added Checkmk init release

This commit is contained in:
Richard Tomik
2026-06-17 15:17:45 +02:00
parent 256f7e6807
commit 0e5c73976b
10 changed files with 597 additions and 0 deletions

18
charts/checkmk/Chart.yaml Normal file
View File

@ -0,0 +1,18 @@
apiVersion: v2
name: checkmk
description: Checkmk monitoring platform helm chart for Kubernetes
type: application
version: 0.1.0
appVersion: "2.5.0p6"
maintainers:
- name: Richard Tomik
email: richard.tomik@proton.me
keywords:
- monitoring
- checkmk
- infrastructure
- observability
home: https://github.com/rtomik/helm-charts
sources:
- https://checkmk.com
- https://hub.docker.com/r/checkmk/check-mk-community

56
charts/checkmk/NOTES.txt Normal file
View File

@ -0,0 +1,56 @@
1. Get the application URL by running these commands:
{{- if .Values.ingress.enabled }}
{{- range $host := .Values.ingress.hosts }}
{{- range .paths }}
http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
{{- end }}
{{- end }}
{{- else if contains "NodePort" .Values.service.type }}
export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "checkmk.fullname" . }})
export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
echo http://$NODE_IP:$NODE_PORT
{{- else if contains "LoadBalancer" .Values.service.type }}
NOTE: It may take a few minutes for the LoadBalancer IP to be available.
You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "checkmk.fullname" . }}'
export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "checkmk.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
echo http://$SERVICE_IP:{{ .Values.service.port }}
{{- else if contains "ClusterIP" .Values.service.type }}
export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "checkmk.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
echo "Visit http://127.0.0.1:5000/{{ .Values.config.siteId }}/check_mk/ to use your application"
kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 5000:5000
{{- end }}
2. Checkmk web interface is available at:
http://<host>/{{ .Values.config.siteId }}/check_mk/
3. Default credentials:
Username: cmkadmin
Password: (as configured in config.adminPassword)
4. Ports:
- Web interface: {{ .Values.service.port }} → container 5000
- Agent Receiver: {{ .Values.service.agentReceiverPort }} → container 8000
{{- if .Values.persistence.enabled }}
5. Persistent storage: {{ if .Values.persistence.existingClaim }}{{ .Values.persistence.existingClaim }}{{ else }}{{ include "checkmk.fullname" . }}-sites{{ end }} ({{ .Values.persistence.size }})
Mounted at /omd/sites — contains all site data, configs, and RRD files.
{{- else }}
5. WARNING: No persistent storage enabled. All monitoring data will be lost on pod restart.
Enable persistence in values.yaml for production use.
{{- end }}
{{- if .Values.config.livestatusTcp }}
6. Livestatus TCP is enabled. Ensure appropriate NetworkPolicies are in place.
{{- end }}
{{- if not .Values.config.adminPassword.existingSecret }}
7. SECURITY NOTE: For production use, store the admin password in a Kubernetes Secret:
kubectl create secret generic checkmk-secrets \
--from-literal=cmk-password=<your-password>
Then set config.adminPassword.existingSecret=checkmk-secrets in your values.
{{- else }}
7. Admin password read from existing secret: {{ .Values.config.adminPassword.existingSecret }}
{{- end }}
For more information, see the official Checkmk Docker documentation:
https://docs.checkmk.com/latest/en/introduction_docker.html

