uploader-bot/monitoring/alert_rules.yml

# Alert rules for my-uploader-bot monitoring

groups:
  - name: application_alerts
    interval: 30s
    rules:
      # Application availability
      - alert: ApplicationDown
        expr: up{job="my-uploader-bot"} == 0
        for: 1m
        labels:
          severity: critical
          service: my-uploader-bot
        annotations:
          summary: "Application instance {{ $labels.instance }} is down"
          description: "My-uploader-bot application has been down for more than 1 minute"

      # High error rate
      - alert: HighErrorRate
        expr: rate(http_requests_total{status=~"5.."}[5m]) / rate(http_requests_total[5m]) > 0.1
        for: 5m
        labels:
          severity: warning
          service: my-uploader-bot
        annotations:
          summary: "High error rate detected"
          description: "Error rate is {{ $value | humanizePercentage }} for the last 5 minutes"

      # High response time
      - alert: HighResponseTime
        expr: histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m])) > 2.0
        for: 5m
        labels:
          severity: warning
          service: my-uploader-bot
        annotations:
          summary: "High response time detected"
          description: "95th percentile response time is {{ $value }}s for the last 5 minutes"

      # High memory usage
      - alert: HighMemoryUsage
        expr: (process_resident_memory_bytes / 1024 / 1024 / 1024) > 2.0
        for: 10m
        labels:
          severity: warning
          service: my-uploader-bot
        annotations:
          summary: "High memory usage detected"
          description: "Memory usage is {{ $value | humanize }}GB"

      # High CPU usage
      - alert: HighCPUUsage
        expr: rate(process_cpu_seconds_total[5m]) * 100 > 80
        for: 10m
        labels:
          severity: warning
          service: my-uploader-bot
        annotations:
          summary: "High CPU usage detected"
          description: "CPU usage is {{ $value | humanizePercentage }}"

  - name: database_alerts
    interval: 30s
    rules:
      # Database down
      - alert: PostgreSQLDown
        expr: up{job="postgres"} == 0
        for: 1m
        labels:
          severity: critical
          service: postgresql
        annotations:
          summary: "PostgreSQL instance {{ $labels.instance }} is down"
          description: "PostgreSQL database has been down for more than 1 minute"

      # High database connections
      - alert: HighDatabaseConnections
        expr: pg_stat_database_numbackends / pg_settings_max_connections > 0.8
        for: 5m
        labels:
          severity: warning
          service: postgresql
        annotations:
          summary: "High database connection usage"
          description: "Database connection usage is {{ $value | humanizePercentage }}"

      # Slow queries
      - alert: SlowQueries
        expr: pg_stat_activity_max_tx_duration > 300
        for: 5m
        labels:
          severity: warning
          service: postgresql
        annotations:
          summary: "Slow database queries detected"
          description: "Longest running query is {{ $value }}s"

      # Replication lag
      - alert: ReplicationLag
        expr: pg_replication_lag > 60
        for: 5m
        labels:
          severity: warning
          service: postgresql
        annotations:
          summary: "High replication lag"
          description: "Replication lag is {{ $value }}s"

  - name: cache_alerts
    interval: 30s
    rules:
      # Redis down
      - alert: RedisDown
        expr: up{job="redis"} == 0
        for: 1m
        labels:
          severity: critical
          service: redis
        annotations:
          summary: "Redis instance {{ $labels.instance }} is down"
          description: "Redis cache has been down for more than 1 minute"

      # High memory usage
      - alert: RedisHighMemoryUsage
        expr: redis_memory_used_bytes / redis_memory_max_bytes > 0.9
        for: 5m
        labels:
          severity: warning
          service: redis
        annotations:
          summary: "Redis high memory usage"
          description: "Redis memory usage is {{ $value | humanizePercentage }}"

      # High hit rate drop
      - alert: RedisCacheHitRateDrop
        expr: rate(redis_keyspace_hits_total[5m]) / (rate(redis_keyspace_hits_total[5m]) + rate(redis_keyspace_misses_total[5m])) < 0.8
        for: 10m
        labels:
          severity: warning
          service: redis
        annotations:
          summary: "Redis cache hit rate dropped"
          description: "Cache hit rate is {{ $value | humanizePercentage }}"

