z "$temp" ] && [ -f /sys/class/thermal/thermal_zone0/temp ]; then
|
||||
temp=$(cat /sys/class/thermal/thermal_zone0/temp)
|
||||
temp=$(echo "scale=1; $temp/1000" | bc -l 2>/dev/null || echo "$temp")
|
||||
fi
|
||||
|
||||
if [ -z "$temp" ] && command -v acpi >/dev/null 2>&1; then
|
||||
temp=$(acpi -t 2>/dev/null | grep -oE '[0-9]+\.[0-9]+' | head -1)
|
||||
fi
|
||||
|
||||
echo "$temp"
|
||||
}
|
||||
|
||||
send_uptime_kuma_alert() {
|
||||
local temp="$1"
|
||||
local message="CPU Temperature Alert: ${temp}°C (Threshold: ${TEMP_THRESHOLD}°C)"
|
||||
|
||||
log_message "ALERT: $message"
|
||||
|
||||
encoded_message=$(printf '%s\n' "$message" | sed 's/ /%20/g; s/°/%C2%B0/g; s/(/%28/g; s/)/%29/g; s/:/%3A/g')
|
||||
response=$(curl -s -w "\n%{http_code}" "$UPTIME_KUMA_URL?status=up&msg=$encoded_message" 2>&1)
|
||||
http_code=$(echo "$response" | tail -n1)
|
||||
|
||||
if [ "$http_code" = "200" ] || [ "$http_code" = "201" ]; then
|
||||
log_message "Alert sent successfully to Uptime Kuma (HTTP $http_code)"
|
||||
else
|
||||
log_message "ERROR: Failed to send alert to Uptime Kuma (HTTP $http_code)"
|
||||
fi
|
||||
}
|
||||
|
||||
main() {
|
||||
log_message "Starting CPU temperature check"
|
||||
|
||||
current_temp=$(get_cpu_temp)
|
||||
|
||||
if [ -z "$current_temp" ]; then
|
||||
log_message "ERROR: Could not read CPU temperature"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
log_message "Current CPU temperature: ${current_temp}°C"
|
||||
|
||||
if (( $(echo "$current_temp > $TEMP_THRESHOLD" | bc -l) )); then
|
||||
log_message "WARNING: CPU temperature ${current_temp}°C exceeds threshold ${TEMP_THRESHOLD}°C"
|
||||
send_uptime_kuma_alert "$current_temp"
|
||||
else
|
||||
log_message "CPU temperature is within normal range"
|
||||
fi
|
||||
}
|
||||
|
||||
main
|
||||
owner: root
|
||||
group: root
|
||||
mode: '0755'
|
||||
|
||||
- name: Create systemd service for CPU temperature monitoring
|
||||
copy:
|
||||
dest: "/etc/systemd/system/{{ systemd_service_name }}.service"
|
||||
content: |
|
||||
[Unit]
|
||||
Description=CPU Temperature Monitor
|
||||
After=network.target
|
||||
|
||||
[Service]
|
||||
Type=oneshot
|
||||
ExecStart={{ monitoring_script_path }}
|
||||
User=root
|
||||
StandardOutput=journal
|
||||
StandardError=journal
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
owner: root
|
||||
group: root
|
||||
mode: '0644'
|
||||
|
||||
- name: Create systemd timer for CPU temperature monitoring
|
||||
copy:
|
||||
dest: "/etc/systemd/system/{{ systemd_service_name }}.timer"
|
||||
content: |
|
||||
[Unit]
|
||||
Description=Run CPU Temperature Monitor every {{ temp_check_interval_minutes }} minute(s)
|
||||
Requires={{ systemd_service_name }}.service
|
||||
|
||||
[Timer]
|
||||
OnBootSec={{ temp_check_interval_minutes }}min
|
||||
OnUnitActiveSec={{ temp_check_interval_minutes }}min
|
||||
Persistent=true
|
||||
|
||||
[Install]
|
||||
WantedBy=timers.target
|
||||
owner: root
|
||||
group: root
|
||||
mode: '0644'
|
||||
|
||||
- name: Reload systemd daemon
|
||||
systemd:
|
||||
daemon_reload: yes
|
||||
|
||||
- name: Enable and start CPU temperature monitoring timer
|
||||
systemd:
|
||||
name: "{{ systemd_service_name }}.timer"
|
||||
enabled: yes
|
||||
state: started
|
||||
|
||||
- name: Test CPU temperature monitoring script
|
||||
command: "{{ monitoring_script_path }}"
|
||||
register: script_test
|
||||
changed_when: false
|
||||
|
||||
- name: Verify script execution
|
||||
assert:
|
||||
that:
|
||||
- script_test.rc == 0
|
||||
fail_msg: "CPU temperature monitoring script failed to execute properly"
|
||||
|
||||
- name: Display monitoring configuration
|
||||
debug:
|
||||
msg:
|
||||
- "CPU Temperature Monitoring configured successfully"
|
||||
- "Temperature threshold: {{ temp_threshold_celsius }}°C"
|
||||
- "Check interval: {{ temp_check_interval_minutes }} minute(s)"
|
||||
- "Monitor Name: {{ monitor_friendly_name }}"
|
||||
- "Monitor Group: {{ uptime_kuma_monitor_group }}"
|
||||
- "Uptime Kuma Push URL: {{ uptime_kuma_cpu_temp_push_url }}"
|
||||
- "Monitoring script: {{ monitoring_script_path }}"
|
||||
- "Systemd Service: {{ systemd_service_name }}.service"
|
||||
- "Systemd Timer: {{ systemd_service_name }}.timer"
|
||||
|
||||
- name: Clean up temporary Uptime Kuma setup script
|
||||
file:
|
||||
path: /tmp/setup_uptime_kuma_cpu_temp_monitor.py
|
||||
state: absent
|
||||
delegate_to: localhost
|
||||
become: no
|
||||
|
||||
Loading…
Add table
Add a link
Reference in a new issue