mirror of
https://github.com/auricom/home-cluster.git
synced 2025-09-17 18:24:14 +02:00
new gitops template
This commit is contained in:
auricom
@@ -0,0 +1,172 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": [
|
||||
{
|
||||
"builtIn": 1,
|
||||
"datasource": "-- Grafana --",
|
||||
"enable": true,
|
||||
"hide": true,
|
||||
"iconColor": "rgba(0, 211, 255, 1)",
|
||||
"name": "Annotations & Alerts",
|
||||
"type": "dashboard"
|
||||
}
|
||||
]
|
||||
},
|
||||
"editable": true,
|
||||
"gnetId": null,
|
||||
"graphTooltip": 0,
|
||||
"id": 23,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"aliasColors": {},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "Prometheus",
|
||||
"decimals": 0,
|
||||
"description": "",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"fill": 0,
|
||||
"fillGradient": 0,
|
||||
"gridPos": {
|
||||
"h": 9,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"hiddenSeries": false,
|
||||
"id": 2,
|
||||
"legend": {
|
||||
"alignAsTable": true,
|
||||
"avg": true,
|
||||
"current": false,
|
||||
"hideEmpty": false,
|
||||
"max": true,
|
||||
"min": true,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"nullPointMode": "null",
|
||||
"options": {
|
||||
"dataLinks": []
|
||||
},
|
||||
"percentage": false,
|
||||
"pointradius": 2,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"seriesOverrides": [],
|
||||
"spaceLength": 10,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "avg by (kubernetes_node) (\r\n node_hwmon_temp_celsius{chip=\"platform_coretemp_0\"}\r\n )",
|
||||
"format": "time_series",
|
||||
"interval": "",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "{{kubernetes_node}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
{
|
||||
"colorMode": "warning",
|
||||
"fill": true,
|
||||
"line": true,
|
||||
"op": "gt",
|
||||
"value": 80,
|
||||
"yaxis": "left"
|
||||
},
|
||||
{
|
||||
"colorMode": "critical",
|
||||
"fill": true,
|
||||
"line": true,
|
||||
"op": "gt",
|
||||
"value": 90,
|
||||
"yaxis": "left"
|
||||
}
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeRegions": [],
|
||||
"timeShift": null,
|
||||
"title": "Nodes Temperatures",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"transformations": [],
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": []
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"decimals": 0,
|
||||
"format": "celsius",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"decimals": null,
|
||||
"format": "celsius",
|
||||
"label": "",
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": false
|
||||
}
|
||||
],
|
||||
"yaxis": {
|
||||
"align": false,
|
||||
"alignLevel": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"schemaVersion": 25,
|
||||
"style": "dark",
|
||||
"tags": [
|
||||
"kubernetes-mixin"
|
||||
],
|
||||
"templating": {
|
||||
"list": []
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {
|
||||
"refresh_intervals": [
|
||||
"10s",
|
||||
"30s",
|
||||
"1m",
|
||||
"5m",
|
||||
"15m",
|
||||
"30m",
|
||||
"1h",
|
||||
"2h",
|
||||
"1d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"title": "Kubernetes / Custom metrics",
|
||||
"uid": "sn-bOoWMz",
|
||||
"version": 5
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
310
cluster/apps/monitoring/kube-prometheus-stack/helm-release.yaml
