{{- /* Generated from 'node-exporter' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/node-exporter-prometheusRule.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.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. 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 < 25 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 {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeFilesystemSpaceFillingUp annotations: description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left and is filling up fast. 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 < 10 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 {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeFilesystemAlmostOutOfSpace annotations: description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left. 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 {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeFilesystemAlmostOutOfSpace annotations: description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left. 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 {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeFilesystemFilesFillingUp annotations: description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left and is filling up. 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 {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeFilesystemFilesFillingUp annotations: description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left and is filling up fast. 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 {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeFilesystemAlmostOutOfFiles annotations: description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left. 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 {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeFilesystemAlmostOutOfFiles annotations: description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left. 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 {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeNetworkReceiveErrs annotations: description: '{{`{{`}} $labels.instance {{`}}`}} interface {{`{{`}} $labels.device {{`}}`}} has encountered {{`{{`}} printf "%.0f" $value {{`}}`}} receive errors in the last two minutes.' summary: Network interface is reporting many receive errors. expr: rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01 for: 1h labels: severity: warning {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeNetworkTransmitErrs annotations: description: '{{`{{`}} $labels.instance {{`}}`}} interface {{`{{`}} $labels.device {{`}}`}} has encountered {{`{{`}} printf "%.0f" $value {{`}}`}} transmit errors in the last two minutes.' summary: Network interface is reporting many transmit errors. expr: rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01 for: 1h labels: severity: warning {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeHighNumberConntrackEntriesUsed annotations: description: '{{`{{`}} $value | humanizePercentage {{`}}`}} of conntrack entries are used.' 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 {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeTextFileCollectorScrapeError annotations: description: Node Exporter text file collector failed to scrape. summary: Node Exporter text file collector failed to scrape. expr: node_textfile_scrape_error{job="node-exporter"} == 1 labels: severity: warning {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeClockSkewDetected annotations: message: Clock on {{`{{`}} $labels.instance {{`}}`}} is out of sync by more than 300s. Ensure NTP is configured correctly on this host. 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 {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeClockNotSynchronising annotations: message: Clock on {{`{{`}} $labels.instance {{`}}`}} is not synchronising. Ensure NTP is configured on this host. summary: Clock not synchronising. expr: |- min_over_time(node_timex_sync_status[5m]) == 0 and node_timex_maxerror_seconds >= 16 for: 10m labels: severity: warning {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeRAIDDegraded annotations: description: RAID array '{{`{{`}} $labels.device {{`}}`}}' on {{`{{`}} $labels.instance {{`}}`}} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically. summary: RAID Array is degraded expr: node_md_disks_required - ignoring (state) (node_md_disks{state="active"}) > 0 for: 15m labels: severity: critical {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} - alert: NodeRAIDDiskFailure annotations: description: At least one device in RAID array on {{`{{`}} $labels.instance {{`}}`}} failed. Array '{{`{{`}} $labels.device {{`}}`}}' needs attention and possibly a disk swap. summary: Failed device in RAID array expr: node_md_disks{state="fail"} > 0 labels: severity: warning {{- if .Values.defaultRules.additionalRuleLabels }} {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }} {{- end }} {{- end }}