Alerting for AWS ENA metrics

alert.rules

 - alert: Bandwidth_In_Allowance_Exceeded
    expr: increase(node_ethtool_bw_in_allowance_exceeded{cluster=“my-cluster”}[10m]) > 30000
    for: 10m
    labels:
      severity: warning
    annotations:
      summary: "Instance {{ $labels.instance }} bandwidth-in exceeded"
      description: "Instance {{ $labels.instance }} from {{ $labels.cluster }} has a bandwidth in allowwance greater than {{ $value }}"

  - alert: Bandwidth_Out_Allowance_Exceeded
    expr: increase(node_ethtool_bw_out_allowance_exceeded{cluster=“my-cluster”}[10m]) > 30000
    for: 10m
    labels:
      severity: warning
    annotations:
      summary: "Instance {{ $labels.instance }} bandwith-out traffic exceeded"
      description: "Instance {{ $labels.instance }} from {{ $labels.cluster }} has a bandwidth out allowance greater than {{ $value }}"

  - alert: Pps_Allowance_Exceeded
    expr: sum(node_ethtool_pps_allowance_exceeded{cluster=“my-cluster”} ) by (instance) > 500
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Instance {{ $labels.instance }} (PPS) allowance exceeded"
      description: "Packet Per Second (PPS) allowance for instance {{ $labels.instance }} is greater than 500"