Sanitized mirror from private repository - 2026-04-19 08:46:29 UTC

alerting/alert-rules.yml

@@ -0,0 +1,146 @@
+# Prometheus Alerting Rules for Homelab Infrastructure
+
+groups:
+  - name: host-availability
+    interval: 30s
+    rules:
+      - alert: HostDown
+        expr: up{job=~".*-node"} == 0
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Host {{ $labels.instance }} is down"
+          description: "Host {{ $labels.instance }} has been unreachable for more than 2 minutes."
+
+      - alert: HostHighLoadAverage
+        expr: node_load15 / count without(cpu, mode) (node_cpu_seconds_total{mode="idle"}) > 2
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High load average on {{ $labels.instance }}"
+          description: "15-minute load average is {{ $value | printf \"%.2f\" }} on {{ $labels.instance }}."
+
+  - name: cpu-alerts
+    interval: 30s
+    rules:
+      - alert: REDACTED_APP_PASSWORD
+        expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High CPU usage on {{ $labels.instance }}"
+          description: "CPU usage is {{ $value | printf \"%.1f\" }}% on {{ $labels.instance }}."
+
+      - alert: HostCriticalCpuUsage
+        expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 95
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "🔥 CRITICAL CPU on {{ $labels.instance }}"
+          description: "CPU usage is {{ $value | printf \"%.1f\" }}% on {{ $labels.instance }}. Immediate attention required!"
+
+  - name: memory-alerts
+    interval: 30s
+    rules:
+      - alert: HostHighMemoryUsage
+        expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 85
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High memory usage on {{ $labels.instance }}"
+          description: "Memory usage is {{ $value | printf \"%.1f\" }}% on {{ $labels.instance }}."
+
+      - alert: HostCriticalMemoryUsage
+        expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 95
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "🔥 CRITICAL Memory on {{ $labels.instance }}"
+          description: "Memory usage is {{ $value | printf \"%.1f\" }}% on {{ $labels.instance }}."
+
+      - alert: HostOutOfMemory
+        expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 5
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "💀 OUT OF MEMORY on {{ $labels.instance }}"
+          description: "Only {{ $value | printf \"%.1f\" }}% memory available on {{ $labels.instance }}."
+
+  - name: disk-alerts
+    interval: 60s
+    rules:
+      - alert: HostHighDiskUsage
+        expr: (1 - (node_filesystem_avail_bytes{fstype!~"tmpfs|overlay"} / node_filesystem_size_bytes{fstype!~"tmpfs|overlay"})) * 100 > 80
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Disk space warning on {{ $labels.instance }}"
+          description: "Disk {{ $labels.mountpoint }} is {{ $value | printf \"%.1f\" }}% full on {{ $labels.instance }}."
+
+      - alert: HostCriticalDiskUsage
+        expr: (1 - (node_filesystem_avail_bytes{fstype!~"tmpfs|overlay"} / node_filesystem_size_bytes{fstype!~"tmpfs|overlay"})) * 100 > 90
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "🔥 CRITICAL Disk space on {{ $labels.instance }}"
+          description: "Disk {{ $labels.mountpoint }} is {{ $value | printf \"%.1f\" }}% full on {{ $labels.instance }}."
+
+      - alert: HostDiskWillFillIn24Hours
+        expr: predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs|overlay"}[6h], 24*60*60) < 0
+        for: 30m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Disk {{ $labels.mountpoint }} will fill within 24 hours"
+          description: "Based on current growth rate, disk on {{ $labels.instance }} will be full within 24 hours."
+
+      - alert: REDACTED_APP_PASSWORD
+        expr: node_filesystem_readonly{fstype!~"tmpfs|overlay"} == 1
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "🔥 Filesystem is read-only on {{ $labels.instance }}"
+          description: "Filesystem {{ $labels.mountpoint }} has become read-only. This usually indicates disk failure!"
+
+  - name: network-alerts
+    interval: 30s
+    rules:
+      - alert: HostNetworkReceiveErrors
+        expr: rate(node_network_receive_errs_total{device!~"lo|veth.*|docker.*|br-.*"}[5m]) > 10
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Network receive errors on {{ $labels.instance }}"
+          description: "{{ $labels.device }} has {{ $value | printf \"%.0f\" }} receive errors/sec."
+
+      - alert: HostNetworkTransmitErrors
+        expr: rate(node_network_transmit_errs_total{device!~"lo|veth.*|docker.*|br-.*"}[5m]) > 10
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Network transmit errors on {{ $labels.instance }}"
+          description: "{{ $labels.device }} has {{ $value | printf \"%.0f\" }} transmit errors/sec."
+
+  - name: system-alerts
+    interval: 60s
+    rules:
+      - alert: HostClockSkew
+        expr: abs(node_timex_offset_seconds) > 0.5
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Clock skew detected on {{ $labels.instance }}"
+          description: "Clock is off by {{ $value | printf \"%.2f\" }} seconds."