91
charts/checkmk/readme.md Normal file
View File

@ -0,0 +1,91 @@
# Checkmk Helm Chart
Helm chart for deploying [Checkmk](https://checkmk.com/) — an infrastructure and application monitoring platform — on Kubernetes.
## Overview
Checkmk uses OMD (Open Monitoring Distribution) to manage monitoring sites. This chart deploys the Community Edition using the official Docker image with:
- Persistent storage for all site data (`/omd/sites`)
- RAM-backed tmpfs for the site temp directory (performance optimization from the official docs)
- Separate service ports for the web interface (5000) and agent receiver (8000)
- Admin password stored in a Kubernetes Secret
## Prerequisites
- Kubernetes 1.19+
- Helm 3.0+
- A default StorageClass or an existing PersistentVolumeClaim
## Quick Start
```bash
helm install checkmk ./charts/checkmk \
--set config.adminPassword.value=mysecretpassword \
--set ingress.enabled=true \
--set ingress.hosts[0].host=checkmk.example.com \
--set ingress.hosts[0].paths[0].path=/ \
--set ingress.hosts[0].paths[0].pathType=Prefix
```
After installation, access the UI at `http://<host>/cmk/check_mk/` with username `cmkadmin`.
## Configuration
### Admin Password (recommended: use existing secret)
```bash
kubectl create secret generic checkmk-secrets \
--from-literal=cmk-password=<your-password>
```
```yaml
config:
adminPassword:
existingSecret: "checkmk-secrets"
passwordKey: "cmk-password"
```
### Site ID
The `config.siteId` value sets the Checkmk site name and determines the URL path (`/<siteId>/check_mk/`). Defaults to `cmk`.
### Livestatus TCP
Enable Livestatus TCP for distributed monitoring setups or external integrations:
```yaml
config:
livestatusTcp: true
```
### Persistence
Site data (hosts, checks, RRD files) is stored in `/omd/sites`. A 5 Gi PVC is created by default. Adjust size or use an existing claim:
```yaml
persistence:
size: 20Gi
storageClass: "fast-ssd"
```
## Key Values
| Key | Default | Description |
|-----|---------|-------------|
| `image.tag` | `2.5.0p6` | Checkmk Community image tag |
| `config.siteId` | `cmk` | Monitoring site name |
| `config.timezone` | `UTC` | Container timezone |
| `config.adminPassword.value` | `changeme` | cmkadmin password (use existingSecret in production) |
| `config.livestatusTcp` | `false` | Enable Livestatus over TCP |
| `config.mailRelayHost` | `""` | SMTP relay for notifications |
| `service.port` | `5000` | Web interface port |
| `service.agentReceiverPort` | `8000` | Agent registration port |
| `persistence.enabled` | `true` | Enable persistent storage |
| `persistence.size` | `5Gi` | PVC size |
## Security Notes
Checkmk (OMD) requires root access inside the container to manage monitoring sites and switch to the site user account. The `podSecurityContext.runAsUser` is set to `0` and `containerSecurityContext.allowPrivilegeEscalation` is `true` by default.
Place a reverse proxy (e.g. Traefik or nginx) in front for TLS termination rather than exposing the container port directly.

View File

@ -0,0 +1,66 @@
{{/*
Expand the name of the chart.
*/}}
{{- define "checkmk.name" -}}
{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
Create a default fully qualified app name.
*/}}
{{- define "checkmk.fullname" -}}
{{- if .Values.fullnameOverride }}
{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
{{- else }}
{{- $name := default .Chart.Name .Values.nameOverride }}
{{- printf "%s" $name | trunc 63 | trimSuffix "-" }}
{{- end }}
{{- end }}
{{/*
Create chart name and version as used by the chart label.
*/}}
{{- define "checkmk.chart" -}}
{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
Common labels
*/}}
{{- define "checkmk.labels" -}}
helm.sh/chart: {{ include "checkmk.chart" . }}
{{ include "checkmk.selectorLabels" . }}
{{- if .Chart.AppVersion }}
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
{{- end }}
app.kubernetes.io/managed-by: {{ .Release.Service }}
{{- end }}
{{/*
Selector labels
*/}}
{{- define "checkmk.selectorLabels" -}}
app.kubernetes.io/name: {{ include "checkmk.name" . }}
app.kubernetes.io/instance: {{ .Release.Name }}
{{- end }}
{{/*
Name of the secret holding CMK_PASSWORD
*/}}
{{- define "checkmk.secretName" -}}
{{- .Values.config.adminPassword.existingSecret | default (printf "%s-secrets" (include "checkmk.fullname" .)) }}
{{- end }}
{{/*
Web UI path for health probes: /<siteId>/check_mk/login.py
*/}}
{{- define "checkmk.probePath" -}}
{{- printf "/%s/check_mk/login.py" .Values.config.siteId }}
{{- end }}
{{/*
tmpfs mount path derived from site ID
*/}}
{{- define "checkmk.tmpPath" -}}
{{- printf "/opt/omd/sites/%s/tmp" .Values.config.siteId }}
{{- end }}

