Server Monitoring

# View live metrics via CLI
deployerp server monitor srv_abc123 --live

# Output
┌─────────────────────────────────────────────┐
│ Server: production-eu-1                     │
│ Status: Running | Uptime: 45d 12h 30m       │
├─────────────────────────────────────────────┤
│ CPU:    [████████░░░░░░░░░░] 42.5%         │
│ Memory: [██████████████░░░░] 73.2% (11.7GB)│
│ Disk:   [████████████░░░░░░] 61.0% (195GB) │
│ Network: ↓ 125 Mbps ↑ 45 Mbps              │
└─────────────────────────────────────────────┘

# High CPU usage
- name: "High CPU Usage"
  metric: system.cpu.usage
  condition: ">"
  threshold: 85
  duration: 5m
  severity: warning

# Memory pressure
- name: "Memory Pressure"
  metric: system.memory.usage
  condition: ">"
  threshold: 90
  duration: 3m
  severity: critical

# Disk space low
- name: "Low Disk Space"
  metric: system.disk.usage
  condition: ">"
  threshold: 85
  duration: 10m
  severity: warning

# Database connections
- name: "Database Connection Pool"
  metric: postgresql.connections.active
  condition: ">"
  threshold: 80
  duration: 2m
  severity: warning

# Response time
- name: "Slow Response Time"
  metric: odoo.http.response_time
  condition: ">"
  threshold: 1000  # milliseconds
  duration: 5m
  severity: warning

{
  "channel": "email",
  "addresses": ["[email protected]", "[email protected]"],
  "settings": {
    "include_graphs": true,
    "include_logs": false,
    "batch_window": "5m"
  }
}

{
  "channel": "slack",
  "webhook_url": "https://hooks.slack.com/services/xxx",
  "settings": {
    "channel": "#alerts",
    "username": "deployERP Bot",
    "icon_emoji": ":warning:",
    "mention_users": ["@oncall"]
  }
}

{
  "channel": "webhook",
  "url": "https://your-app.com/webhooks/alerts",
  "method": "POST",
  "headers": {
    "Authorization": "Bearer YOUR_TOKEN"
  },
  "retry": {
    "attempts": 3,
    "backoff": "exponential"
  }
}

-- Top slow queries
SELECT 
  query,
  calls,
  mean_time,
  total_time
FROM pg_stat_statements
ORDER BY mean_time DESC
LIMIT 10;

-- Connection statistics
SELECT 
  datname,
  numbackends,
  xact_commit,
  xact_rollback
FROM pg_stat_database;

auto_healing:
  enabled: true
  
  rules:
    - name: "Restart on crash"
      trigger: service_down
      action: restart_service
      max_attempts: 3
      cooldown: 5m
    
    - name: "Memory cleanup"
      trigger: memory_usage > 85%
      actions:
        - clear_cache
        - restart_workers
      cooldown: 15m
    
    - name: "Disk cleanup"
      trigger: disk_usage > 80%
      actions:
        - rotate_logs
        - clean_temp_files
      cooldown: 1h

# Search Odoo logs
deployerp logs search --instance=production --query="ERROR" --last=1h

# Tail logs in real-time
deployerp logs tail --instance=production --filter="sale.order"

# Export logs
deployerp logs export --instance=production --from=2024-01-01 --to=2024-01-15

# Custom metric example
{
  "name": "daily_orders",
  "type": "gauge",
  "query": "SELECT COUNT(*) FROM sale_order WHERE date >= CURRENT_DATE",
  "interval": "5m",
  "labels": {
    "app": "odoo",
    "module": "sales"
  }
}

# Check agent status
systemctl status deployerp-agent

# Test metric collection
deployerp-agent test

# Verify connectivity
deployerp-agent ping

# Debug mode
deployerp-agent run --debug