#在k8s中部署prometheus所用到的yaml文件都托管在github
git clone https://github.com/bibinwilson/kubernetes-prometheus.git
#部署kube-state-metric所用到的yaml文件都托管在github上
git clone https://github.com/devopscube/kube-state-metrics-configs.git

一：创建namespace

kubectl create namespace monitoring

二：配置RBAC访问策略

#clusterRole.yaml
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: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: prometheus
subjects:
- kind: ServiceAccount
  name: default
  namespace: monitoring

三：配置SVC和deployment

#prometheus-deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus-deployment
  namespace: monitoring
  labels:
    app: prometheus-server
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus-server
  template:
    metadata:
      labels:
        app: prometheus-server
    spec:
      containers:
        - name: prometheus
          image: prom/prometheus
          args:
            - "--config.file=/etc/prometheus/prometheus.yml"
            - "--storage.tsdb.path=/prometheus/"
          ports:
            - containerPort: 9090
          volumeMounts:
            - name: prometheus-config-volume
              mountPath: /etc/prometheus/
            - name: prometheus-storage-volume
              mountPath: /prometheus/
      volumes:
        - name: prometheus-config-volume
          configMap:
            defaultMode: 420
            name: prometheus-server-conf

        - name: prometheus-storage-volume
          emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
  name: prometheus-service
  namespace: monitoring
  annotations:
      prometheus.io/scrape: 'true'
      prometheus.io/port:   '9090'

spec:
  selector:
    app: prometheus-server
  type: NodePort
  ports:
    - port: 8080
      targetPort: 9090
      nodePort: 30000

四：将prometheus文件持久化出来,包含了node节点，pod，container，以及各个组件的监控信息

#config-map.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-server-conf
  labels:
    name: prometheus-server-conf
  namespace: monitoring
data:
  prometheus.rules: |-
    groups:
    - name: devopscube demo alert
      rules:
      - alert: High Pod Memory
        expr: sum(container_memory_usage_bytes) > 1
        for: 1m
        labels:
          severity: slack
        annotations:
          summary: High Memory Usage
  prometheus.yml: |-
    global:
      scrape_interval: 5s
      evaluation_interval: 5s
    rule_files:
      - /etc/prometheus/prometheus.rules
    alerting:
      alertmanagers:
      - scheme: http
        static_configs:
        - targets:
          - "alertmanager.monitoring.svc:9093"

    scrape_configs:
      - job_name: 'node-exporter'
        kubernetes_sd_configs:
          - role: endpoints
        relabel_configs:
        - source_labels: [__meta_kubernetes_endpoints_name]
          regex: 'node-exporter'
          action: keep

      - 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

      - job_name: 'kubernetes-nodes'

        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-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: 'kube-state-metrics'
        static_configs:
          - targets: ['kube-state-metrics.monitoring.svc.cluster.local:8080']

      - 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:
        - 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-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

五：应用配置并检测，确认常用指标是UP状态

kubectl create -f clusterRole.yaml
kubectl create -f config-map.yaml
kubectl create -f prometheus-deployment.yaml

访问prometheus网页
http://10.0.0.11:30000

六：配置kube-state-metrics监控pod信息

git clone https://github.com/devopscube/kube-state-metrics-configs.git
#1:提前去下载kube-state-metrics:v2.3.0镜像，并将tag改成k8s.gcr.io/kube-state-metrics/kube-state-metrics:v2.3.0
docker pull registry.cn-wulanchabu.aliyuncs.com/moge1/kube-state-metrics:v2.3.0
#2：将目录下的yaml文件namespace换成刚刚新建的monitoring

#创建资源
kubectl create -f ./

七：网页检测状态是否为UP

image.png

八：对接grafana

apiVersion: apps/v1
kind: Deployment
metadata:
  name: grafana-server
  namespace: monitoring
spec:
  replicas: 1
  selector:
    matchLabels:
      app: grafana
  template:
    metadata:
      labels:
        app: grafana
    spec:
      imagePullSecrets:   #如果公网镜像，删除这段
      - name: registry-pps
      containers:
      - name: grafana-server
        imagePullPolicy: IfNotPresent
        image: registry.drifter.net/grafana:5.0.4
        ports:
        - containerPort: 3000
          protocol: TCP
        volumeMounts:
        - mountPath: /etc/ssl/certs
          name: ca-certificates
          readOnly: true
        - mountPath: /var
          name: grafana-storage
        env:
        - name: INFLUXDB_HOST
          value: monitoring-influxdb
        - name: GF_SERVER_HTTP_PORT
          value: "3000"
        - name: GF_AUTH_BASIC_ENABLED
          value: "true"
        - name: GF_SECURITY_ADMIN_USER
          value: admin
        - name: GF_SECURITY_ADMIN_PASSWORD
          value: admin        
        - name: GF_SERVER_ROOT_URL
          value: /
      volumes:
      - name: ca-certificates
        hostPath:
          path: /etc/ssl/certs
      - name: grafana-storage  #这里数据为持久化，可以自己配置PV/PVC进行持久化
        emptyDir: {}
---        
apiVersion: v1
kind: Service
metadata:
  labels:
    kubernetes.io/cluster-service: 'true'
    kubernetes.io/name: grafana-server
  name: grafana-server
  namespace: monitoring
spec:
  ports:
  - port: 80
    targetPort: 3000
  selector:
    app: grafana

#网页访问
http://10.0.0.11:3000

添加数据源

image.png

grafana配置用户和dashboard权限请参照该文档

https://help.aliyun.com/document_detail/438736.html?scm=20140722.S_help%40%40%E6%96%87%E6%A1%A3%40%40438736._.ID_438736-RL_%E5%AE%81%E6%B3%A2%E7%BD%91%E4%B8%8A%E6%8A%A5%E7%A8%8E%E5%B0%8F%E8%A7%84%E6%A8%A1%E7%BA%B3%E7%A8%8E%E4%BA%BA-LOC_main-OR_ser-V_2-P0_1455

纯内网环境如何将告警信息推送至钉钉,可以借鉴该文档

https://blog.csdn.net/qq_34777982/article/details/125813641