kube-prometheus部署

一、自定义配置(二选一，不建议用这个)

grafana-service.yml

apiVersion: v1
kind: Service
metadata:
  name: grafana
  namespace: kube-monitoring
  labels:
    app: grafana
    component: core
spec:
  type: NodePort
  ports:
    - port: 3000
      nodePort: 30011
  selector:
    app: grafana
    component: core

grafana-statefulset.yml

apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: grafana-core
  namespace: kube-monitoring
  labels:
    app: grafana
    component: core
spec:
  serviceName: "grafana"
  selector:
    matchLabels:
      app: grafana
  replicas: 1
  template:
    metadata:
      labels:
        app: grafana
        component: core
    spec:
      containers:
      - image: grafana/grafana:6.5.3
        name: grafana-core
        imagePullPolicy: IfNotPresent
        env:
          # The following env variables set up basic auth twith the default admin user and admin password.
          - name: GF_AUTH_BASIC_ENABLED
            value: "true"
          - name: GF_AUTH_ANONYMOUS_ENABLED
            value: "false"
          # - name: GF_AUTH_ANONYMOUS_ORG_ROLE
          #   value: Admin
          # does not really work, because of template variables in exported dashboards:
          # - name: GF_DASHBOARDS_JSON_ENABLED
          #   value: "true"
        readinessProbe:
          httpGet:
            path: /login
            port: 3000
          # initialDelaySeconds: 30
          # timeoutSeconds: 1
        volumeMounts:
        - name: grafana-persistent-storage
          mountPath: /var/lib/grafana
          subPath: grafana
  volumeClaimTemplates:
  - metadata:
      name: grafana-persistent-storage
    spec:
      storageClassName: managed-nfs-storage
      accessModes:
      - ReadWriteOnce
      resources:
        requests:
          storage: "1Gi"

 kube-monitoring.yml

apiVersion: v1
kind: Namespace
metadata:
  name: kube-monitoring

prometheus-config.yml

apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: kube-monitoring
data:
  prometheus.yml: |
    global:
      scrape_interval: 15s 
      evaluation_interval: 15s
    scrape_configs:
      - job_name: 'prometheus'
        static_configs:
        - targets: ['localhost:9090']

      - job_name: 'kubernetes-nodes'
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        kubernetes_sd_configs:
        - role: node

      - job_name: 'kubernetes-service'
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        kubernetes_sd_configs:
        - role: service

      - job_name: 'kubernetes-endpoints'
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        kubernetes_sd_configs:
        - role: endpoints

      - job_name: 'kubernetes-ingress'
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        kubernetes_sd_configs:
        - role: ingress

      - job_name: 'kubernetes-kubelet'
        scheme: https
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        kubernetes_sd_configs:
        - role: node
        relabel_configs:
        - action: labelmap
          regex: __meta_kubernetes_node_label_(.+)
        - target_label: __address__
          replacement: kubernetes.default.svc:443
        - source_labels: [__meta_kubernetes_node_name]
          regex: (.+)
          target_label: __metrics_path__
          replacement: /api/v1/nodes/${1}/proxy/metrics

      - job_name: 'kubernetes-cadvisor'
        scheme: https
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        kubernetes_sd_configs:
        - role: node
        relabel_configs:
        - target_label: __address__
          replacement: kubernetes.default.svc:443
        - source_labels: [__meta_kubernetes_node_name]
          regex: (.+)
          target_label: __metrics_path__
          replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
        - action: labelmap
          regex: __meta_kubernetes_node_label_(.+)

      - job_name: 'kubernetes-pods'
        kubernetes_sd_configs:
        - role: pod
        relabel_configs:
        - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
          action: keep
          regex: true
        - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
          action: replace
          target_label: __metrics_path__
          regex: (.+)
        - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
          action: replace
          regex: ([^:]+)(?::\d+)?;(\d+)
          replacement: $1:$2
          target_label: __address__
        - action: labelmap
          regex: __meta_kubernetes_pod_label_(.+)
        - source_labels: [__meta_kubernetes_namespace]
          action: replace
          target_label: kubernetes_namespace
        - source_labels: [__meta_kubernetes_pod_name]
          action: replace
          target_label: kubernetes_pod_name

      - job_name: 'kubernetes-apiservers'
        kubernetes_sd_configs:
        - role: endpoints
        scheme: https
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        relabel_configs:
        - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
          action: keep
          regex: default;kubernetes;https
        - target_label: __address__
          replacement: kubernetes.default.svc:443

      - job_name: 'kubernetes-services'
        metrics_path: /probe
        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: [__address__]
          target_label: __param_target
        - target_label: __address__
          replacement: blackbox-exporter.default.svc.cluster.local: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-ingresses'
        metrics_path: /probe
        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.default.svc.cluster.local: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

 prometheus-daemonset.yml

apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: node-exporter
  namespace: kube-monitoring
spec:
  selector:
    matchLabels:
      app: node-exporter
  template:
    metadata:
      annotations:
        prometheus.io/scrape: 'true'
        prometheus.io/port: '9100'
        prometheus.io/path: 'metrics'
      labels:
        app: node-exporter
      name: node-exporter
    spec:
      containers:
      - image: prom/node-exporter
        imagePullPolicy: IfNotPresent
        name: node-exporter
        ports:
        - containerPort: 9100
          hostPort: 9100
          name: scrape
      hostNetwork: true
      hostPID: true

