Kubernetes监控体系(8)-prometheus监控k8s组件-静态配置

  • Post author:
  • Post category:其他


1.prometheus监控kube-schedule组件

第一种方法:
创建kube-scheduler的service
cat kube-scheduler-service.yaml

apiVersion: v1
kind: Service
metadata:
  annotations:
    prometheus.io/port: "32107"
    prometheus.io/scrape: "true"
  labels:
    component: kube-scheduler
    tier: control-plane
  name: kube-scheduler
  namespace: kube-system
spec:
  clusterIP:
  ports:
  - name: metrics
    port: 10251
    protocol: TCP
    targetPort: 10251
    nodePort: 32107
  selector:
    component: kube-scheduler
    tier: control-plane
  type: NodePort


kubectl apply -f kube-scheduler-service.yaml




第二种方法:
kubectl delete -f kube-scheduler-service.yaml
修改prometheus-cfg.yaml文件,新增一个job,用来监控kube-scheduler
cat  prometheus-cfg.yaml
---
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 
    - job_name: 'kubernetes-schedule'
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.124.16:10251']



kubectl delete -f prometheus-cfg.yaml
kubectl apply  -f prometheus-cfg.yaml

kubectl delete -f prometheus-deploy.yaml 
kubectl apply -f prometheus-deploy.yaml 

2.prometheus监控kube-controller-manager组件

第一种方法:
创建kube-controller-manager的service

cat kube-controller-manager.yaml
apiVersion: v1
kind: Service
metadata:
  annotations:
    prometheus.io/port: "32108"
    prometheus.io/scrape: "true"
  labels:
    component: kube-controller-manager
    tier: control-plane
  name: kube-controller
  namespace: kube-system
spec:
  clusterIP:
  ports:
  - name: metrics
    port: 10252
    protocol: TCP
    targetPort: 10252
    nodePort: 32108
  selector:
    component: kube-controller-manager
    tier: control-plane
  type: NodePort

kubectl apply -f kube-controller-manager.yaml

集群外部访问k8s集群中pod应用,流量走向:物理节点ip:port--->service ip:port-->pod ip:port

第二种方法:
kubectl delete -f kube-controller-manager.yaml

修改prometheus-cfg的yaml文件,新增一个job来监控kube-controller-manager
cat prometheus-cfg.yaml
---
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 
    - job_name: 'kubernetes-schedule'
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.124.16:10251']
    - job_name: 'kubernetes-controller-manager'
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.124.16:10252']


kubectl delete -f prometheus-cfg.yaml
kubectl apply  -f prometheus-cfg.yaml

kubectl delete -f prometheus-deploy.yaml 
kubectl apply -f prometheus-deploy.yaml 

3.prometheus监控kube-proxy组件


kube-proxy默认监听的地址是127.0.0.1:10249,想要修改监听的端口,按如下方法
kubectl edit configmap kube-proxy -n kube-system
把metricsBindAddress这段修改成metricsBindAddress: 0.0.0.0:10249

然后重新启动kube-proxy这个pod
kubectl get pods -n kube-system | grep kube-proxy |awk '{print $1}' | xargs kubectl delete pods -n kube-system

ss  -antulp |grep :10249
可显示如下
[root@k8s-master ~]# ss -antulp | grep :10249
tcp    LISTEN     0      128    [::]:10249        

cat prometheus-cfg.yaml
---
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 
    - job_name: 'kubernetes-schedule'
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.124.16:10251']
    - job_name: 'kubernetes-controller-manager'
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.124.16:10252']
    - job_name: 'kubernetes-kube-proxy'
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.124.16:10249','192.168.124.26:10249']


kubectl apply  -f prometheus-cfg.yaml

kubectl delete -f prometheus-deploy.yaml 
kubectl apply -f prometheus-deploy.yaml 

4.prometheus监控etcd组件

1.在k8s-master节点建secret,将需要的etcd证书保存到secret对象etcd-certs中:
kubectl -n monitor-sa create secret generic etcd-certs --from-file=/etc/kubernetes/pki/etcd/server.key  --from-file=/etc/kubernetes/pki/etcd/server.crt --from-file=/etc/kubernetes/pki/etcd/ca.crt


2.在k8s-master节点查看创建的secret
kubectl get secret -n monitor-sa|grep etcd-certs

修改prometheus-deploy.yaml文件,添加secrets,即将创建的secret对象"etcd-certs"通过volumes挂载方式,添加到prometheus-deploy.yaml部署文件中,如下所示:
 - name: k8s-certs
   mountPath: /var/run/secrets/kubernetes.io/k8s-certs/etcd/
和
 - name: k8s-certs
          secret:
            secretName: etcd-certs
变成下面这样
        volumeMounts:
        - mountPath: /etc/prometheus/prometheus.yml
          name: prometheus-config
          subPath: prometheus.yml
        - mountPath: /prometheus/
          name: prometheus-storage-volume
        - name: k8s-certs
          mountPath: /var/run/secrets/kubernetes.io/k8s-certs/etcd/

      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
        - name: k8s-certs
          secret:
           secretName: etcd-certs

修改之后的prometheus-deploy.yaml文件如下所示:
---
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-node
      serviceAccountName: monitor
      containers:
      - name: prometheus
        image: prom/prometheus:v2.2.1
        imagePullPolicy: IfNotPresent
        command:
          - prometheus
          - --config.file=/etc/prometheus/prometheus.yml
          - --storage.tsdb.path=/prometheus
          - --storage.tsdb.retention=720h
        ports:
        - containerPort: 9090
          protocol: TCP
        volumeMounts:
        - mountPath: /etc/prometheus/prometheus.yml
          name: prometheus-config
          subPath: prometheus.yml
        - mountPath: /prometheus/
          name: prometheus-storage-volume
        - mountPath: /var/run/secrets/kubernetes.io/k8s-certs/etcd/
          name: k8s-certs
      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
        - name: k8s-certs
          secret:
            secretName: etcd-certs



3.修改prometheus-cfg.yaml文件,增加如下job

 - job_name: 'kubernetes-etcd'
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/ca.crt
        cert_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.crt
        key_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.key
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.124.16:2379']

修改之后的prometheus-cfg.yaml文件如下所示:
---
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 
    - job_name: 'kubernetes-schedule'
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.124.16:10251']
    - job_name: 'kubernetes-controller-manager'
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.124.16:10252']
    - job_name: 'kubernetes-kube-proxy'
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.124.16:10249','192.168.124.26:10249']
    - job_name: 'kubernetes-etcd'
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/ca.crt
        cert_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.crt
        key_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.key
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.124.16:2379']

kubectl apply  -f prometheus-cfg.yaml

kubectl delete -f prometheus-deploy.yaml 
kubectl apply -f prometheus-deploy.yaml 



版权声明:本文为yujia_666原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。