bladex/script/docker/app/prometheus/config/alert_rules.yml

groups:
  - name: alert_rules
    rules:
      - alert: CpuUsageAlertWarning
        expr: sum(avg(irate(node_cpu_seconds_total{mode!='idle'}[5m])) without (cpu)) by (instance) > 0.60
        for: 2m
        labels:
          level: warning
        annotations:
          summary: "Instance {{ $labels.instance }} CPU usage high"
          description: "{{ $labels.instance }} CPU usage above 60% (current value: {{ $value }})"
      - alert: CpuUsageAlertSerious
        #expr: sum(avg(irate(node_cpu_seconds_total{mode!='idle'}[5m])) without (cpu)) by (instance) > 0.85
        expr: (100 - (avg by (instance) (irate(node_cpu_seconds_total{job=~".*",mode="idle"}[5m])) * 100)) > 85
        for: 3m
        labels:
          level: serious
        annotations:
          summary: "Instance {{ $labels.instance }} CPU usage high"
          description: "{{ $labels.instance }} CPU usage above 85% (current value: {{ $value }})"
      - alert: MemUsageAlertWarning
        expr: avg by(instance) ((1 - (node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes) / node_memory_MemTotal_bytes) * 100) > 70
        for: 2m
        labels:
          level: warning
        annotations:
          summary: "Instance {{ $labels.instance }} MEM usage high"
          description: "{{$labels.instance}}: MEM usage is above 70% (current value is: {{ $value }})"
      - alert: MemUsageAlertSerious
        expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)/node_memory_MemTotal_bytes > 0.90
        for: 3m
        labels:
          level: serious
        annotations:
          summary: "Instance {{ $labels.instance }} MEM usage high"
          description: "{{ $labels.instance }} MEM usage above 90% (current value: {{ $value }})"
      - alert: DiskUsageAlertWarning
        expr: (1 - node_filesystem_free_bytes{fstype!="rootfs",mountpoint!="",mountpoint!~"/(run|var|sys|dev).*"} / node_filesystem_size_bytes) * 100 > 80
        for: 2m
        labels:
          level: warning
        annotations:
          summary: "Instance {{ $labels.instance }} Disk usage high"
          description: "{{$labels.instance}}: Disk usage is above 80% (current value is: {{ $value }})"
      - alert: DiskUsageAlertSerious
        expr: (1 - node_filesystem_free_bytes{fstype!="rootfs",mountpoint!="",mountpoint!~"/(run|var|sys|dev).*"} / node_filesystem_size_bytes) * 100 > 90
        for: 3m
        labels:
          level: serious
        annotations:
          summary: "Instance {{ $labels.instance }} Disk usage high"
          description: "{{$labels.instance}}: Disk usage is above 90% (current value is: {{ $value }})"
      - alert: NodeFileDescriptorUsage
        expr: avg by (instance) (node_filefd_allocated{} / node_filefd_maximum{}) * 100 > 60
        for: 2m
        labels:
          level: warning
        annotations:
          summary: "Instance {{ $labels.instance }} File Descriptor usage high"
          description: "{{$labels.instance}}: File Descriptor usage is above 60% (current value is: {{ $value }})"
      - alert: NodeLoad15
        expr: avg by (instance) (node_load15{}) > 80
        for: 2m
        labels:
          level: warning
        annotations:
          summary: "Instance {{ $labels.instance }} Load15 usage high"
          description: "{{$labels.instance}}: Load15 is above 80 (current value is: {{ $value }})"
      - alert: NodeAgentStatus
        expr: avg by (instance) (up{}) == 0
        for: 2m
        labels:
          level: warning
        annotations:
          summary: "{{$labels.instance}}: has been down"
          description: "{{$labels.instance}}: Node_Exporter Agent is down (current value is: {{ $value }})"
      - alert: NodeProcsBlocked
        expr: avg by (instance) (node_procs_blocked{}) > 10
        for: 2m
        labels:
          level: warning
        annotations:
          summary: "Instance {{ $labels.instance }}  Process Blocked usage high"
          description: "{{$labels.instance}}: Node Blocked Procs detected! above 10 (current value is: {{ $value }})"
      - alert: NetworkTransmitRate
        #expr:  avg by (instance) (floor(irate(node_network_transmit_bytes_total{device="ens192"}[2m]) / 1024 / 1024)) > 50
        expr: avg by (instance) (floor(irate(node_network_transmit_bytes_total{}[2m]) / 1024 / 1024 * 8 )) > 40
        for: 1m
        labels:
          level: warning
        annotations:
          summary: "Instance {{ $labels.instance }} Network Transmit Rate usage high"
          description: "{{$labels.instance}}: Node Transmit Rate (Upload) is above 40Mbps/s (current value is: {{ $value }}Mbps/s)"
      - alert: NetworkReceiveRate
        #expr:  avg by (instance) (floor(irate(node_network_receive_bytes_total{device="ens192"}[2m]) / 1024 / 1024)) > 50
        expr: avg by (instance) (floor(irate(node_network_receive_bytes_total{}[2m]) / 1024 / 1024 * 8 )) > 40
        for: 1m
        labels:
          level: warning
        annotations:
          summary: "Instance {{ $labels.instance }} Network Receive Rate usage high"
          description: "{{$labels.instance}}: Node Receive Rate (Download) is above 40Mbps/s (current value is: {{ $value }}Mbps/s)"
      - alert: DiskReadRate
        expr: avg by (instance) (floor(irate(node_disk_read_bytes_total{}[2m]) / 1024 )) > 200
        for: 2m
        labels:
          level: warning
        annotations:
          summary: "Instance {{ $labels.instance }} Disk Read Rate usage high"
          description: "{{$labels.instance}}: Node Disk Read Rate is above 200KB/s (current value is: {{ $value }}KB/s)"
      - alert: DiskWriteRate
        expr: avg by (instance) (floor(irate(node_disk_written_bytes_total{}[2m]) / 1024 / 1024 )) > 20
        for: 2m
        labels:
          level: warning
        annotations:
          summary: "Instance {{ $labels.instance }} Disk Write Rate usage high"
          description: "{{$labels.instance}}: Node Disk Write Rate is above 20MB/s (current value is: {{ $value }}MB/s)"