aboutsummaryrefslogtreecommitdiffstats
path: root/vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/prometheus.rules.yaml
diff options
context:
space:
mode:
Diffstat (limited to 'vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/prometheus.rules.yaml')
-rw-r--r--vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/prometheus.rules.yaml102
1 files changed, 102 insertions, 0 deletions
diff --git a/vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/prometheus.rules.yaml b/vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/prometheus.rules.yaml
new file mode 100644
index 00000000..e2d8a68d
--- /dev/null
+++ b/vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/prometheus.rules.yaml
@@ -0,0 +1,102 @@
+# Generated from 'prometheus.rules' group from https://raw.githubusercontent.com/coreos/prometheus-operator/master/contrib/kube-prometheus/manifests/prometheus-rules.yaml
+{{- if and .Values.defaultRules.create }}
+{{- $prometheusJob := printf "%s-%s" (include "prometheus-operator.fullname" .) "prometheus" }}
+apiVersion: {{ printf "%s/v1" (.Values.prometheusOperator.crdApiGroup | default "monitoring.coreos.com") }}
+kind: PrometheusRule
+metadata:
+ name: {{ printf "%s-%s" (include "prometheus-operator.fullname" .) "prometheus.rules" | trunc 63 | trimSuffix "-" }}
+ labels:
+ app: {{ template "prometheus-operator.name" . }}
+{{ include "prometheus-operator.labels" . | indent 4 }}
+{{- if .Values.defaultRules.labels }}
+{{ toYaml .Values.defaultRules.labels | indent 4 }}
+{{- end }}
+{{- if .Values.defaultRules.annotations }}
+ annotations:
+{{ toYaml .Values.defaultRules.annotations | indent 4 }}
+{{- end }}
+spec:
+ groups:
+ - name: prometheus.rules
+ rules:
+ - alert: PrometheusConfigReloadFailed
+ annotations:
+ description: Reloading Prometheus' configuration has failed for {{`{{$labels.namespace}}`}}/{{`{{$labels.pod}}`}}
+ summary: Reloading Prometheus' configuration failed
+ expr: prometheus_config_last_reload_successful{job="{{ $prometheusJob }}"} == 0
+ for: 10m
+ labels:
+ severity: warning
+ - alert: PrometheusNotificationQueueRunningFull
+ annotations:
+ description: Prometheus' alert notification queue is running full for {{`{{$labels.namespace}}`}}/{{`{{ $labels.pod}}`}}
+ summary: Prometheus' alert notification queue is running full
+ expr: predict_linear(prometheus_notifications_queue_length{job="{{ $prometheusJob }}"}[5m], 60 * 30) > prometheus_notifications_queue_capacity{job="{{ $prometheusJob }}"}
+ for: 10m
+ labels:
+ severity: warning
+ - alert: PrometheusErrorSendingAlerts
+ annotations:
+ description: Errors while sending alerts from Prometheus {{`{{$labels.namespace}}`}}/{{`{{ $labels.pod}}`}} to Alertmanager {{`{{$labels.Alertmanager}}`}}
+ summary: Errors while sending alert from Prometheus
+ expr: rate(prometheus_notifications_errors_total{job="{{ $prometheusJob }}"}[5m]) / rate(prometheus_notifications_sent_total{job="{{ $prometheusJob }}"}[5m]) > 0.01
+ for: 10m
+ labels:
+ severity: warning
+ - alert: PrometheusErrorSendingAlerts
+ annotations:
+ description: Errors while sending alerts from Prometheus {{`{{$labels.namespace}}`}}/{{`{{ $labels.pod}}`}} to Alertmanager {{`{{$labels.Alertmanager}}`}}
+ summary: Errors while sending alerts from Prometheus
+ expr: rate(prometheus_notifications_errors_total{job="{{ $prometheusJob }}"}[5m]) / rate(prometheus_notifications_sent_total{job="{{ $prometheusJob }}"}[5m]) > 0.03
+ for: 10m
+ labels:
+ severity: critical
+ - alert: PrometheusNotConnectedToAlertmanagers
+ annotations:
+ description: Prometheus {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} is not connected to any Alertmanagers
+ summary: Prometheus is not connected to any Alertmanagers
+ expr: prometheus_notifications_alertmanagers_discovered{job="{{ $prometheusJob }}"} < 1
+ for: 10m
+ labels:
+ severity: warning
+ - alert: PrometheusTSDBReloadsFailing
+ annotations:
+ description: '{{`{{$labels.job}}`}} at {{`{{$labels.instance}}`}} had {{`{{$value | humanize}}`}} reload failures over the last four hours.'
+ summary: Prometheus has issues reloading data blocks from disk
+ expr: increase(prometheus_tsdb_reloads_failures_total{job="{{ $prometheusJob }}"}[2h]) > 0
+ for: 12h
+ labels:
+ severity: warning
+ - alert: PrometheusTSDBCompactionsFailing
+ annotations:
+ description: '{{`{{$labels.job}}`}} at {{`{{$labels.instance}}`}} had {{`{{$value | humanize}}`}} compaction failures over the last four hours.'
+ summary: Prometheus has issues compacting sample blocks
+ expr: increase(prometheus_tsdb_compactions_failed_total{job="{{ $prometheusJob }}"}[2h]) > 0
+ for: 12h
+ labels:
+ severity: warning
+ - alert: PrometheusTSDBWALCorruptions
+ annotations:
+ description: '{{`{{$labels.job}}`}} at {{`{{$labels.instance}}`}} has a corrupted write-ahead log (WAL).'
+ summary: Prometheus write-ahead log is corrupted
+ expr: tsdb_wal_corruptions_total{job="{{ $prometheusJob }}"} > 0
+ for: 4h
+ labels:
+ severity: warning
+ - alert: PrometheusNotIngestingSamples
+ annotations:
+ description: Prometheus {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} isn't ingesting samples.
+ summary: Prometheus isn't ingesting samples
+ expr: rate(prometheus_tsdb_head_samples_appended_total{job="{{ $prometheusJob }}"}[5m]) <= 0
+ for: 10m
+ labels:
+ severity: warning
+ - alert: PrometheusTargetScrapesDuplicate
+ annotations:
+ description: '{{`{{$labels.namespace}}`}}/{{`{{$labels.pod}}`}} has many samples rejected due to duplicate timestamps but different values'
+ summary: Prometheus has many samples rejected
+ expr: increase(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="{{ $prometheusJob }}"}[5m]) > 0
+ for: 10m
+ labels:
+ severity: warning
+{{- end }} \ No newline at end of file