alerting/alertmanager/alertmanager.yml

@@ -0,0 +1,49 @@
+# Alertmanager Configuration for Homelab
+# Routes alerts to both ntfy (via bridge) and Signal
+
+global:
+  resolve_timeout: 5m
+
+route:
+  group_by: ['alertname', 'severity', 'instance']
+  group_wait: 30s
+  group_interval: 5m
+  repeat_interval: 4h
+  receiver: 'ntfy-all'
+
+  routes:
+    # Critical alerts go to both Signal AND ntfy
+    - match:
+        severity: critical
+      receiver: 'critical-alerts'
+      continue: false
+
+    # Warning alerts go to ntfy only
+    - match:
+        severity: warning
+      receiver: 'ntfy-all'
+
+receivers:
+  # ntfy receiver for all alerts (via bridge for nice formatting)
+  - name: 'ntfy-all'
+    webhook_configs:
+      - url: 'http://ntfy-bridge:5001/alert'
+        send_resolved: true
+
+  # Critical alerts: Signal + ntfy
+  - name: 'critical-alerts'
+    webhook_configs:
+      # ntfy via bridge (formatted nicely)
+      - url: 'http://ntfy-bridge:5001/alert'
+        send_resolved: true
+
+      # Signal via bridge service
+      - url: 'http://signal-bridge:5000/alert'
+        send_resolved: true
+
+inhibit_rules:
+  - source_match:
+      severity: 'critical'
+    target_match:
+      severity: 'warning'
+    equal: ['alertname', 'instance']

alerting/docker-compose.alerting.yml

@@ -0,0 +1,68 @@
+# Alerting Stack for Homelab
+
+services:
+  alertmanager:
+    image: prom/alertmanager:latest
+    container_name: alertmanager
+    restart: unless-stopped
+    ports:
+      - "9093:9093"
+    volumes:
+      - ./alertmanager:/etc/alertmanager
+      - alertmanager-data:/alertmanager
+    command:
+      - '--config.file=/etc/alertmanager/alertmanager.yml'
+      - '--storage.path=/alertmanager'
+      - '--web.external-url=http://localhost:9093'
+    networks:
+      - monitoring-stack_default
+      - signal-api-stack_default
+      - ntfy-stack_default
+
+  signal-bridge:
+    build: ./signal-bridge
+    container_name: signal-bridge
+    restart: unless-stopped
+    ports:
+      - "5000:5000"
+    environment:
+      - SIGNAL_API_URL=http://signal-api:8080
+      - SIGNAL_SENDER=REDACTED_PHONE_NUMBER
+      - SIGNAL_RECIPIENTS=REDACTED_PHONE_NUMBER
+    networks:
+      - monitoring-stack_default
+      - signal-api-stack_default
+    healthcheck:
+      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:5000/health')"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+  ntfy-bridge:
+    build: ./ntfy-bridge
+    container_name: ntfy-bridge
+    restart: unless-stopped
+    ports:
+      - "5001:5001"
+    environment:
+      - NTFY_URL=http://NTFY:80
+      - NTFY_TOPIC="REDACTED_NTFY_TOPIC"
+    networks:
+      - monitoring-stack_default
+      - ntfy-stack_default
+    healthcheck:
+      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:5001/health')"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+volumes:
+  alertmanager-data:
+
+networks:
+  monitoring-stack_default:
+    external: true
+  signal-api-stack_default:
+    external: true
+  ntfy-stack_default:
+    external: true

