k8s安装Prometheus+Grafana：
1.在kubernetest集群中创建namespace：
[root@master k8s-promethus]# cat namespace.yaml
apiVersion: v1
kind: Namespace
metadata:
name: ns-monitor
labels:
name: ns-monitor
[root@master k8s-promethus]# kubectl apply -f namespace.yaml
2.安装node-exporter:
[root@master k8s-promethus]# cat node-exporter.yaml
kind: DaemonSet
apiVersion: apps/v1
metadata:
labels:
app: node-exporter
name: node-exporter
namespace: ns-monitor
spec:
revisionHistoryLimit: 10
selector:
matchLabels:
app: node-exporter
template:
metadata:
labels:
app: node-exporter
spec:
containers:
- name: node-exporter
image: prom/node-exporter:v0.16.0
ports:
- containerPort: 9100
protocol: TCP
name: http
hostNetwork: true
hostPID: true
tolerations:
- effect: NoSchedule
operator: Exists
---
kind: Service
apiVersion: v1
metadata:
labels:
app: node-exporter
name: node-exporter-service
namespace: ns-monitor
spec:
ports:
- name: http
port: 9100
protocol: TCP
type: NodePort
selector:
app: node-exporter
[root@master k8s-promethus]# kubectl apply -f node-exporter.yaml
[root@master k8s-promethus]# kubectl get pod -n ns-monitor -o wide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
node-exporter-cl6d5 1/1 Running 15 3h15m 192.168.100.64 test <none> <none>
node-exporter-gwwnj 1/1 Running 0 3h15m 192.168.100.201 node1 <none> <none>
node-exporter-hbglm 1/1 Running 0 3h15m 192.168.100.200 master <none> <none>
node-exporter-kwsfv 1/1 Running 0 3h15m 192.168.100.202 node2 <none> <none>
[root@master k8s-promethus]# kubectl get svc -n ns-monitor
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
node-exporter-service NodePort 10.99.128.173 <none> 9100:30372/TCP 3h17m
访问测试：
说明：node-exporter已经运行在成功。
3.部署Prometheus ：
注意：prometheus.yaml 中包含rbac认证、ConfigMap等
[root@master k8s-promethus]# kubectl apply -f prometheus.yaml
clusterrole.rbac.authorization.k8s.io/prometheus unchanged
serviceaccount/prometheus unchanged
clusterrolebinding.rbac.authorization.k8s.io/prometheus unchanged
configmap/prometheus-conf unchanged
configmap/prometheus-rules unchanged
persistentvolume/prometheus-data-pv unchanged
persistentvolumeclaim/prometheus-data-pvc unchanged
deployment.apps/prometheus unchanged
service/prometheus-service unchanged
注意：这里prometheus是用的pv,pvc做本地存储。所以，需要在这之前需要部署好nfs，此处省略部署nfs
[root@master k8s-promethus]# kubectl get pv -n ns-monitor
NAME CAPACITY ACCESSMODES RECLAIM POLICY STATUS CLAIM STORAGECLASS REASON AGE
prometheus-data-pv 5Gi RWO Recycle Bound ns-monitor/prometheus-data-pvc 157m
[root@master k8s-promethus]# kubectl get pvc -n ns-monitor
NAME STATUS VOLUME CAPACITY ACCESS MODES STORAGECLASS AGE
prometheus-data-pvc Bound prometheus-data-pv 5Gi RWO 158m
说明：此时pvc已经成功绑定pv.
