63 lines
2.9 KiB
YAML
63 lines
2.9 KiB
YAML
{{ if .Values.nfc_monitoring.kube_monitor_proxy.enabled }}
|
|
---
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/component: exporter
|
|
app.kubernetes.io/instance: {{ $.Release.Name }}
|
|
app.kubernetes.io/name: kube-prometheus
|
|
app.kubernetes.io/part-of: {{ $.Chart.Name }}
|
|
app.kubernetes.io/version: {{ $.Chart.Version }}
|
|
app.kubernetes.io/managed-by: {{ $.Release.Service }}
|
|
prometheus: {{ $.Release.Name }}
|
|
role: alert-rules
|
|
name: kube-prometheus-rules
|
|
namespace: {{ .Values.nfc_monitoring.prometheus.namespace }}
|
|
spec:
|
|
groups:
|
|
- name: general.rules
|
|
rules:
|
|
- alert: TargetDown
|
|
annotations:
|
|
description: '{{ `{{` }} printf "%.4g" $value }}% of the {{ `{{` }} $labels.job }}/{{ `{{` }} $labels.service }} targets in {{ `{{` }} $labels.namespace }} namespace are down.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/targetdown
|
|
summary: One or more targets are unreachable.
|
|
expr: 100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job, namespace, service)) > 10
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- name: node-network
|
|
rules:
|
|
- alert: NodeNetworkInterfaceFlapping
|
|
annotations:
|
|
description: Network interface "{{ `{{` }} $labels.device }}" changing its up status often on node-exporter {{ `{{` }} $labels.namespace }}/{{ `{{` }} $labels.pod }}
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/nodenetworkinterfaceflapping
|
|
summary: Network interface is often changing its status
|
|
expr: |
|
|
changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m]) > 2
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
- name: kube-prometheus-node-recording.rules
|
|
rules:
|
|
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m])) BY (instance)
|
|
record: instance:node_cpu:rate:sum
|
|
- expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance)
|
|
record: instance:node_network_receive_bytes:rate:sum
|
|
- expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance)
|
|
record: instance:node_network_transmit_bytes:rate:sum
|
|
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance)
|
|
record: instance:node_cpu:ratio
|
|
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m]))
|
|
record: cluster:node_cpu:sum_rate5m
|
|
- expr: cluster:node_cpu:sum_rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu))
|
|
record: cluster:node_cpu:ratio
|
|
- name: kube-prometheus-general.rules
|
|
rules:
|
|
- expr: count without(instance, pod, node) (up == 1)
|
|
record: count:up1
|
|
- expr: count without(instance, pod, node) (up == 0)
|
|
record: count:up0
|
|
|
|
{{ end }} |