View File

@ -0,0 +1,135 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "checkmk.fullname" . }}
labels:
{{- include "checkmk.labels" . | nindent 4 }}
annotations:
checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }}
spec:
replicas: {{ .Values.replicaCount }}
revisionHistoryLimit: {{ .Values.revisionHistoryLimit }}
selector:
matchLabels:
{{- include "checkmk.selectorLabels" . | nindent 6 }}
strategy:
type: Recreate
template:
metadata:
labels:
{{- include "checkmk.selectorLabels" . | nindent 8 }}
annotations:
{{- with .Values.podAnnotations }}
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
securityContext:
{{- toYaml .Values.podSecurityContext | nindent 8 }}
containers:
- name: {{ .Chart.Name }}
securityContext:
{{- toYaml .Values.containerSecurityContext | nindent 12 }}
image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
imagePullPolicy: {{ .Values.image.pullPolicy }}
ports:
- name: http
containerPort: 5000
protocol: TCP
- name: agent-receiver
containerPort: 8000
protocol: TCP
{{- if .Values.probes.startup.enabled }}
startupProbe:
httpGet:
path: {{ include "checkmk.probePath" . }}
port: http
initialDelaySeconds: {{ .Values.probes.startup.initialDelaySeconds }}
periodSeconds: {{ .Values.probes.startup.periodSeconds }}
timeoutSeconds: {{ .Values.probes.startup.timeoutSeconds }}
failureThreshold: {{ .Values.probes.startup.failureThreshold }}
successThreshold: {{ .Values.probes.startup.successThreshold }}
{{- end }}
{{- if .Values.probes.liveness.enabled }}
livenessProbe:
httpGet:
path: {{ include "checkmk.probePath" . }}
port: http
periodSeconds: {{ .Values.probes.liveness.periodSeconds }}
timeoutSeconds: {{ .Values.probes.liveness.timeoutSeconds }}
failureThreshold: {{ .Values.probes.liveness.failureThreshold }}
successThreshold: {{ .Values.probes.liveness.successThreshold }}
{{- end }}
{{- if .Values.probes.readiness.enabled }}
readinessProbe:
httpGet:
path: {{ include "checkmk.probePath" . }}
port: http
periodSeconds: {{ .Values.probes.readiness.periodSeconds }}
timeoutSeconds: {{ .Values.probes.readiness.timeoutSeconds }}
failureThreshold: {{ .Values.probes.readiness.failureThreshold }}
successThreshold: {{ .Values.probes.readiness.successThreshold }}
{{- end }}
env:
- name: CMK_PASSWORD
valueFrom:
secretKeyRef:
name: {{ include "checkmk.secretName" . }}
key: {{ .Values.config.adminPassword.passwordKey }}
- name: CMK_SITE_ID
value: {{ .Values.config.siteId | quote }}
- name: TZ
value: {{ .Values.config.timezone | quote }}
{{- if .Values.config.livestatusTcp }}
- name: CMK_LIVESTATUS_TCP
value: "on"
{{- end }}
{{- if .Values.config.mailRelayHost }}
- name: MAIL_RELAY_HOST
value: {{ .Values.config.mailRelayHost | quote }}
{{- end }}
{{- with .Values.extraEnv }}
{{- toYaml . | nindent 12 }}
{{- end }}
volumeMounts:
- name: sites
mountPath: /omd/sites
# tmpfs for site temp dir — improves performance by using host RAM
# equivalent to Docker's --tmpfs /opt/omd/sites/<siteId>/tmp:uid=1000,gid=1000
- name: tmp
mountPath: {{ include "checkmk.tmpPath" . }}
{{- with .Values.extraVolumeMounts }}
{{- toYaml . | nindent 12 }}
{{- end }}
resources:
{{- toYaml .Values.resources | nindent 12 }}
volumes:
{{- if .Values.persistence.enabled }}
- name: sites
persistentVolumeClaim:
claimName: {{ if .Values.persistence.existingClaim }}{{ .Values.persistence.existingClaim }}{{ else }}{{ include "checkmk.fullname" . }}-sites{{ end }}
{{- else }}
- name: sites
emptyDir: {}
{{- end }}
- name: tmp
emptyDir:
medium: Memory
{{- with .Values.extraVolumes }}
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}

View File

@ -0,0 +1,43 @@
{{- if .Values.ingress.enabled -}}
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: {{ include "checkmk.fullname" . }}
labels:
{{- include "checkmk.labels" . | nindent 4 }}
{{- with .Values.ingress.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
{{- if .Values.ingress.className }}
ingressClassName: {{ .Values.ingress.className }}
{{- end }}
{{- if .Values.ingress.tls }}
tls:
{{- range .Values.ingress.tls }}
- hosts:
{{- range .hosts }}
- {{ . | quote }}
{{- end }}
{{- if .secretName }}
secretName: {{ .secretName }}
{{- end }}
{{- end }}
{{- end }}
rules:
{{- range .Values.ingress.hosts }}
- host: {{ .host | quote }}
http:
paths:
{{- range .paths }}
- path: {{ .path }}
pathType: {{ .pathType }}
backend:
service:
name: {{ include "checkmk.fullname" $ }}
port:
number: {{ $.Values.service.port }}
{{- end }}
{{- end }}
{{- end }}

