groups:
- name: EKS-Node-Alerts
  rules:
  - alert: Kubernetes-Node-Not-Ready-Generic
    expr: kube_node_status_condition{job=~'kube-state-metrics-p-.*', condition='Ready', status='true'} == 0
    for: 6m
    labels:
      severity: critical
      bu: infra
      team: devops
      service: eks-node-not-ready-generic
      env: prd
      priority: p0
    annotations:
      summary: URGENT - Kubernetes Node not ready (instance {{ $labels.instance }})
      description: "Node {{ $labels.node }} has been unready for a long time\n LABELS = {{ $labels }}"

  - alert: Kubernetes-Node-Not-Ready-NetworkUnavailable
    expr: kube_node_status_condition{job=~'kube-state-metrics-p-.*', condition='NetworkUnavailable', status='true'} == 1
    for: 1m
    labels:
      severity: critical
      bu: infra
      team: devops
      service: eks-node-not-ready-networkunavailable
      env: prd
      priority: p0
    annotations:
      summary: URGENT - Kubernetes Node not ready due to NetworkUnavailable (instance {{ $labels.instance }})
      description: "Node {{ $labels.node }} has been unready due to NetworkUnavailable for a long time\n LABELS = {{ $labels }}"

  - alert: Kubernetes-Node-Not-Ready-MemoryPressure
    expr: kube_node_status_condition{job=~'kube-state-metrics-p-.*', condition="MemoryPressure", status="true"} == 1
    for: 5m
    labels:
      severity: critical
      bu: infra
      team: devops
      service: eks-node-not-ready-memorypressure
      env: prd
      priority: p0
    annotations:
      summary: URGENT - Kubernetes Node not ready due to MemoryPressure (instance {{ $labels.instance }})
      description: "{{ $labels.node }} has been unready due to MemoryPressure for a long time\n  LABELS = {{ $labels }}"

  - alert: Kubernetes-Node-Not-Ready-DiskPressure
    expr: kube_node_status_condition{job=~'kube-state-metrics-p-.*', condition="DiskPressure", status="true"} == 1
    for: 1m
    labels:
      severity: critical
      bu: infra
      team: devops
      service: eks-node-not-ready-diskpressure
      env: prd
      priority: p0
    annotations:
      summary: URGENT - Kubernetes Node not ready due to DiskPressure (instance {{ $labels.instance }})
      description: "{{ $labels.node }} has been unready due to DiskPressure for a long time\n  LABELS = {{ $labels }}"

  - alert: Kubernetes-Node-DiskSpace-Crossed-Threshold
    expr: 100 - ((node_filesystem_avail_bytes{mountpoint="/",fstype!="rootfs", job=~"node_exporter_eks"} * 100) / node_filesystem_size_bytes{mountpoint="/",fstype!="rootfs", job=~"node_exporter_eks"}) > 85
    for: 2m
    labels:
      severity: critical
      bu: infra
      team: devops
      service: eks-node-diskspace-alert
      env: prd
      priority: p0
    annotations:
      summary: Kubernetes Node running out of Disk Space (instance {{ $labels.private_ip }})
      description: "{{ $labels.name }}/{{ $labels.private_ip }} is running out of Disk Space\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"