标签：node kubectl monitor 系统 yaml prometheus 监控 root

准备

官网：

创建命名空间：

mkdir -p /root/prometheus && cd /root/prometheus
cat > monitor-sa.yaml <<"EOF"
kind: Namespace
apiVersion: v1
metadata:
  name: monitor-sa
EOF

查看命名空间：

kubectl apply -f  monitor-sa.yaml
kubectl get namespace  monitor-sa
NAME         STATUS   AGE
monitor-sa   Active   37s

1. node-export安装

镜像地址：https://hub.docker.com/r/prom/node-exporter/tags

github：https://github.com/prometheus/node_exporter

mkdir -p /root/prometheus && cd /root/prometheus
cat > node-export.yaml <<"EOF"
apiVersion: apps/v1
kind: DaemonSet #可以保证k8s集群的每个节点都运行完全一样的pod
metadata:
  name: node-exporter
  namespace: monitor-sa
  labels:
    name: node-exporter
spec:
  selector:
    matchLabels:
     name: node-exporter
  template:
    metadata:
      labels:
        name: node-exporter
    spec:
      hostPID: true # 使用主机的PID
      hostIPC: true # 使用主机的IPC
      hostNetwork: true # 使用主机的网络
      containers:
      - name: node-exporter
        image: prom/node-exporter:v1.3.0
        ports:
        - containerPort: 9100
        resources:
          requests:
            cpu: 0.15
        securityContext: # 开启特权模式，以root运行容器
          privileged: true
        args:
        - --path.procfs=/host/proc
        - --path.sysfs=/host/sys
        - --path.rootfs=/host
        - --collector.filesystem.ignored-mount-points
        - '"^/(sys|proc|dev|host|etc)($|/)"'
        volumeMounts:
        - name: dev
          mountPath: /host/dev
        - name: proc
          mountPath: /host/proc
        - name: sys
          mountPath: /host/sys
        - name: rootfs
          mountPath: /rootfs
      tolerations: # 配置容忍度，可以容忍master节点的污点，master节点也需要收集数据
      - key: "node-role.kubernetes.io/master"
        operator: "Exists"
        effect: "NoSchedule"
      volumes: # 下面定义的是宿主机的目录，挂载到容器内
        - name: proc
          hostPath:
            path: /proc
        - name: dev
          hostPath:
            path: /dev
        - name: sys
          hostPath:
            path: /sys
        - name: rootfs
          hostPath:
            path: /
EOF

创建node-export：

kubectl apply -f node-export.yaml
kubectl get pod -n monitor-sa
NAME                  READY   STATUS    RESTARTS   AGE
node-exporter-4f568   1/1     Running   0          17s
node-exporter-l2nw7   1/1     Running   0          17s
node-exporter-m58ps   1/1     Running   0          17s

# 查看端口
netstat -lntup | grep 9100
tcp6       0      0 :::9100                 :::*                    LISTEN      1407112/node_export

# 查看数据采集数据
curl http://localhost:9100/metrics

# 显示本地主机cpu使用情况
curl http://localhost:9100/metrics | grep node_cpu_seconds

# 查看负载
curl http://localhost:9100/metrics | grep node_load

注：node-export默认的监听端口是9100，可以看到当前主机获取到的所有监控数据。

netstat -lntup | grep 9100
tcp6       0      0 :::9100                 :::*                    LISTEN      3045628/node_export

报错处理，使用prom/node-exporter:v0.16.0出现的问题，本地是已经挂载了这个目录，但是出现报错，干脆直接升级镜像到prom/node-exporter:v1.3.0，重启Prometheus，发现可以了，可以观察node-exporter容器的日志和监控模版磁盘读写速率的数据有没有出现。

kubectl logs -f -n monitor-sa node-exporter-4f568
time="2023-03-11T04:54:35Z" level=error msg="ERROR: diskstats collector failed after 0.000281s: invalid line for /host/proc/diskstats for sda" source="collector.go:132"
time="2023-03-11T04:54:50Z" level=error msg="ERROR: diskstats collector failed after 0.001121s: invalid line for /host/proc/diskstats for sr0" source="collector.go:132"
time="2023-03-11T04:55:05Z" level=error msg="ERROR: diskstats collector failed after 0.000325s: invalid line for /host/proc/diskstats for sr0" source="collector.go:132"
time="2023-03-11T04:55:20Z" level=error msg="ERROR: diskstats collector failed after 0.000349s: invalid line for /host/proc/diskstats for sr1" source="collector.go:132"
time="2023-03-11T04:55:35Z" level=error msg="ERROR: diskstats collector failed after 0.001031s: invalid line for /host/proc/diskstats for sr1" source="collector.go:132"

