claude-flow-novice/monitoring/alerts/resource-alerts.yml

Claude Flow Novice - Advanced orchestration platform for multi-agent AI workflows with CFN Loop architecture Includes Local RuVector Accelerator and all CFN skills for complete functionality.

groups:
  - name: resource_alerts
    interval: 30s
    rules:
      - alert: HighCPUUsage
        expr: |
          (sum(rate(process_cpu_seconds_total[5m])) / count(process_cpu_seconds_total) * 100) > 80
        for: 10m
        labels:
          severity: warning
          resource: cpu
        annotations:
          summary: "High CPU usage detected"
          description: "Average CPU usage is {{ $value | humanize }}% (threshold: 80%)"

      - alert: CriticalCPUUsage
        expr: |
          (sum(rate(process_cpu_seconds_total[5m])) / count(process_cpu_seconds_total) * 100) > 90
        for: 5m
        labels:
          severity: critical
          resource: cpu
        annotations:
          summary: "Critical CPU usage"
          description: "Average CPU usage is {{ $value | humanize }}%"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: HighMemoryUsage
        expr: |
          (sum(process_resident_memory_bytes) / sum(node_memory_MemTotal_bytes) * 100) > 85
        for: 10m
        labels:
          severity: warning
          resource: memory
        annotations:
          summary: "High memory usage detected"
          description: "Memory usage is {{ $value | humanize }}% (threshold: 85%)"

      - alert: CriticalMemoryUsage
        expr: |
          (sum(process_resident_memory_bytes) / sum(node_memory_MemTotal_bytes) * 100) > 95
        for: 5m
        labels:
          severity: critical
          resource: memory
        annotations:
          summary: "Critical memory usage"
          description: "Memory usage is {{ $value | humanize }}%"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: HighDiskUsage
        expr: |
          (node_filesystem_avail_bytes / node_filesystem_size_bytes * 100) < 15
        for: 15m
        labels:
          severity: warning
          resource: disk
        annotations:
          summary: "Low disk space"
          description: "Available disk space is {{ $value | humanize }}% (threshold: 15%)"

      - alert: CriticalDiskSpace
        expr: |
          (node_filesystem_avail_bytes / node_filesystem_size_bytes * 100) < 5
        for: 5m
        labels:
          severity: critical
          resource: disk
        annotations:
          summary: "Critical disk space condition"
          description: "Available disk space is {{ $value | humanize }}%"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: HighDiskIOUsage
        expr: |
          (rate(node_disk_io_time_seconds_total[5m]) / on(device) rate(node_disk_io_time_ms_total[5m])) > 0.8
        for: 10m
        labels:
          severity: warning
          resource: disk_io
        annotations:
          summary: "High disk I/O utilization"
          description: "Disk I/O utilization is {{ $value | humanizePercentage }}"

      - alert: HighNetworkBandwidth
        expr: |
          sum(rate(node_network_transmit_bytes_total[5m]) + rate(node_network_receive_bytes_total[5m])) > 1000000000
        for: 10m
        labels:
          severity: warning
          resource: network
        annotations:
          summary: "High network bandwidth usage"
          description: "Network bandwidth is {{ $value | humanize }} bytes/sec"

      - alert: DatabaseConnectionPoolExhaustion
        expr: |
          (pg_stat_activity_count / pg_settings_max_connections) > 0.85
        for: 5m
        labels:
          severity: critical
          component: database
        annotations:
          summary: "Database connection pool near exhaustion"
          description: "{{ $value | humanizePercentage }} of connections in use"
          runbook_url: "docs/ROLLBACK_RUNBOOK.md"

      - alert: RedisMemoryUsageHigh
        expr: |
          (redis_memory_used_bytes / redis_memory_max_bytes) > 0.8
        for: 10m
        labels:
          severity: warning
          component: redis
        annotations:
          summary: "Redis memory usage high"
          description: "Redis memory usage is {{ $value | humanizePercentage }}"

      - alert: NodeOutOfMemory
        expr: |
          (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) < 0.05
        for: 5m
        labels:
          severity: critical
          resource: memory
        annotations:
          summary: "Node running out of memory"
          description: "Available memory is {{ $value | humanizePercentage }}"
          runbook_url: "docs/INCIDENT_RESPONSE.md"

      - alert: FileDescriptorExhaustion
        expr: |
          (process_open_fds / process_max_fds) > 0.85
        for: 10m
        labels:
          severity: warning
          resource: file_descriptors
        annotations:
          summary: "File descriptor limit near exhaustion"
          description: "{{ $value | humanizePercentage }} of file descriptors in use"

      - alert: TemporaryStorageUsage
        expr: |
          (node_filesystem_avail_bytes{fstype="tmpfs"} / node_filesystem_size_bytes{fstype="tmpfs"}) < 0.1
        for: 10m
        labels:
          severity: warning
          resource: tmp_storage
        annotations:
          summary: "Temporary storage usage high"
          description: "Temporary storage available: {{ $value | humanizePercentage }}"

      - alert: DatabaseDiskSpaceUsage
        expr: |
          (pg_database_size_bytes / node_filesystem_size_bytes) > 0.7
        for: 15m
        labels:
          severity: warning
          component: database
        annotations:
          summary: "Database disk usage growing"
          description: "Database size is {{ $value | humanizePercentage }} of available space"