Normal file
310
cluster/apps/monitoring/kube-prometheus-stack/helm-release.yaml
Normal file
@@ -0,0 +1,310 @@
|
||||
---
|
||||
apiVersion: helm.toolkit.fluxcd.io/v2beta1
|
||||
kind: HelmRelease
|
||||
metadata:
|
||||
name: kube-prometheus-stack
|
||||
namespace: monitoring
|
||||
spec:
|
||||
interval: 5m
|
||||
chart:
|
||||
spec:
|
||||
# renovate: registryUrl=https://prometheus-community.github.io/helm-charts
|
||||
chart: kube-prometheus-stack
|
||||
version: 14.6.2
|
||||
sourceRef:
|
||||
kind: HelmRepository
|
||||
name: prometheus-community-charts
|
||||
namespace: flux-system
|
||||
interval: 5m
|
||||
timeout: 20m
|
||||
values:
|
||||
server:
|
||||
resources:
|
||||
requests:
|
||||
memory: 1500Mi
|
||||
cpu: 200m
|
||||
limits:
|
||||
memory: 2000Mi
|
||||
prometheusOperator:
|
||||
createCustomResource: true
|
||||
alertmanager:
|
||||
ingress:
|
||||
enabled: true
|
||||
annotations:
|
||||
kubernetes.io/ingress.class: "nginx"
|
||||
nginx.ingress.kubernetes.io/auth-url: "http://authelia.networking.svc.cluster.local/api/verify"
|
||||
nginx.ingress.kubernetes.io/auth-signin: "https://login.${SECRET_CLUSTER_DOMAIN}/"
|
||||
hosts: ["alert-manager.${SECRET_CLUSTER_DOMAIN}"]
|
||||
tls:
|
||||
- hosts:
|
||||
- alert-manager.${SECRET_CLUSTER_DOMAIN}
|
||||
config:
|
||||
global:
|
||||
resolve_timeout: 5m
|
||||
receivers:
|
||||
- name: "null"
|
||||
- name: "pushover"
|
||||
pushover_configs:
|
||||
- user_key: ${SECRET_KUBE_PROMETHEUS_STACK_ALERTMANAGER_PUSHOVER_USER_KEY}
|
||||
token: ${SECRET_KUBE_PROMETHEUS_STACK_ALERTMANAGER_PUSHOVER_TOKEN}
|
||||
route:
|
||||
receiver: "pushover"
|
||||
routes:
|
||||
- match:
|
||||
alertname: Watchdog
|
||||
receiver: "null"
|
||||
- receiver: "pushover"
|
||||
inhibit_rules:
|
||||
- source_match:
|
||||
severity: "critical"
|
||||
target_match:
|
||||
severity: "warning"
|
||||
# Apply inhibition if the alertname is the same.
|
||||
equal: ["alertname", "namespace"]
|
||||
alertmanagerSpec:
|
||||
storage:
|
||||
volumeClaimTemplate:
|
||||
spec:
|
||||
storageClassName: longhorn
|
||||
resources:
|
||||
requests:
|
||||
storage: 10Gi
|
||||
nodeExporter:
|
||||
serviceMonitor:
|
||||
relabelings:
|
||||
- action: replace
|
||||
regex: (.*)
|
||||
replacement: $1
|
||||
sourceLabels:
|
||||
- __meta_kubernetes_pod_node_name
|
||||
targetLabel: kubernetes_node
|
||||
kubelet:
|
||||
serviceMonitor:
|
||||
metricRelabelings:
|
||||
- action: replace
|
||||
sourceLabels:
|
||||
- node
|
||||
targetLabel: instance
|
||||
grafana:
|
||||
adminPassword: ${SECRET_KUBE_PROMETHEUS_STACK_GRAFANA_ADMIN_PASSWORD}
|
||||
dashboards:
|
||||
default:
|
||||
kubernetes-custom:
|
||||
url: https://raw.githubusercontent.com/auricom/home-cluster/main/cluster/apps/monitoring/kube-prometheus-stack/grafana-dashboards/kubernetes-custom.json
|
||||
datasource: Prometheus
|
||||
longhorn:
|
||||
url: https://raw.githubusercontent.com/auricom/home-cluster/main/cluster/apps/monitoring/kube-prometheus-stack/grafana-dashboards/longhorn.json
|
||||
datasource: Prometheus
|
||||
deploymentStrategy:
|
||||
type: Recreate
|
||||
persistence:
|
||||
enabled: false
|
||||
env:
|
||||
GF_EXPLORE_ENABLED: true
|
||||
GF_DISABLE_SANITIZE_HTML: true
|
||||
GF_PANELS_DISABLE_SANITIZE_HTML: true
|
||||
plugins:
|
||||