2. 部署prometheus server

2.1 创建sa账号

rbac文件内容：

mkdir -p /root/prometheus && cd /root/prometheus
cat > rbac.yaml <<"EOF"
apiVersion: v1
kind: ServiceAccount
metadata:
  name: prometheus
  namespace: monitor-sa
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: prometheus
rules:
- apiGroups:
  - ""
  resources:
  - nodes
  - services
  - endpoints
  - pods
  - nodes/proxy
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - configmaps
  - nodes/metrics
  verbs:
  - get
- nonResourceURLs:
  - /metrics
  verbs:
  - get
---
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: monitor-sa
EOF

创建rbac：

kubectl apply -f rbac.yaml

2.2 创建数据目录

prometheus在哪个节点部署就在哪个节点上创建目录

mkdir -p /data
chmod 777 /data/

2.3 部署prometheus

2.3.1 prometheus.yml文件配置

ConfigMap文件内容：

mkdir -p /root/prometheus && cd /root/prometheus
cat > prometheus-cfg.yaml <<"EOF"
---
kind: ConfigMap
apiVersion: v1
metadata:
  labels:
    app: prometheus
  name: prometheus-config
  namespace: monitor-sa
data:
  prometheus.yml: |
    global:
      scrape_interval: 15s
      scrape_timeout: 10s
      evaluation_interval: 1m
    scrape_configs:
    - job_name: 'kubernetes-node'
      kubernetes_sd_configs:
      - role: node
      relabel_configs:
      - source_labels: [__address__]
        regex: '(.*):10250'
        replacement: '${1}:9100'
        target_label: __address__
        action: replace
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
    - job_name: 'kubernetes-node-cadvisor'
      kubernetes_sd_configs:
      - role:  node
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      relabel_configs:
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
      - target_label: __address__
        replacement: kubernetes.default.svc:443
      - source_labels: [__meta_kubernetes_node_name]
        regex: (.+)
        target_label: __metrics_path__
        replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
    - job_name: 'kubernetes-apiserver'
      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
    - job_name: 'kubernetes-service-endpoints'
      kubernetes_sd_configs:
      - role: endpoints
      relabel_configs:
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
        action: replace
        target_label: __scheme__
        regex: (https?)
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
        action: replace
        target_label: __metrics_path__
        regex: (.+)
      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
        action: replace
        target_label: __address__
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
      - action: labelmap
        regex: __meta_kubernetes_service_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_service_name]
        action: replace
        target_label: kubernetes_name
EOF

创建configmap：

# kubectl apply -f prometheus-cfg.yaml
configmap/prometheus-config created

# kubectl get configmaps  -n monitor-sa
NAME                DATA   AGE
prometheus-config   1      29s

2.3.2 prometheus Deployment创建

镜像地址：https://hub.docker.com/r/prom/prometheus/tags

查看node节点名称，将服务创建到k8s-node01节点上（这里如果想部署到master需要注意节点的污点）。

kubectl get node | awk '{print $1}'
NAME
k8s-master01
k8s-node01
k8s-node02

deployments文件内容：

mkdir -p /root/prometheus && cd /root/prometheus
cat > prometheus-deploy.yaml <<"EOF"
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus-server
  namespace: monitor-sa
  labels:
    app: prometheus
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
      component: server
    #matchExpressions:
    #- {key: app, operator: In, values: [prometheus]}
    #- {key: component, operator: In, values: [server]}
  template:
    metadata:
      labels:
        app: prometheus
        component: server
      annotations:
        prometheus.io/scrape: 'false'
    spec:
      nodeName: k8s-node01  # 注意这里node01的名称，根据本地填写让pod调度到这个节点上面
      serviceAccountName: prometheus
      containers:
      - name: prometheus
        image: prom/prometheus:v2.37.6
        imagePullPolicy: IfNotPresent
        command:
          - prometheus
          - --config.file=/etc/prometheus/prometheus.yml
          - --storage.tsdb.path=/prometheus
          - --storage.tsdb.retention=720h
          - --web.enable-lifecycle
        ports:
        - containerPort: 9090
          protocol: TCP
        volumeMounts:
        - mountPath: /etc/prometheus/prometheus.yml
          name: prometheus-config
          subPath: prometheus.yml
        - mountPath: /prometheus/
          name: prometheus-storage-volume
      volumes:
        - name: prometheus-config
          configMap:
            name: prometheus-config
            items:
              - key: prometheus.yml
                path: prometheus.yml
                mode: 0644
        - name: prometheus-storage-volume
          hostPath:
           path: /data
           type: Directory
EOF

创建deployments：

# kubectl apply -f prometheus-deploy.yaml
deployment.apps/prometheus-server created

# kubectl get pod -n monitor-sa
NAME                                 READY   STATUS    RESTARTS   AGE
node-exporter-4f568                  1/1     Running   0          5h41m
node-exporter-l2nw7                  1/1     Running   0          5h41m
node-exporter-m58ps                  1/1     Running   0          5h41m
prometheus-server-858c97464f-b4czn   1/1     Running   0          3m57s