  - name: system_alerts
    interval: 30s
    rules:
      # High disk usage
      - alert: HighDiskUsage
        expr: (node_filesystem_size_bytes - node_filesystem_avail_bytes) / node_filesystem_size_bytes > 0.85
        for: 5m
        labels:
          severity: warning
          service: system
        annotations:
          summary: "High disk usage on {{ $labels.mountpoint }}"
          description: "Disk usage is {{ $value | humanizePercentage }}"

      # High memory usage
      - alert: HighSystemMemoryUsage
        expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes > 0.9
        for: 5m
        labels:
          severity: warning
          service: system
        annotations:
          summary: "High system memory usage"
          description: "System memory usage is {{ $value | humanizePercentage }}"

      # High load average
      - alert: HighLoadAverage
        expr: node_load15 / count without (cpu, mode) (node_cpu_seconds_total{mode="idle"}) > 2.0
        for: 10m
        labels:
          severity: warning
          service: system
        annotations:
          summary: "High system load"
          description: "15-minute load average is {{ $value }}"

  - name: storage_alerts
    interval: 60s
    rules:
      # High upload queue
      - alert: HighUploadQueue
        expr: upload_queue_size > 100
        for: 5m
        labels:
          severity: warning
          service: storage
        annotations:
          summary: "High upload queue size"
          description: "Upload queue has {{ $value }} pending items"

      # Failed uploads
      - alert: HighFailedUploads
        expr: rate(upload_failures_total[10m]) > 0.1
        for: 5m
        labels:
          severity: warning
          service: storage
        annotations:
          summary: "High upload failure rate"
          description: "Upload failure rate is {{ $value }}/min"

      # Storage space
      - alert: LowStorageSpace
        expr: storage_available_bytes / storage_total_bytes < 0.1
        for: 5m
        labels:
          severity: critical
          service: storage
        annotations:
          summary: "Low storage space"
          description: "Available storage is {{ $value | humanizePercentage }}"

  - name: blockchain_alerts
    interval: 60s
    rules:
      # TON service down
      - alert: TONServiceDown
        expr: ton_service_up == 0
        for: 2m
        labels:
          severity: critical
          service: blockchain
        annotations:
          summary: "TON service is down"
          description: "TON blockchain service has been unavailable for more than 2 minutes"

      # High transaction failures
      - alert: HighTransactionFailures
        expr: rate(blockchain_transaction_failures_total[10m]) > 0.05
        for: 5m
        labels:
          severity: warning
          service: blockchain
        annotations:
          summary: "High blockchain transaction failure rate"
          description: "Transaction failure rate is {{ $value }}/min"

      # Pending transactions
      - alert: HighPendingTransactions
        expr: blockchain_pending_transactions > 50
        for: 10m
        labels:
          severity: warning
          service: blockchain
        annotations:
          summary: "High number of pending transactions"
          description: "{{ $value }} transactions are pending for more than 10 minutes"

  - name: security_alerts
    interval: 30s
    rules:
      # High login failures
      - alert: HighLoginFailures
        expr: rate(auth_login_failures_total[5m]) > 0.1
        for: 5m
        labels:
          severity: warning
          service: security
        annotations:
          summary: "High login failure rate"
          description: "Login failure rate is {{ $value }}/min"

      # Rate limit hits
      - alert: HighRateLimitHits
        expr: rate(rate_limit_hits_total[5m]) > 10
        for: 5m
        labels:
          severity: warning
          service: security
        annotations:
          summary: "High rate limit hits"
          description: "Rate limit hit rate is {{ $value }}/min"

      # Suspicious activity
      - alert: SuspiciousActivity
        expr: security_suspicious_events > 5
        for: 1m
        labels:
          severity: critical
          service: security
        annotations:
          summary: "Suspicious security activity detected"
          description: "{{ $value }} suspicious events detected in the last minute"