diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml index 14e7df254e99..c306dc6c18ad 100644 --- a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml +++ b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml @@ -106,7 +106,7 @@ spec: ( rate(alertmanager_notifications_failed_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) / - rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) + ignoring (reason) group_left rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) ) > 0.01 for: 5m @@ -140,7 +140,7 @@ spec: min by ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}namespace,service, integration) ( rate(alertmanager_notifications_failed_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration=~`.*`}[5m]) / - rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration=~`.*`}[5m]) + ignoring (reason) group_left rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration=~`.*`}[5m]) ) > 0.01 for: 5m @@ -174,7 +174,7 @@ spec: min by ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}namespace,service, integration) ( rate(alertmanager_notifications_failed_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration!~`.*`}[5m]) / - rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration!~`.*`}[5m]) + ignoring (reason) group_left rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration!~`.*`}[5m]) ) > 0.01 for: 5m diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-availability.rules.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-availability.rules.yaml index 67263d2f62f0..ceec327e8686 100644 --- a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-availability.rules.yaml +++ b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-availability.rules.yaml @@ -270,4 +270,4 @@ spec: {{- toYaml . | nindent 8 }} {{- end }} {{- end }} -{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-burnrate.rules.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-burnrate.rules.yaml index b5d7857c0797..369a0ae1b448 100644 --- a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-burnrate.rules.yaml +++ b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-burnrate.rules.yaml @@ -437,4 +437,4 @@ spec: {{- end }} {{- end }} record: apiserver_request:burnrate6h -{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-histogram.rules.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-histogram.rules.yaml index 3bf850a2dd52..e269cf33cd1c 100644 --- a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-histogram.rules.yaml +++ b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-histogram.rules.yaml @@ -50,4 +50,4 @@ spec: {{- end }} {{- end }} record: cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile -{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml index 7a95e8338d49..8b7e965fd6af 100644 --- a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml +++ b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml @@ -259,9 +259,9 @@ spec: runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/cputhrottlinghigh summary: Processes experience elevated CPU throttling. expr: |- - sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace) + sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, container, pod, namespace) / - sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace) + sum(increase(container_cpu_cfs_periods_total{}[5m])) by ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, container, pod, namespace) > ( 25 / 100 ) for: 15m {{- with .Values.defaultRules.keepFiringFor }} @@ -278,4 +278,4 @@ spec: {{- end }} {{- end }} {{- end }} -{{- end }} +{{- end }} \ No newline at end of file diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml index 5c14e28f75bf..34d7d833cbe2 100644 --- a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml +++ b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml @@ -770,4 +770,32 @@ spec: {{- end }} {{- end }} {{- end }} +{{- if not (.Values.defaultRules.disabled.NodeBondingDegraded | default false) }} + - alert: NodeBondingDegraded + annotations: +{{- if .Values.defaultRules.additionalRuleAnnotations }} +{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }} +{{- end }} +{{- if .Values.defaultRules.additionalRuleGroupAnnotations.nodeExporterAlerting }} +{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.nodeExporterAlerting | indent 8 }} +{{- end }} + description: Bonding interface {{`{{`}} $labels.master {{`}}`}} on {{`{{`}} $labels.instance {{`}}`}} is in degraded state due to one or more slave failures. + runbook_url: {{ .Values.defaultRules.runbookUrl }}/node/nodebondingdegraded + summary: Bonding interface is degraded + expr: (node_bonding_slaves - node_bonding_active) != 0 + for: 5m + {{- with .Values.defaultRules.keepFiringFor }} + keep_firing_for: "{{ . }}" + {{- end }} + labels: + severity: warning + {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.nodeExporterAlerting }} + {{- with .Values.defaultRules.additionalRuleLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.defaultRules.additionalRuleGroupLabels.nodeExporterAlerting }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} +{{- end }} {{- end }} \ No newline at end of file