2.3.3 prometheus svc创建

svc文件内容：

mkdir -p /root/prometheus && cd /root/prometheus
cat > prometheus-svc.yaml <<"EOF"
apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: monitor-sa
  labels:
    app: prometheus
spec:
  type: NodePort
  ports:
    - port: 9090
      targetPort: 9090
      protocol: TCP
  selector:
    app: prometheus
    component: server
EOF

创建svc（这里我们使用的是用node节点的port去访问）：

# kubectl apply -f prometheus-svc.yaml
service/prometheus created

# kubectl get svc -n monitor-sa
NAME         TYPE       CLUSTER-IP      EXTERNAL-IP   PORT(S)          AGE
prometheus   NodePort   10.101.117.42   <none>        9090:30170/TCP   11h

访问地址：http://{任意主机ip地址}:30170

注：如果查看这样页面没数据最好去看看prometheus-server容器的log日志。

level=error ts=2023-03-09T13:09:18.515651655Z caller=main.go:216 component=k8s_client_runtime err="github.com/prometheus/prometheus/discovery/kubernetes/kubernetes.go:269: Failed to list *v1.Service: services is forbidden: User \"system:serviceaccount:monitor-sa:monitor\" cannot list resource \"services\" in API group \"\" at the cluster scope: RBAC: clusterrole.rbac.authorization.k8s.io \"cluster-admin\\u00a0\" not found"

这里是因为ClusterRole授权有问题。

3. Grafana安装和配置

3.1 部署Grafana

镜像地址：https://hub.docker.com/r/grafana/grafana

mkdir -p /root/prometheus && cd /root/prometheus
cat > Grafana.yaml <<"EOF"
apiVersion: apps/v1
kind: Deployment
metadata:
  name: monitoring-grafana
  namespace: monitor-sa
spec:
  replicas: 1
  selector:
    matchLabels:
      task: monitoring
      k8s-app: grafana
  template:
    metadata:
      labels:
        task: monitoring
        k8s-app: grafana
    spec:
      securityContext:
        fsGroup: 472
        supplementalGroups:
          - 0
      containers:
      - name: grafana
        image: grafana/grafana:9.4.3
        imagePullPolicy: IfNotPresent
        ports:
        - containerPort: 3000
          protocol: TCP
        volumeMounts:
        - mountPath: /var/lib/grafana
          name: grafana-storage
        - mountPath: /etc/ssl/certs
          name: ca-certificates
          readOnly: true
        env:
        - name: INFLUXDB_HOST
          value: monitoring-influxdb
        - name: GF_SERVER_HTTP_PORT
          value: "3000"
          # The following env variables are required to make Grafana accessible via
          # the kubernetes api-server proxy. On production clusters, we recommend
          # removing these env variables, setup auth for grafana, and expose the grafana
          # service using a LoadBalancer or a public IP.
        - name: GF_AUTH_BASIC_ENABLED
          value: "false"
        - name: GF_AUTH_ANONYMOUS_ENABLED
          value: "true"
        - name: GF_AUTH_ANONYMOUS_ORG_ROLE
          value: Admin
        - name: GF_SERVER_ROOT_URL
          # If you're only using the API Server proxy, set this value instead:
          # value: /api/v1/namespaces/kube-system/services/monitoring-grafana/proxy
          value: /
      volumes:
      - name: ca-certificates
        hostPath:
          path: /etc/ssl/certs
      - name: grafana-storage
        emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
  labels:
    # For use as a Cluster add-on (https://github.com/kubernetes/kubernetes/tree/master/cluster/addons)
    # If you are NOT using this as an addon, you should comment out this line.
    kubernetes.io/cluster-service: 'true'
    kubernetes.io/name: monitoring-grafana
  name: monitoring-grafana
  namespace: monitor-sa
spec:
  # In a production setup, we recommend accessing Grafana through an external Loadbalancer
  # or through a public IP.
  # type: LoadBalancer
  # You could also use NodePort to expose the service at a randomly-generated port
  # type: NodePort
  ports:
  - port: 80
    targetPort: 3000
  selector:
    k8s-app: grafana
  type: NodePort
EOF

创建Grafana：

# kubectl apply -f Grafana.yaml
deployment.apps/monitoring-grafana created
service/monitoring-grafana created

# 查看pod启动情况
kubectl get pods -n kube-system| grep monitor
monitoring-grafana-5b4bb4c64b-5qwxj        1/1     Running   0                41s

# 查看svc
kubectl get svc -n kube-system | grep grafana
monitoring-grafana            NodePort    10.101.25.22   <none>        80:31478/TCP                   17m