rancher-charts/charts/rancher-monitoring/9.4.202/templates/prometheus/rules-1.14/node-exporter.yaml

{{- /*
Generated from 'node-exporter' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }}
{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.nodeExporter.enabled .Values.defaultRules.rules.node }}
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "node-exporter" | trunc 63 | trimSuffix "-" }}
  namespace: {{ template "kube-prometheus-stack.namespace" . }}
  labels:
    app: {{ template "kube-prometheus-stack.name" . }}
{{ include "kube-prometheus-stack.labels" . | indent 4 }}
{{- if .Values.defaultRules.labels }}
{{ toYaml .Values.defaultRules.labels | indent 4 }}
{{- end }}
{{- if .Values.defaultRules.annotations }}
  annotations:
{{ toYaml .Values.defaultRules.annotations | indent 4 }}
{{- end }}
spec:
  groups:
  - name: node-exporter
    rules:
    - alert: NodeFilesystemSpaceFillingUp
      annotations:
        description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left and is filling up.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemspacefillingup
        summary: Filesystem is predicted to run out of space within the next 24 hours.
      expr: |-
        (
          node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 40
        and
          predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: warning
    - alert: NodeFilesystemSpaceFillingUp
      annotations:
        description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left and is filling up fast.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemspacefillingup
        summary: Filesystem is predicted to run out of space within the next 4 hours.
      expr: |-
        (
          node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 15
        and
          predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: critical
    - alert: NodeFilesystemAlmostOutOfSpace
      annotations:
        description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemalmostoutofspace
        summary: Filesystem has less than 5% space left.
      expr: |-
        (
          node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 5
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: warning
    - alert: NodeFilesystemAlmostOutOfSpace
      annotations:
        description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemalmostoutofspace
        summary: Filesystem has less than 3% space left.
      expr: |-
        (
          node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 3
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: critical
    - alert: NodeFilesystemFilesFillingUp
      annotations:
        description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left and is filling up.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemfilesfillingup
        summary: Filesystem is predicted to run out of inodes within the next 24 hours.
      expr: |-
        (
          node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 40
        and
          predict_linear(node_filesystem_files_free{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: warning
    - alert: NodeFilesystemFilesFillingUp
      annotations:
        description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left and is filling up fast.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemfilesfillingup
        summary: Filesystem is predicted to run out of inodes within the next 4 hours.
      expr: |-
        (
          node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 20
        and
          predict_linear(node_filesystem_files_free{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: critical
    - alert: NodeFilesystemAlmostOutOfFiles
      annotations:
        description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemalmostoutoffiles
        summary: Filesystem has less than 5% inodes left.
      expr: |-
        (
          node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 5
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: warning
    - alert: NodeFilesystemAlmostOutOfFiles
      annotations:
        description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemalmostoutoffiles
        summary: Filesystem has less than 3% inodes left.
      expr: |-
        (
          node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 3
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: critical
    - alert: NodeNetworkReceiveErrs
      annotations:
        description: '{{`{{`}} $labels.instance {{`}}`}} interface {{`{{`}} $labels.device {{`}}`}} has encountered {{`{{`}} printf "%.0f" $value {{`}}`}} receive errors in the last two minutes.'
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodenetworkreceiveerrs
        summary: Network interface is reporting many receive errors.
      expr: increase(node_network_receive_errs_total[2m]) > 10
      for: 1h
      labels:
        severity: warning
    - alert: NodeNetworkTransmitErrs
      annotations:
        description: '{{`{{`}} $labels.instance {{`}}`}} interface {{`{{`}} $labels.device {{`}}`}} has encountered {{`{{`}} printf "%.0f" $value {{`}}`}} transmit errors in the last two minutes.'
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodenetworktransmiterrs
        summary: Network interface is reporting many transmit errors.
      expr: increase(node_network_transmit_errs_total[2m]) > 10
      for: 1h
      labels:
        severity: warning
    - alert: NodeHighNumberConntrackEntriesUsed
      annotations:
        description: '{{`{{`}} $value | humanizePercentage {{`}}`}} of conntrack entries are used.'
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodehighnumberconntrackentriesused
        summary: Number of conntrack are getting close to the limit.
      expr: (node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75
      labels:
        severity: warning
    - alert: NodeTextFileCollectorScrapeError
      annotations:
        description: Node Exporter text file collector failed to scrape.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodetextfilecollectorscrapeerror
        summary: Node Exporter text file collector failed to scrape.
      expr: node_textfile_scrape_error{job="node-exporter"} == 1
      labels:
        severity: warning
    - alert: NodeClockSkewDetected
      annotations:
        message: Clock on {{`{{`}} $labels.instance {{`}}`}} is out of sync by more than 300s. Ensure NTP is configured correctly on this host.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodeclockskewdetected
        summary: Clock skew detected.
      expr: |-
        (
          node_timex_offset_seconds > 0.05
        and
          deriv(node_timex_offset_seconds[5m]) >= 0
        )
        or
        (
          node_timex_offset_seconds < -0.05
        and
          deriv(node_timex_offset_seconds[5m]) <= 0
        )
      for: 10m
      labels:
        severity: warning
    - alert: NodeClockNotSynchronising
      annotations:
        message: Clock on {{`{{`}} $labels.instance {{`}}`}} is not synchronising. Ensure NTP is configured on this host.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodeclocknotsynchronising
        summary: Clock not synchronising.
      expr: min_over_time(node_timex_sync_status[5m]) == 0
      for: 10m
      labels:
        severity: warning
{{- end }}