Prometheus 容器化部署

实验部署

工作中是基于kube-api的自动发现

1、创建账户绑定集群

kubectl create serviceaccount monitor -n monitor-sa 
#创建账户
kubectl create clusterrolebinding monitor-clusterrolebinding -n monitor-sa --clusterrole=cluster-admin  --serviceaccount=monitor-sa:monitor
#绑定集群

2、node-exporter发现节点

先部署node-exporter发现节点：

apiVersion: apps/v1
kind: DaemonSet
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
      hostIPC: true
      hostNetwork: true
#表示共用节点服务器的网络，进程号和进程间的通信命名空间
      containers:
      - name: node-exporter
        image: prom/node-exporter
        ports:
        - containerPort: 9100
        resources:
          limits:
            cpu: "0.5"
        securityContext:
          privileged: true
#给容器在节点服务器上拥有所有权限
        args:
        - --path.procfs
        - /host/proc
        - --path.sysfs
        - /host/sys
        - --collector.filesystem.ignored-mount-points
        - '"^/(sys|proc|dev|host|etc)($|/)"'
#收集节点系统配置，网络配置，硬件设备，主机信息
        volumeMounts:
        - name: dev
          mountPath: /host/dev
        - name: proc
          mountPath: /host/proc
        - name: sys
          mountPath: /host/sys
        - name: rootfs
          mountPath: /rootfs
      volumes:
        - name: proc
          hostPath:
            path: /proc
        - name: dev
          hostPath:
            path: /dev
        - name: sys
          hostPath:
            path: /sys
        - name: rootfs
          hostPath:
            path: /

3、创建configmap，传输配置文件

apiVersion: v1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     
kind: ConfigMap
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
 
    - job_name: 'kubernetes-ingresses'
      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.example.com: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
 
    - 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

注释
apiVersion: v1
kind: ConfigMap
matadata:
  labels:
    app: prometheus
  name: prometheus-config
  namespace: monitor-sa
data:
  prometheus.yaml:
    global:
      scrape_interval: 15s
      scrape_timeout: 10s
      evaluation_interval: 1m
   scrape_configs:
   - job_name: 'kubernetes-node'
     kubernetes_sd_configs:
#*_sd_configs,是promQL的语法，使用k8s的服务发现
     - role: node
#使用默认kubernets提供的http端口，发现集群中的每个node
     relabel_configs:
#重新标记
     - source_labels: [_address_]
#匹配原始的标签
       regex: '(.*):10250'
#匹配10250端口的url
       replacement: '${1}:9100'
       target_label: _address_
#把新生成的URL是${1}获取的ip:192.168.233.81:9100---->传给address
       action: replace
     - action: labelmap
#替换动作
       regex: _meta_kubernets_node_label_(.+)
#匹配下面的正则表达式，保留node的标签，否则只会展示instance,这些主要是为了获取和匹配node节点的信息
   - 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_kubernets

3.1、热更新修改configmap方式

curl -X POST -Ls http://10.244.1.45:9090/-/reload
#热更新的方式。不要直接delete。线上环境一定要热更新
#线上重启，千万不要Delete重启，会数据丢失

4、部署Prometheus：

apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus-server
  namespace: monitor-sa
  labels:
    app: prometheus
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
      component: server
  template:
    metadata:
      labels:
        app: prometheus
        component: server
      annotations:
        prometheus.io/scrape: 'false'
#prometheus能够获取集群的信息
    spec:
      serviceAccountName: monitor
      initContainers:
      - name: init-chmod
        image: busybox:latest
#busybox是最精简版的centos系统
        command: ['sh','-c','chmod -R 777 /prometheus;chmod -R 777 /etc']
        volumeMounts:
        - mountPath: /prometheus
          name: prometheus-storage-volume
        - mountPath: /etc/localtime
          name: timezone
      containers:
      - name: prometheus
        image: prom/prometheus:v2.45.0
        command:
          - prometheus
          - --config.file=/etc/prometheus/prometheus.yml
          - --storage.tsdb.path=/prometheus
          - --storage.tsdb.retention=720h
          - --web.enable-lifecycle
        ports:
        - containerPort: 9090
        volumeMounts:
        - name: prometheus-config
          mountPath: /etc/prometheus/prometheus.yml
          subPath: prometheus.yml
        - mountPath: /prometheus/
          name: prometheus-storage-volume
        - name: timezone
          mountPath: /etc/localtime
      volumes:
        - name: prometheus-config
          configMap:
            name: prometheus-config
            defaultMode: 0777
        - name: prometheus-storage-volume
          hostPath:
            path: /data
            type: Directory
        - name: timezone
          hostPath:
            path: /usr/share/zoneinfo/Asia/Shanghai

5、部署service提供外部访问：

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

 6、安装grafana可视化工具

apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: grafana
  namespace: kube-system
spec:
  accessModes:
    - ReadWriteMany
  storageClassName: nfs-client-storageclass
  resources:
    requests:
      storage: 2Gi
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: monitoring-grafana
  namespace: kube-system
spec:
  replicas: 1
  selector:
    matchLabels:
      task: monitoring
      k8s-app: grafana
  template:
    metadata:
      labels:
        task: monitoring
        k8s-app: grafana
    spec:
      containers:
      - name: grafana
        image: grafana/grafana:7.5.11
        securityContext:
          runAsUser: 104
          runAsGroup: 107
        ports:
        - containerPort: 3000
          protocol: TCP
        volumeMounts:
        - mountPath: /etc/ssl/certs
          name: ca-certificates
          readOnly: false
        - mountPath: /var
          name: grafana-storage
        - mountPath: /var/lib/grafana
          name: graf-test
        env:
        - name: INFLUXDB_HOST
          value: monitoring-influxdb
        - name: GF_SERVER_HTTP_PORT
          value: "3000"
        - 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
          value: /
      volumes:
      - name: ca-certificates
        hostPath:
          path: /etc/ssl/certs
      - name: grafana-storage
        emptyDir: {}
      - name: graf-test
        persistentVolumeClaim:
          claimName: grafana
---
apiVersion: v1
kind: Service
metadata:
  labels:
  name: monitoring-grafana
  namespace: kube-system
spec:
  ports:
  - port: 80
    targetPort: 3000
  selector:
    k8s-app: grafana
  type: NodePort

[root@node01 ~]# mkdir -p /data
[root@master01 node]# kubectl get pod -n monitor-sa -o wide
NAME                                 READY   STATUS    RESTARTS   AGE     IP               NODE       NOMINATED NODE   READINESS GATES
node-exporter-f9825                  1/1     Running   0          34m     192.168.233.83   node02     <none>           <none>
node-exporter-pklzk                  1/1     Running   0          34m     192.168.233.81   master01   <none>           <none>
node-exporter-xnfxv                  1/1     Running   0          34m     192.168.233.82   node01     <none>           <none>
prometheus-server-76bd89b95b-cdbqb   1/1     Running   0          29m     10.244.2.11      node02     <none>           <none>
prometheus-server-76bd89b95b-lgpr2   1/1     Running   0          3m22s   10.244.0.3       master01   <none>           <none>
prometheus-server-76bd89b95b-mx5gd   1/1     Running   0          29m     10.244.1.12      node01     <none>           <none>

 

[root@master01 node]# yum -y install stress
[root@master01 node]# stress --cpu 2
stress: info: [72419] dispatching hogs: 2 cpu, 0 io, 0 vm, 0 hdd
压力测试