- natel-discrete-panel
|
||||
- pr0ps-trackmap-panel
|
||||
- grafana-piechart-panel
|
||||
- vonage-status-panel
|
||||
- grafana-worldmap-panel
|
||||
- grafana-clock-panel
|
||||
dashboardProviders:
|
||||
dashboardproviders.yaml:
|
||||
apiVersion: 1
|
||||
providers:
|
||||
- name: "default"
|
||||
orgId: 1
|
||||
folder: ""
|
||||
type: file
|
||||
disableDeletion: false
|
||||
editable: true
|
||||
options:
|
||||
path: /var/lib/grafana/dashboards/default
|
||||
sidecar:
|
||||
datasources:
|
||||
enabled: true
|
||||
defaultDatasourceEnabled: false
|
||||
dashboards:
|
||||
enabled: true
|
||||
searchNamespace: ALL
|
||||
additionalDataSources:
|
||||
- name: Prometheus
|
||||
type: prometheus
|
||||
access: proxy
|
||||
url: http://thanos-query-http:10902/
|
||||
isDefault: true
|
||||
grafana.ini:
|
||||
server:
|
||||
root_url: https://grafana.${SECRET_CLUSTER_DOMAIN}
|
||||
paths:
|
||||
data: /var/lib/grafana/data
|
||||
logs: /var/log/grafana
|
||||
plugins: /var/lib/grafana/plugins
|
||||
provisioning: /etc/grafana/provisioning
|
||||
analytics:
|
||||
check_for_updates: true
|
||||
log:
|
||||
mode: console
|
||||
grafana_net:
|
||||
url: https://grafana.net
|
||||
smtp:
|
||||
enabled: false
|
||||
ingress:
|
||||
enabled: true
|
||||
annotations:
|
||||
kubernetes.io/ingress.class: "nginx"
|
||||
nginx.ingress.kubernetes.io/auth-url: "http://authelia.networking.svc.cluster.local/api/verify"
|
||||
nginx.ingress.kubernetes.io/auth-signin: "https://login.${SECRET_CLUSTER_DOMAIN}/"
|
||||
hosts: ["grafana.${SECRET_CLUSTER_DOMAIN}"]
|
||||
tls:
|
||||
- hosts:
|
||||
- grafana.${SECRET_CLUSTER_DOMAIN}
|
||||
kubeEtcd:
|
||||
enabled: false
|
||||
kubeControllerManager:
|
||||
enabled: false
|
||||
kubeScheduler:
|
||||
enabled: false
|
||||
kubeProxy:
|
||||
enabled: false
|
||||
prometheus:
|
||||
ingress:
|
||||
enabled: true
|
||||
annotations:
|
||||
kubernetes.io/ingress.class: "nginx"
|
||||
nginx.ingress.kubernetes.io/auth-url: "http://authelia.networking.svc.cluster.local/api/verify"
|
||||
nginx.ingress.kubernetes.io/auth-signin: "https://login.${SECRET_CLUSTER_DOMAIN}/"
|
||||
hosts: ["prometheus.${SECRET_CLUSTER_DOMAIN}"]
|
||||
tls:
|
||||
- hosts:
|
||||
- prometheus.${SECRET_CLUSTER_DOMAIN}
|
||||
prometheusSpec:
|
||||
replicas: 2
|
||||
replicaExternalLabelName: "replica"
|
||||
ruleSelector: {}
|
||||
ruleNamespaceSelector: {}
|
||||
ruleSelectorNilUsesHelmValues: false
|
||||
serviceMonitorSelector: {}
|
||||
serviceMonitorNamespaceSelector: {}
|
||||
serviceMonitorSelectorNilUsesHelmValues: false
|
||||
podMonitorSelector: {}
|
||||
podMonitorNamespaceSelector: {}
|
||||
podMonitorSelectorNilUsesHelmValues: false
|
||||
retention: 6h
|
||||
enableAdminAPI: true
|
||||
walCompression: true
|
||||
storageSpec:
|
||||
volumeClaimTemplate:
|
||||
spec:
|
||||
storageClassName: longhorn
|
||||
resources:
|
||||
requests:
|
||||
storage: 10Gi
|
||||
thanos:
|
||||
image: quay.io/thanos/thanos:v0.18.0
|
||||
objectStorageConfig:
|
||||
name: thanos
|
||||
key: object-store.yaml
|
||||
additionalScrapeConfigs:
|
||||
- job_name: "opnsense"
|
||||
scrape_interval: 60s
|
||||
metrics_path: "/metrics"
|
||||
static_configs:
|
||||
- targets: ["opnsense.${SECRET_CLUSTER_DOMAIN_ROOT}:9273"]
|
||||
labels:
|
||||
app: "opnsense"