View File

@ -0,0 +1,21 @@
{{- if and .Values.persistence.enabled (not .Values.persistence.existingClaim) }}
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ include "checkmk.fullname" . }}-sites
labels:
{{- include "checkmk.labels" . | nindent 4 }}
{{- with .Values.persistence.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
accessModes:
- {{ .Values.persistence.accessMode | quote }}
{{- if .Values.persistence.storageClass }}
storageClassName: {{ .Values.persistence.storageClass | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.persistence.size | quote }}
{{- end }}

View File

@ -0,0 +1,11 @@
{{- if not .Values.config.adminPassword.existingSecret }}
apiVersion: v1
kind: Secret
metadata:
name: {{ include "checkmk.fullname" . }}-secrets
labels:
{{- include "checkmk.labels" . | nindent 4 }}
type: Opaque
data:
{{ .Values.config.adminPassword.passwordKey }}: {{ .Values.config.adminPassword.value | default "changeme" | b64enc }}
{{- end }}

View File

@ -0,0 +1,25 @@
apiVersion: v1
kind: Service
metadata:
name: {{ include "checkmk.fullname" . }}
labels:
{{- include "checkmk.labels" . | nindent 4 }}
spec:
type: {{ .Values.service.type }}
ports:
- port: {{ .Values.service.port }}
targetPort: http
protocol: TCP
name: http
- port: {{ .Values.service.agentReceiverPort }}
targetPort: agent-receiver
protocol: TCP
name: agent-receiver
{{- if .Values.config.livestatusTcp }}
- port: 6557
targetPort: 6557
protocol: TCP
name: livestatus
{{- end }}
selector:
{{- include "checkmk.selectorLabels" . | nindent 4 }}

131
charts/checkmk/values.yaml Normal file
View File

@ -0,0 +1,131 @@
## Global settings
nameOverride: ""
fullnameOverride: ""
## Image settings
image:
repository: checkmk/check-mk-community
tag: "2.5.0p6"
pullPolicy: IfNotPresent
## Deployment settings
replicaCount: 1
revisionHistoryLimit: 3
# Pod security settings
# Checkmk (OMD) requires root to manage monitoring sites and switch to site users.
# fsGroup: 1000 matches Docker's --tmpfs uid=1000,gid=1000 so the site user can write to tmp.
podSecurityContext:
runAsNonRoot: false
runAsUser: 0
fsGroup: 1000
containerSecurityContext:
allowPrivilegeEscalation: true
readOnlyRootFilesystem: false
## Pod scheduling
nodeSelector: {}
tolerations: []
affinity: {}
## Pod annotations
podAnnotations: {}
## Service settings
service:
type: ClusterIP
port: 5000
agentReceiverPort: 8000
## Ingress settings
ingress:
enabled: false
className: ""
annotations:
traefik.ingress.kubernetes.io/router.entrypoints: websecure
hosts:
- host: checkmk.domain.com
paths:
- path: /
pathType: Prefix
tls:
- hosts:
- checkmk.domain.com
# secretName: "existing-tls-secret"
## Persistence settings for /omd/sites (all site data, configs, and RRDs)
persistence:
enabled: true
existingClaim: ""
storageClass: ""
accessMode: ReadWriteOnce
size: 5Gi
annotations: {}
## Resource limits and requests
# resources:
# limits:
# cpu: 2000m
# memory: 2Gi
# requests:
# cpu: 500m
# memory: 512Mi
## Application health checks
# startupProbe absorbs slow first-boot (site init + DB creation) so liveness/readiness
# don't fire until the site is actually up. Budget: 120 * 10s = 20 minutes max.
probes:
startup:
enabled: true
initialDelaySeconds: 30
periodSeconds: 10
timeoutSeconds: 10
failureThreshold: 120
successThreshold: 1
liveness:
enabled: true
periodSeconds: 30
timeoutSeconds: 10
failureThreshold: 6
successThreshold: 1
readiness:
enabled: true
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 3
successThreshold: 1
## Checkmk configuration
config:
# Site name — also determines the URL path: /<siteId>/check_mk/
siteId: "cmk"
# Timezone (e.g. Europe/Berlin)
timezone: "UTC"
# Enable Livestatus TCP access (for distributed monitoring or external tools).
# When enabled, port 6557 is added to the Service.
livestatusTcp: false
# SMTP relay host for notifications (leave empty to disable)
mailRelayHost: ""
## Admin (cmkadmin) password
adminPassword:
# Use an existing Kubernetes secret
existingSecret: ""
passwordKey: "cmk-password"
# Or set directly (not recommended for production)
value: "changeme"
# Extra environment variables
extraEnv: []
# - name: CMK_LIVESTATUS_TCP
# value: "on"
# Extra volume mounts
extraVolumeMounts: []
# Extra volumes
extraVolumes: []