prometheus-deploy.yml

apiVersion: v1
kind: Service
metadata:
  name: prometheus
  labels:
    name: prometheus
spec:
  ports:
  - name: prometheus
    protocol: TCP
    port: 9090
    targetPort: 9090
  selector:
    app: prometheus
  type: NodePort
---
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    name: prometheus
  name: prometheus
spec:
  replicas: 1
  selector:
    app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      containers:
      - name: prometheus
        image: prom/prometheus:v2.2.1
        command:
        - "/bin/prometheus"
        args:
        - "--config.file=/etc/prometheus/prometheus.yml"
        ports:
        - containerPort: 9090
          protocol: TCP
        volumeMounts:
        - mountPath: "/etc/prometheus"
          name: prometheus-config
      volumes:
      - name: prometheus-config
        configMap:
          name: prometheus-config

 prometheus-deployment.yml

apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    name: prometheus
  name: prometheus
  namespace: kube-monitoring
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      serviceAccountName: prometheus
      serviceAccount: prometheus
      containers:
      - name: prometheus
        image: prom/prometheus:v2.2.1
        command:
        - "/bin/prometheus"
        args:
        - "--config.file=/etc/prometheus/prometheus.yml"
        ports:
        - containerPort: 9090
          protocol: TCP
        volumeMounts:
        - mountPath: "/etc/prometheus"
          name: prometheus-config
        - mountPath: "/etc/localtime"
          name: timezone
      volumes:
      - name: prometheus-config
        configMap:
          name: prometheus-config
      - name: timezone
        hostPath:
          path: /usr/share/zoneinfo/Asia/Shanghai

prometheus-rbac-setup.yml

apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: prometheus
rules:
- apiGroups: [""]
  resources:
  - nodes
  - nodes/proxy
  - services
  - endpoints
  - pods
  verbs: ["get", "list", "watch"]
- apiGroups:
  - extensions
  resources:
  - ingresses
  verbs: ["get", "list", "watch"]
- nonResourceURLs: ["/metrics"]
  verbs: ["get"]
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: prometheus
  namespace: kube-monitoring
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: prometheus
subjects:
- kind: ServiceAccount
  name: prometheus
  namespace: kube-monitoring

 prometheus-service.yml

apiVersion: v1
kind: Service
metadata:
  name: prometheus
  labels:
    name: prometheus
  namespace: kube-monitoring
spec:
  ports:
  - name: prometheus
    protocol: TCP
    port: 9090
    targetPort: 9090
  selector:
    app: prometheus
  type: NodePort

把这些文件传到/opt/k8s/k8s/prometheus下

 kubectl apply -f prometheus/kube-monitoring.yml

 kubectl apply -f prometheus/

#查看

kubectl get all -n kube-monitoring

grafana访问地址：

prometheus访问地址：

二、kube-prometheus部署（二选一，建议用这个）

#在github上面下载kube-prometheus

https://github.com/prometheus-operator/kube-prometheus.git

注意下载版本要跟k8s兼容

我这里k8s是1.23,我用kube-prometheus的release-0.10

#替换国内镜像

sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' prometheusOperator-deployment.yaml
sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' prometheus-prometheus.yaml
sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' alertmanager-alertmanager.yaml
sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' kubeStateMetrics-deployment.yaml
sed -i 's/k8s.gcr.io/lank8s.cn/g' kubeStateMetrics-deployment.yaml
sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' nodeExporter-daemonset.yaml
sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' prometheusAdapter-deployment.yaml
sed -i 's/k8s.gcr.io/lank8s.cn/g' prometheusAdapter-deployment.yaml

# 查看是否还有国外镜像
grep "image: " * -r

#修改访问入口(选择是用这个还是配置ingress)

分别修改 prometheus、alertmanager、grafana 中的 spec.type 为 NodePort 方便测试访问

#安装

kubectl create -f manifests/setup/

kubectl apply -f manifests/

#检查

kubectl get all -n monitoring

kubectl get pod -n monitoring

kubectl get svc -n monitoring

#配置ingress（注意，需要先装ingress-nginx。或者也可以不执行这个，用上一步改nodeport也行，就是为了k8s集群外可以访问到prometheus、alertmanager、grafana的界面）

# 创建 ingress
kubectl apply -f prometheus-ingress.yaml 

# 通过域名访问（没有域名可以在主机配置 hosts）
192.168.113.121 grafana.wolfcode.cn
192.168.113.121 prometheus.wolfcode.cn
192.168.113.121 alertmanager.wolfcode.cn

# 创建 prometheus-ingress.yaml
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  namespace: monitoring
  name: prometheus-ingress
spec:
  ingressClassName: nginx
  rules:
  - host: grafana.wolfcode.cn  # 访问 Grafana 域名
    http:
      paths:
      - path: /
        pathType: Prefix
        backend:
          service:
            name: grafana
            port:
              number: 3000
  - host: prometheus.wolfcode.cn  # 访问 Prometheus 域名
    http:
      paths:
      - path: /
        pathType: Prefix
        backend:
          service:
            name: prometheus-k8s 
            port:
              number: 9090
  - host: alertmanager.wolfcode.cn  # 访问 alertmanager 域名
    http:
      paths:
      - path: /
        pathType: Prefix
        backend:
          service:
            name: alertmanager-main
            port:
              number: 9093

#卸载

kubectl delete --ignore-not-found=true -f manifests/ -f manifests/setup