|
||||
# Example scrape config for probing ingresses via the Blackbox Exporter.
|
||||
#
|
||||
# The relabeling allows the actual ingress scrape endpoint to be configured
|
||||
# via the following annotations:
|
||||
#
|
||||
# * `prometheus.io/probe`: Only probe ingresses that have a value of `true`
|
||||
- job_name: "kubernetes-ingresses"
|
||||
metrics_path: /probe
|
||||
scrape_interval: 60s
|
||||
params:
|
||||
module: [http_2xx]
|
||||
kubernetes_sd_configs:
|
||||
- role: ingress
|
||||
relabel_configs:
|
||||
- source_labels:
|
||||
[__meta_kubernetes_ingress_annotation_prometheus_io_probe]
|
||||
action: keep
|
||||
regex: true
|
||||
- source_labels:
|
||||
[
|
||||
__meta_kubernetes_ingress_scheme,
|
||||
__address__,
|
||||
__meta_kubernetes_ingress_path,
|
||||
]
|
||||
regex: (.+);(.+);(.+)
|
||||
replacement: ${1}://${2}${3}
|
||||
target_label: __param_target
|
||||
- target_label: __address__
|
||||
replacement: blackbox-exporter-prometheus-blackbox-exporter:9115
|
||||
- source_labels: [__param_target]
|
||||
target_label: instance
|
||||
- action: labelmap
|
||||
regex: __meta_kubernetes_ingress_label_(.+)
|
||||
- source_labels: [__meta_kubernetes_namespace]
|
||||
target_label: kubernetes_namespace
|
||||
- source_labels: [__meta_kubernetes_ingress_name]
|
||||
target_label: kubernetes_name
|
||||
- job_name: "kubernetes-services-http"
|
||||
metrics_path: /probe
|
||||
scrape_interval: 60s
|
||||
params:
|
||||
module: [http_2xx]
|
||||
kubernetes_sd_configs:
|
||||
- role: service
|
||||
relabel_configs:
|
||||
- source_labels:
|
||||
[__meta_kubernetes_service_annotation_prometheus_io_probe]
|
||||
action: keep
|
||||
regex: true
|
||||
- source_labels:
|
||||
[__meta_kubernetes_service_annotation_prometheus_io_protocol]
|
||||
action: keep
|
||||
regex: http
|
||||
- source_labels: [__address__]
|
||||
target_label: __param_target
|
||||
- target_label: __address__
|
||||
replacement: blackbox-exporter-prometheus-blackbox-exporter:9115
|
||||
- source_labels: [__param_target]
|
||||
target_label: instance
|
||||
- action: labelmap
|
||||
regex: __meta_kubernetes_service_label_(.+)
|
||||
- source_labels: [__meta_kubernetes_namespace]
|
||||
target_label: kubernetes_namespace
|
||||
- source_labels: [__meta_kubernetes_service_name]
|
||||
target_label: kubernetes_name
|
||||
- job_name: "kubernetes-services-tcp"
|
||||
metrics_path: /probe
|
||||
scrape_interval: 60s
|
||||
params:
|
||||
module: [tcp_connect]
|
||||
kubernetes_sd_configs:
|
||||
- role: service
|
||||
relabel_configs:
|
||||
- source_labels:
|
||||
[__meta_kubernetes_service_annotation_prometheus_io_probe]
|
||||
action: keep
|
||||
regex: true
|
||||
- source_labels:
|
||||
[__meta_kubernetes_service_annotation_prometheus_io_protocol]
|
||||
action: keep
|
||||
regex: tcp
|
||||
- source_labels: [__address__]
|
||||
target_label: __param_target
|
||||
- target_label: __address__
|
||||
replacement: blackbox-exporter-prometheus-blackbox-exporter:9115
|
||||
- source_labels: [__param_target]
|
||||
target_label: instance
|
||||
- action: labelmap
|
||||
regex: __meta_kubernetes_service_label_(.+)
|
||||
- source_labels: [__meta_kubernetes_namespace]
|
||||
target_label: kubernetes_namespace
|
||||
- source_labels: [__meta_kubernetes_service_name]
|
||||
target_label: kubernetes_name
|
||||
@@ -0,0 +1,5 @@
|
||||
---
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
resources:
|
||||
- helm-release.yaml
|
||||
Reference in New Issue
Block a user