kubezero/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml

398 lines
19 KiB
YAML

{{- /*
Generated from 'node-exporter' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/nodeExporter-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.nodeExporterAlerting }}
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:
{{- if not (.Values.defaultRules.disabled.NodeFilesystemSpaceFillingUp | default false) }}
- alert: NodeFilesystemSpaceFillingUp
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
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 }}/node/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 < 15
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 }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeFilesystemSpaceFillingUp | default false) }}
- alert: NodeFilesystemSpaceFillingUp
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
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 }}/node/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 < 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 }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeFilesystemAlmostOutOfSpace | default false) }}
- alert: NodeFilesystemAlmostOutOfSpace
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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: 30m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeFilesystemAlmostOutOfSpace | default false) }}
- alert: NodeFilesystemAlmostOutOfSpace
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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: 30m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeFilesystemFilesFillingUp | default false) }}
- alert: NodeFilesystemFilesFillingUp
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
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 }}/node/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
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeFilesystemFilesFillingUp | default false) }}
- alert: NodeFilesystemFilesFillingUp
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
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 }}/node/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
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeFilesystemAlmostOutOfFiles | default false) }}
- alert: NodeFilesystemAlmostOutOfFiles
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeFilesystemAlmostOutOfFiles | default false) }}
- alert: NodeFilesystemAlmostOutOfFiles
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeNetworkReceiveErrs | default false) }}
- alert: NodeNetworkReceiveErrs
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: '{{`{{`}} $labels.instance {{`}}`}} interface {{`{{`}} $labels.device {{`}}`}} has encountered {{`{{`}} printf "%.0f" $value {{`}}`}} receive errors in the last two minutes.'
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/nodenetworkreceiveerrs
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 }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeNetworkTransmitErrs | default false) }}
- alert: NodeNetworkTransmitErrs
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: '{{`{{`}} $labels.instance {{`}}`}} interface {{`{{`}} $labels.device {{`}}`}} has encountered {{`{{`}} printf "%.0f" $value {{`}}`}} transmit errors in the last two minutes.'
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/nodenetworktransmiterrs
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 }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeHighNumberConntrackEntriesUsed | default false) }}
- alert: NodeHighNumberConntrackEntriesUsed
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: '{{`{{`}} $value | humanizePercentage {{`}}`}} of conntrack entries are used.'
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/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
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeTextFileCollectorScrapeError | default false) }}
- alert: NodeTextFileCollectorScrapeError
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Node Exporter text file collector failed to scrape.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/nodetextfilecollectorscrapeerror
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 }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeClockSkewDetected | default false) }}
- alert: NodeClockSkewDetected
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: 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 }}/node/nodeclockskewdetected
summary: Clock skew detected.
expr: |-
(
node_timex_offset_seconds{job="node-exporter"} > 0.05
and
deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) >= 0
)
or
(
node_timex_offset_seconds{job="node-exporter"} < -0.05
and
deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) <= 0
)
for: 10m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeClockNotSynchronising | default false) }}
- alert: NodeClockNotSynchronising
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Clock on {{`{{`}} $labels.instance {{`}}`}} is not synchronising. Ensure NTP is configured on this host.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/nodeclocknotsynchronising
summary: Clock not synchronising.
expr: |-
min_over_time(node_timex_sync_status{job="node-exporter"}[5m]) == 0
and
node_timex_maxerror_seconds{job="node-exporter"} >= 16
for: 10m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeRAIDDegraded | default false) }}
- alert: NodeRAIDDegraded
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
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.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/noderaiddegraded
summary: RAID Array is degraded
expr: node_md_disks_required{job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)"} - ignoring (state) (node_md_disks{state="active",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)"}) > 0
for: 15m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeRAIDDiskFailure | default false) }}
- alert: NodeRAIDDiskFailure
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: At least one device in RAID array on {{`{{`}} $labels.instance {{`}}`}} failed. Array '{{`{{`}} $labels.device {{`}}`}}' needs attention and possibly a disk swap.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/noderaiddiskfailure
summary: Failed device in RAID array
expr: node_md_disks{state="failed",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+)"} > 0
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeFileDescriptorLimit | default false) }}
- alert: NodeFileDescriptorLimit
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: File descriptors limit at {{`{{`}} $labels.instance {{`}}`}} is currently at {{`{{`}} printf "%.2f" $value {{`}}`}}%.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/nodefiledescriptorlimit
summary: Kernel is predicted to exhaust file descriptors limit soon.
expr: |-
(
node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 70
)
for: 15m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.NodeFileDescriptorLimit | default false) }}
- alert: NodeFileDescriptorLimit
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: File descriptors limit at {{`{{`}} $labels.instance {{`}}`}} is currently at {{`{{`}} printf "%.2f" $value {{`}}`}}%.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/nodefiledescriptorlimit
summary: Kernel is predicted to exhaust file descriptors limit soon.
expr: |-
(
node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 90
)
for: 15m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- end }}