k8s prometheus 搭建和采集配置文件解析

部署yaml文件

cat << EOF >> prometheus.yaml
apiVersion: v1
kind: Namespace
metadata:
  name: monitor
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: prometheus
  namespace: monitor
---
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:
  - "extensions"
  resources:
    - ingresses
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - configmaps
  - nodes/metrics
  verbs:
  - get
- nonResourceURLs:
  - /metrics
  verbs:
  - get
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRoleBinding
metadata:
  name: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: prometheus
subjects:
- kind: ServiceAccount
  name: prometheus
  namespace: monitor
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: monitor
data:
  prometheus.yml: |
    global:
      scrape_interval: 15s
      evaluation_interval: 15s
    scrape_configs:
    - job_name: 'prometheus'
      static_configs:
      - targets: ['localhost:9090']
    - job_name: 'kubernetes-apiserver'
      static_configs:
      - targets: ['10.96.0.1']
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        insecure_skip_verify: true
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
    - job_name: 'kubernetes-sd-node-exporter'
      kubernetes_sd_configs:
        - role: node
      relabel_configs:
      - source_labels: [__address__]
        regex: '(.*):10250'
        replacement: '${1}:9100'
        target_label: __address__
        action: replace
    - job_name: 'kubernetes-sd-cadvisor'
      kubernetes_sd_configs:
        - role: node
      scheme: https
	        tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        insecure_skip_verify: true
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      relabel_configs:
      - target_label: __metrics_path__
        replacement: /metrics/cadvisor
    - job_name: 'kubernetes-sd-kubelet'
      kubernetes_sd_configs:
        - role: node
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        insecure_skip_verify: true
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
    - job_name: 'kubernetes-sd-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_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
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_service_name]
        action: replace
        target_label: kubernetes_name
      - source_labels: [__meta_kubernetes_pod_name]
        action: replace
        target_label: kubernetes_pod_name
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus
  namespace: monitor
  labels:
    app: prometheus
spec:
  selector:
    matchLabels:
      app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      serviceAccountName: prometheus
      nodeSelector:
        app: prometheus
      initContainers:
      - name: "change-permission-of-directory"
        image: busybox
        command: ["/bin/sh"]
        args: ["-c", "chown -R 65534:65534 /prometheus"]
        securityContext:
          privileged: true
        volumeMounts:
        - mountPath: "/etc/prometheus"
          name: config-volume
        - mountPath: "/prometheus"
          name: data
      containers:
      - image: prom/prometheus:v2.19.2
        name: prometheus
        args:
        - "--config.file=/etc/prometheus/prometheus.yml"
        - "--storage.tsdb.path=/prometheus"  # 指定tsdb数据路径
        - "--web.enable-lifecycle"  # 支持热更新，直接执行localhost:9090/-/reload立即生效
        - "--web.console.libraries=/usr/share/prometheus/console_libraries"
        - "--web.console.templates=/usr/share/prometheus/consoles"
        ports:
        - containerPort: 9090
          name: http
        volumeMounts:
        - mountPath: "/etc/prometheus"
          name: config-volume
        - mountPath: "/prometheus"
          name: data
        resources:
          requests:
            cpu: 100m
            memory: 512Mi
          limits:
            cpu: 100m
            memory: 512Mi
      volumes:
      - name: data
        hostPath:
          path: /root/data/prometheus/
      - configMap:
          name: prometheus-config
        name: config-volume
---
apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: monitor
  labels:
    app: prometheus
spec:
  selector:
    app: prometheus
  type: ClusterIP
  ports:
    - name: web
      port: 9090
      targetPort: http
---
apiVersion: extensions/v1beta1
kind: Ingress
metadata:
  name: prometheus
  namespace: monitor
spec:
  ingressClassName: nginx
  rules:
  - host: prometheus.test.com
    http:
      paths:
      - path: /
        backend:
          serviceName: prometheus
          servicePort: 9090
EOF

配置文件说明

1、默认采集prometheus指标
    - job_name: 'prometheus'
      static_configs:
      - targets: ['localhost:9090']
2、采集apiserver指标（配置token认证）
- job_name: 'kubernetes-apiserver'
      static_configs:
      - targets: ['10.96.0.1']
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        insecure_skip_verify: true
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
3、采集node_exporter指标（包含端口替换和node服务发现）
   - job_name: 'kubernetes-sd-node-exporter'
      kubernetes_sd_configs:
        - role: node
      relabel_configs:
      - source_labels: [__address__]
        regex: '(.*):10250'
        replacement: '${1}:9100'
        target_label: __address__
        action: replace
4、采集容器相关指标（包含指标路径替换和node服务发现）
    - job_name: 'kubernetes-sd-cadvisor'
      kubernetes_sd_configs:
        - role: node
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        insecure_skip_verify: true
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      relabel_configs:
      - target_label: __metrics_path__
        replacement: /metrics/cadvisor
5、采集cord_dns指标（包含endpoints服务发现）
    - job_name: 'kubernetes-sd-endpoints'
      kubernetes_sd_configs:
      - role: endpoints
      relabel_configs:
	# 包含prometheus_io_scrape注释并且值为true则保留
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
        action: keep
        regex: true
	# 获取prometheus_io_path 并替换到 __metrics_path__
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
        action: replace
        target_label: __metrics_path__
        regex: (.+)
	# 获取prometheus_io_port 替换到 __address__ ，?: --> 非获取匹配
      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
        action: replace
        target_label: __address__
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_service_name]
        action: replace
        target_label: kubernetes_name
      - source_labels: [__meta_kubernetes_pod_name]
        action: replace
        target_label: kubernetes_pod_name