{{- if (.Capabilities.APIVersions.Has "monitoring.coreos.com/v1/PrometheusRule") }}
---
apiVersion: "monitoring.coreos.com/v1"
kind: "PrometheusRule"
metadata:
  name: prometheus-node-exporter
  labels:
    {{- toYaml .Values.commons.prometheus.rules.labels | nindent 4 }}
spec:
  groups:
    - name: "Node disk rate"
      rules:
        - alert: HostUnusualDiskReadRate
          expr: '(sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
          for: "5m"
          labels:
            severity: "warning"
            detectedBy: "NodeExporter"
          annotations:
            {{`
            summary: "Host unusual disk read rate (instance {{ $labels.instance }})"
            description: "Disk is probably reading too much data (> 50 MB/s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
            `}}

        - alert: HostUnusualDiskWriteRate
          expr: '(sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'
          for: "2m"
          labels:
            severity: "warning"
            detectedBy: "NodeExporter"
          annotations:
            {{`
            summary: "Host unusual disk write rate (instance {{ $labels.instance }})"
            description: "Disk is probably writing too much data (> 50 MB/s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
            `}}
      
    - name: "ZFS"
      rules:
        - alert: ZFSOfflinePool
          expr: 'node_zfs_zpool_state{state!="online"} > 0'
          for: "1m"
          labels:
            severity: "critical"
            detectedBy: "NodeExporter"
          annotations:
            {{`
            summary: "ZFS offline pool (instance {{ $labels.instance }})"
            description: "A ZFS zpool is in a unexpected state: {{ $labels.state }}.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
            `}}

    - name: "Hardware Temperature"
      rules:
        - alert: HostPhysicalComponentTooHot
          expr: 'avg(node_hwmon_temp_crit_alarm_celsius * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}) without(container,endpoint,instance,pod,service,namespace,job) > 0'
          for: "0m"
          labels:
            severity: "critical"
            detectedBy: "NodeExporter"
          annotations:
            {{`
            summary: Host node overtemperature alarm (node {{ $labels.nodename }})
            description: "Physical node temperature alarm triggered\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
            `}}
        - alert: HostPhysicalComponentTooHot
          expr: 'avg((node_hwmon_temp_celsius > node_hwmon_temp_max_celsius) * ignoring(label) group_left(instance,chip,sensor) node_hwmon_sensor_label{} * on(instance) group_left (nodename) node_uname_info{nodename=~".+"} ) without(container,endpoint,instance,pod,service,namespace,job)'
          for: "5m"
          labels:
            severity: "warning"
            detectedBy: "NodeExporter"
          annotations:
            {{`
            summary: Host physical component too hot (node {{ $labels.nodename }})
            description: "Physical hardware component too hot\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
            `}}
{{- end }}