[root@master k8s-promethus]# kubectl get pod -n ns-monitor
NAME READY STATUS RESTARTS AGE
node-exporter-cl6d5 1/1 Running 15 3h27m
node-exporter-gwwnj 1/1 Running 0 3h27m
node-exporter-hbglm 1/1 Running 0 3h27m
node-exporter-kwsfv 1/1 Running 0 3h27m
prometheus-dd69c4889-qwmww 1/1 Running 0 161m
[root@master k8s-promethus]# kubectl get svc -n ns-monitor
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
node-exporter-service NodePort 10.99.128.173 <none> 9100:30372/TCP 3h29m
prometheus-service NodePort 10.96.119.235 <none> 9090:31555/TCP 162m
访问测试：
说明：prometheus已经成功运行。
4.在kubernetest中部署grafana：
[root@master k8s-promethus]# cat grafana.yaml
apiVersion: v1
kind: PersistentVolume
metadata:
name: "grafana-data-pv"
labels:
name: grafana-data-pv
release: stable
spec:
capacity:
storage: 5Gi
accessModes:
- ReadWriteOnce
persistentVolumeReclaimPolicy: Recycle
nfs:
path: /data/volumes/v2
server: 192.168.100.64
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: grafana-data-pvc
namespace: ns-monitor
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 5Gi
selector:
matchLabels:
name: grafana-data-pv
release: stable
---
kind: Deployment
apiVersion: apps/v1
metadata:
labels:
app: grafana
name: grafana
namespace: ns-monitor
spec:
replicas: 1
revisionHistoryLimit: 10
selector:
matchLabels:
app: grafana
template:
metadata:
labels:
app: grafana
spec:
securityContext:
runAsUser: 0
containers:
- name: grafana
image: grafana/grafana:latest
imagePullPolicy: IfNotPresent
env:
- name: GF_AUTH_BASIC_ENABLED
value: "true"
- name: GF_AUTH_ANONYMOUS_ENABLED
value: "false"
readinessProbe:
httpGet:
path: /login
port: 3000
volumeMounts:
- mountPath: /var/lib/grafana
name: grafana-data-volume
ports:
- containerPort: 3000
protocol: TCP
volumes:
- name: grafana-data-volume
persistentVolumeClaim:
claimName: grafana-data-pvc
---
kind: Service
apiVersion: v1
metadata:
labels:
app: grafana
name: grafana-service
namespace: ns-monitor
spec:
ports:
- port: 3000
targetPort: 3000
selector:
app: grafana
type: NodePort
[root@master k8s-promethus]# kubectl apply -f grafana.yaml
persistentvolume/grafana-data-pv unchanged
persistentvolumeclaim/grafana-data-pvc unchanged
deployment.apps/grafana unchanged
service/grafana-service unchanged
注意：此时grafana也需要pvc.
[root@master k8s-promethus]# kubectl get pv,pvc -n ns-monitor
NAME CAPACITY ACCESS MODES RECLAIM POLICY STATUS CLAIM STORAGECLASS REASON AGE
persistentvolume/grafana-data-pv 5Gi RWO Recycle Bound ns-monitor/grafana-data-pvc 164m
persistentvolume/prometheus-data-pv 5Gi RWO Recycle Bound ns-monitor/prometheus-data-pvc 168m
NAME STATUS VOLUME CAPACITY ACCESS MODES STORAGECLASS AGE
persistentvolumeclaim/grafana-data-pvc Bound grafana-data-pv 5Gi RWO 164m
persistentvolumeclaim/prometheus-data-pvc Bound prometheus-data-pv 5Gi RWO 168m
[root@master k8s-promethus]# kubectl get pod -n ns-monitor
NAME READY STATUS RESTARTS AGE
grafana-576db894c6-4qtcl 1/1 Running 0 166m
node-exporter-cl6d5 1/1 Running 15 3h36m
node-exporter-gwwnj 1/1 Running 0 3h36m
node-exporter-hbglm 1/1 Running 0 3h36m
node-exporter-kwsfv 1/1 Running 0 3h36m
prometheus-dd69c4889-qwmww 1/1 Running 0 169m
[root@master k8s-promethus]# kubectl get svc -n ns-monitor
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
grafana-service NodePort 10.104.174.223 <none> 3000:30771/TCP 166m
node-exporter-service NodePort 10.99.128.173 <none> 9100:30372/TCP 3h37m
prometheus-service NodePort 10.96.119.235 <none> 9090:31555/TCP 170m
访问测试：
说明：Grafana已经部署完成，用户名/密码:admin/admin
添加数据源：URL=http://prometheus-service.ns-monitor.svc.cluster.local:9090
导入模板：
