ivanch/haven-ops
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

adding monitoring

Browse Source
This commit is contained in:
ivanch
2026-08-29 14:20:59 -03:00
parent 2c15b1f668
commit 19da5f6deb
5 changed files with 566 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/monitoring/grafana.yaml
+127
View File
@@ -0,0 +1,127 @@
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app: grafana
name: grafana
namespace: monitoring
spec:
selector:
matchLabels:
app: grafana
template:
metadata:
labels:
app: grafana
spec:
securityContext:
fsGroup: 472
supplementalGroups:
- 0
containers:
- name: grafana
image: grafana/grafana:latest
imagePullPolicy: Always
ports:
- containerPort: 3000
name: http-grafana
protocol: TCP
readinessProbe:
failureThreshold: 3
httpGet:
path: /robots.txt
port: 3000
scheme: HTTP
initialDelaySeconds: 10
periodSeconds: 30
successThreshold: 1
timeoutSeconds: 2
livenessProbe:
failureThreshold: 3
initialDelaySeconds: 30
periodSeconds: 10
successThreshold: 1
tcpSocket:
port: 3000
timeoutSeconds: 1
resources:
requests:
cpu: 250m
memory: 750Mi
limits:
memory: 1Gi
cpu: 500m
volumeMounts:
- mountPath: /var/lib/grafana
name: grafana-pv
volumes:
- name: grafana-pv
persistentVolumeClaim:
claimName: grafana-pvc
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: grafana-pvc
namespace: monitoring
annotations:
nfs.io/storage-path: "grafana-data"
spec:
storageClassName: "nfs-client"
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 1Gi
---
apiVersion: v1
kind: Service
metadata:
namespace: monitoring
name: grafana
spec:
ports:
- port: 3000
protocol: TCP
targetPort: http-grafana
selector:
app: grafana
type: ClusterIP
---
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
namespace: monitoring
name: grafana
spec:
ingressClassName: nginx
rules:
- host: grafana.haven
http:
paths:
- path: /
pathType: Prefix
backend:
service:
name: grafana
port:
number: 3000
---
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
namespace: monitoring
name: grafana-public
spec:
ingressClassName: nginx
rules:
- host: grafanah.ivanch.me
http:
paths:
- path: /
pathType: Prefix
backend:
service:
name: grafana
port:
number: 3000
apps/monitoring/kube-state-metrics.yaml
+145
View File
@@ -0,0 +1,145 @@
apiVersion: v1
kind: ServiceAccount
metadata:
name: kube-state-metrics
namespace: monitoring
labels:
app: kube-state-metrics
app.kubernetes.io/component: exporter
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: 2.19.1
automountServiceAccountToken: false
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: kube-state-metrics
labels:
app: kube-state-metrics
app.kubernetes.io/component: exporter
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: 2.19.1
rules:
- apiGroups: [""]
resources:
- nodes
- pods
- persistentvolumeclaims
verbs: ["list", "watch"]
- apiGroups: ["apps"]
resources:
- statefulsets
- daemonsets
- deployments
- replicasets
verbs: ["list", "watch"]
- apiGroups: ["batch"]
resources:
- cronjobs
- jobs
verbs: ["list", "watch"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: kube-state-metrics
labels:
app: kube-state-metrics
app.kubernetes.io/component: exporter
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: 2.19.1
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: kube-state-metrics
subjects:
- kind: ServiceAccount
name: kube-state-metrics
namespace: monitoring
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: kube-state-metrics
namespace: monitoring
labels:
app: kube-state-metrics
app.kubernetes.io/component: exporter
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: 2.19.1
spec:
replicas: 1
selector:
matchLabels:
app: kube-state-metrics
template:
metadata:
labels:
app: kube-state-metrics
app.kubernetes.io/component: exporter
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: 2.19.1
spec:
automountServiceAccountToken: true
serviceAccountName: kube-state-metrics
nodeSelector:
kubernetes.io/os: linux
containers:
- name: kube-state-metrics
image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.19.1
imagePullPolicy: IfNotPresent
args:
- --resources=cronjobs,daemonsets,deployments,jobs,nodes,persistentvolumeclaims,pods,replicasets,statefulsets
ports:
- name: http-metrics
containerPort: 8080
protocol: TCP
livenessProbe:
httpGet:
path: /livez
port: http-metrics
initialDelaySeconds: 5
timeoutSeconds: 5
readinessProbe:
httpGet:
path: /readyz
port: 8081
initialDelaySeconds: 5
timeoutSeconds: 5
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 65534
seccompProfile:
type: RuntimeDefault
resources:
requests:
cpu: 50m
memory: 64Mi
limits:
cpu: 200m
memory: 256Mi
---
apiVersion: v1
kind: Service
metadata:
name: kube-state-metrics
namespace: monitoring
labels:
app: kube-state-metrics
app.kubernetes.io/component: exporter
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: 2.19.1