alerting/ntfy-bridge/Dockerfile

@@ -0,0 +1,5 @@
+FROM python:3.11-slim
+WORKDIR /app
+RUN pip install --no-cache-dir flask requests gunicorn
+COPY app.py .
+CMD ["gunicorn", "--bind", "0.0.0.0:5001", "--workers", "2", "app:app"]

alerting/ntfy-bridge/app.py

@@ -0,0 +1,104 @@
+from flask import Flask, request, jsonify
+import requests
+import os
+
+app = Flask(__name__)
+
+NTFY_URL = os.environ.get('NTFY_URL', 'http://NTFY:80')
+NTFY_TOPIC = os.environ.get('NTFY_TOPIC', 'homelab-alerts')
+
+def get_status_icon(severity, status):
+    if status == 'resolved':
+        return 'white_check_mark'
+    if severity == 'critical':
+        return 'rotating_light'
+    return 'warning'
+
+def get_priority(severity, status):
+    if status == 'resolved':
+        return '3'
+    if severity == 'critical':
+        return '5'
+    return '4'
+
+def format_alert(alert):
+    status = alert.get('status', 'firing')
+    labels = alert.get('labels', {})
+    annotations = alert.get('annotations', {})
+
+    alertname = labels.get('alertname', 'Unknown Alert')
+    severity = labels.get('severity', 'warning')
+    instance = labels.get('instance', 'unknown')
+
+    status_text = 'RESOLVED' if status == 'resolved' else 'FIRING'
+    title = f"{alertname} [{status_text}]"
+
+    summary = annotations.get('summary', '')
+    description = annotations.get('description', '')
+
+    body_parts = []
+    if summary:
+        body_parts.append(summary)
+    if description and description != summary:
+        body_parts.append(description)
+    if instance and instance != 'unknown':
+        body_parts.append(f"Host: {instance}")
+
+    body = '\n'.join(body_parts) if body_parts else f"Alert {status_text.lower()} on {instance}"
+
+    return title, body, severity, status
+
+@app.route('/alert', methods=['POST'])
+def handle_alert():
+    try:
+        data = request.json
+        alerts = data.get('alerts', [])
+
+        for alert in alerts:
+            title, body, severity, status = format_alert(alert)
+            priority = get_priority(severity, status)
+            tag = get_status_icon(severity, status)
+
+            response = requests.post(
+                f"{NTFY_URL}/{NTFY_TOPIC}",
+                data=body,
+                headers={
+                    'Title': title,
+                    'Priority': priority,
+                    'Tags': tag
+                }
+            )
+
+            if response.status_code not in [200, 201]:
+                print(f"Failed to send to ntfy: {response.status_code} - {response.text}")
+
+        return jsonify({'status': 'sent', 'count': len(alerts)})
+    except Exception as e:
+        print(f"Error: {e}")
+        return jsonify({'status': 'error', 'message': str(e)}), 500
+
+@app.route('/health', methods=['GET'])
+def health():
+    return jsonify({'status': 'healthy'})
+
+@app.route('/test', methods=['POST'])
+def test():
+    try:
+        data = request.json or {}
+        message = data.get('message', 'Test notification from ntfy-bridge')
+
+        response = requests.post(
+            f"{NTFY_URL}/{NTFY_TOPIC}",
+            data=message,
+            headers={
+                'Title': 'Test Alert',
+                'Priority': '4',
+                'Tags': 'test_tube'
+            }
+        )
+        return jsonify({'status': 'sent'})
+    except Exception as e:
+        return jsonify({'status': 'error', 'message': str(e)}), 500
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5001)

alerting/signal-bridge/Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+RUN pip install --no-cache-dir flask requests gunicorn
+
+COPY app.py .
+
+EXPOSE 5000
+
+CMD ["gunicorn", "--bind", "0.0.0.0:5000", "--workers", "2", "--timeout", "60", "app:app"]

alerting/signal-bridge/app.py

@@ -0,0 +1,130 @@
+#!/usr/bin/env python3
+"""
+Signal Bridge for Alertmanager
+Receives webhooks from Alertmanager and forwards to Signal API
+"""
+
+import os
+import json
+import requests
+from flask import Flask, request, jsonify
+
+app = Flask(__name__)
+
+# Configuration from environment variables
+SIGNAL_API_URL = os.environ.get('SIGNAL_API_URL', 'http://signal-api:8080')
+SIGNAL_SENDER = os.environ.get('SIGNAL_SENDER', '')  # Your Signal number
+SIGNAL_RECIPIENTS = os.environ.get('SIGNAL_RECIPIENTS', '').split(',')  # Comma-separated
+
+def format_alert_message(alert_data):
+    """Format Alertmanager webhook payload into a readable message"""
+    messages = []
+
+    status = alert_data.get('status', 'unknown')
+
+    for alert in alert_data.get('alerts', []):
+        alert_status = alert.get('status', status)
+        labels = alert.get('labels', {})
+        annotations = alert.get('annotations', {})
+
+        severity = labels.get('severity', 'unknown')
+        alertname = labels.get('alertname', 'Unknown Alert')
+        instance = labels.get('instance', 'unknown')
+
+        summary = annotations.get('summary', alertname)
+        description = annotations.get('description', '')
+
+        # Status emoji
+        if alert_status == 'resolved':
+            status_emoji = '✅'
+            status_text = 'RESOLVED'
+        elif severity == 'critical':
+            status_emoji = '🚨'
+            status_text = 'CRITICAL'
+        else:
+            status_emoji = '⚠️'
+            status_text = 'WARNING'
+
+        msg = f"{status_emoji} [{status_text}] {summary}"
+        if description:
+            msg += f"\n{description}"
+
+        messages.append(msg)
+
+    return "\n\n".join(messages)
+
+def send_signal_message(message):
+    """Send message via Signal API"""
+    if not SIGNAL_SENDER or not SIGNAL_RECIPIENTS:
+        app.logger.error("Signal sender or recipients not configured")
+        return False
+
+    success = True
+    for recipient in SIGNAL_RECIPIENTS:
+        recipient = recipient.strip()
+        if not recipient:
+            continue
+
+        try:
+            payload = {
+                "message": message,
+                "number": SIGNAL_SENDER,
+                "recipients": [recipient]
+            }
+
+            response = requests.post(
+                f"{SIGNAL_API_URL}/v2/send",
+                json=payload,
+                timeout=30
+            )
+
+            if response.status_code in [200, 201]:
+                app.logger.info(f"Message sent to {recipient}")
+            else:
+                app.logger.error(f"Failed to send to {recipient}: {response.status_code} - {response.text}")
+                success = False
+
+        except Exception as e:
+            app.logger.error(f"Error sending to {recipient}: {e}")
+            success = False
+
+    return success
+
+@app.route('/health', methods=['GET'])
+def health():
+    return jsonify({"status": "healthy"}), 200
+
+@app.route('/alert', methods=['POST'])
+def receive_alert():
+    """Receive alert from Alertmanager and forward to Signal"""
+    try:
+        alert_data = request.get_json()
+
+        if not alert_data:
+            return jsonify({"error": "No data received"}), 400
+
+        app.logger.info(f"Received alert: {json.dumps(alert_data, indent=2)}")
+
+        message = format_alert_message(alert_data)
+
+        if send_signal_message(message):
+            return jsonify({"status": "sent"}), 200
+        else:
+            return jsonify({"status": "partial_failure"}), 207
+
+    except Exception as e:
+        app.logger.error(f"Error processing alert: {e}")
+        return jsonify({"error": str(e)}), 500
+
+@app.route('/test', methods=['POST'])
+def test_message():
+    """Send a test message"""
+    message = request.json.get('message', '🧪 Test alert from Signal Bridge')
+
+    if send_signal_message(message):
+        return jsonify({"status": "sent"}), 200
+    else:
+        return jsonify({"status": "failed"}), 500
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5000)