spec:
type: ClusterIP
selector:
app: kube-state-metrics
ports:
- name: http-metrics
port: 8080
targetPort: http-metrics
protocol: TCP
apps/monitoring/loki.yaml
+108
View File
@@ -0,0 +1,108 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: loki
namespace: monitoring
spec:
replicas: 1
selector:
matchLabels:
app: loki
template:
metadata:
labels:
app: loki
spec:
containers:
- name: loki
image: grafana/loki:3
args: ["-config.file=/etc/loki/config/config.yaml"]
ports:
- containerPort: 3100
volumeMounts:
- name: config
mountPath: /etc/loki/config
- name: loki-storage
mountPath: /tmp/loki
resources:
requests:
cpu: 100m
memory: 1Gi
limits:
cpu: 200m
memory: 1Gi
volumes:
- name: config
configMap:
name: loki-config
- name: loki-storage
emptyDir:
medium: Memory
---
apiVersion: v1
kind: ConfigMap
metadata:
name: loki-config
namespace: monitoring
data:
config.yaml: |
auth_enabled: true
server:
http_listen_port: 3100
common:
ring:
instance_addr: 127.0.0.1
kvstore:
store: inmemory
replication_factor: 1
path_prefix: /tmp/loki
querier:
multi_tenant_queries_enabled: true
schema_config:
configs:
- from: "2024-01-01"
store: tsdb
object_store: filesystem
schema: v13
index:
prefix: index_
period: 24h
storage_config:
tsdb_shipper:
active_index_directory: /tmp/loki/index
cache_location: /tmp/loki/cache
filesystem:
directory: /tmp/loki/chunks
limits_config:
allow_structured_metadata: true
retention_period: 0
ingester:
lifecycler:
ring:
kvstore:
store: inmemory
replication_factor: 1
chunk_idle_period: 1m
max_chunk_age: 5m
chunk_target_size: 1536000
compactor:
retention_enabled: false
---
apiVersion: v1
kind: Service
metadata:
name: loki
namespace: monitoring
spec:
ports:
- port: 3100
targetPort: 3100
name: http
selector:
app: loki
apps/monitoring/nodeexporter.yaml
+56
View File
@@ -0,0 +1,56 @@
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: node-exporter
namespace: monitoring
labels:
app: node-exporter
spec:
selector:
matchLabels:
app: node-exporter
template:
metadata:
labels:
app: node-exporter
spec:
hostNetwork: true
containers:
- name: node-exporter
image: prom/node-exporter:latest
imagePullPolicy: Always
args:
- "--path.rootfs=/host"
ports:
- containerPort: 9100
hostPort: 9100
name: metrics
protocol: TCP
resources:
requests:
memory: "50Mi"
cpu: "100m"
limits:
memory: "100Mi"
cpu: "200m"
volumeMounts:
- name: host
mountPath: /host
readOnly: true
volumes:
- name: host
hostPath:
path: /
---
apiVersion: v1
kind: Service
metadata:
name: node-exporter
namespace: monitoring
spec:
selector:
app: node-exporter
ports:
- name: metrics
port: 9100
targetPort: metrics
apps/monitoring/prometheus.yaml
+130
View File
@@ -0,0 +1,130 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: prometheus
namespace: monitoring
labels:
app: prometheus
spec:
replicas: 1
selector:
matchLabels:
app: prometheus
template:
metadata:
labels:
app: prometheus
spec:
serviceAccountName: prometheus
containers:
- name: prometheus
image: prom/prometheus:latest
args:
- "--config.file=/etc/prometheus/prometheus.yml"
- "--storage.tsdb.path=/prometheus"
- "--storage.tsdb.retention.time=1d"
- "--web.enable-lifecycle"
ports:
- containerPort: 9090
name: web
volumeMounts:
- name: prometheus-config-volume
mountPath: /etc/prometheus
- name: prometheus-storage
mountPath: /prometheus
resources:
requests:
memory: "500Mi"
cpu: "200m"
limits:
memory: "1Gi"
cpu: "500m"
volumes:
- name: prometheus-config-volume
persistentVolumeClaim:
claimName: prometheus-pvc
- name: prometheus-storage
emptyDir:
medium: Memory
sizeLimit: 256Mi
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: prometheus-pvc
namespace: monitoring
annotations:
nfs.io/storage-path: "prometheus-config"
spec:
storageClassName: "nfs-client"
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 1Gi
---
# Service URL - http://prometheus.monitoring.svc.cluster.local:9090
apiVersion: v1
kind: Service
metadata:
name: prometheus
namespace: monitoring
labels:
app: prometheus
spec:
ports:
- name: web
port: 9090
targetPort: web
selector:
app: prometheus
type: ClusterIP
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: prometheus
namespace: monitoring
labels:
app: prometheus
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: prometheus
namespace: monitoring
labels:
app: prometheus
rules:
- apiGroups: [""]
resources:
- nodes
- nodes/proxy
- services
- endpoints
- pods
verbs: ["get", "list", "watch"]
- apiGroups: ["extensions"]
resources:
- ingresses
verbs: ["get", "list", "watch"]
- apiGroups: ["networking.k8s.io"]
resources:
- ingresses
verbs: ["get", "list", "watch"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: prometheus
namespace: monitoring
labels:
app: prometheus
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: prometheus
subjects:
- kind: ServiceAccount
name: prometheus
namespace: monitoring