集群健康工具

我就是我 2022-10-05 05:55 296阅读 0赞

kubenetes集群可以采用普罗米修斯和grafana进行监控，比如监控资源占用率、容器指标信息等，普罗米修斯用于采集数据，grafana对数据分析及可视化。

在安装监控组件前，要保证集群各个节点与windows系统时间同步

$ yum install ntpdate -y
    $ ntpdate time.windows.com

# 一 部署普罗米修斯 #

1 部署守护进程node-exporter.yaml

[root@k8smaster k8s-prometheus-grafana-master]# cat node-exporter.yaml
    ---
    apiVersion: apps/v1
    kind: DaemonSet
    metadata:
      name: node-exporter
      namespace: kube-system
      labels:
        k8s-app: node-exporter
    spec:
      selector:
        matchLabels:
          k8s-app: node-exporter
      template:
        metadata:
          labels:
            k8s-app: node-exporter
        spec:
          containers:
          - image: prom/node-exporter
            name: node-exporter
            ports:
            - containerPort: 9100
              protocol: TCP
              name: http
    ---
    apiVersion: v1
    kind: Service
    metadata:
      labels:
        k8s-app: node-exporter
      name: node-exporter
      namespace: kube-system
    spec:
      ports:
      - name: http
        port: 9100
        nodePort: 31672
        protocol: TCP
      type: NodePort
      selector:
        k8s-app: node-exporter

[root@k8smaster k8s-prometheus-grafana-master]# kubectl create -f node-exporter.yaml

2 部署rbac-setup.yaml

[root@k8smaster prometheus]# cat rbac-setup.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: v1
    kind: ServiceAccount
    metadata:
      name: prometheus
      namespace: kube-system
    ---
    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: kube-system

[root@k8smaster prometheus]# kubectl create -f rbac-setup.yaml

3 部署configmap.yaml

[root@k8smaster prometheus]# cat configmap.yaml
    apiVersion: v1
    kind: ConfigMap
    metadata:
      name: prometheus-config
      namespace: kube-system
    data:
      prometheus.yml: |
        global:
          scrape_interval:     15s
          evaluation_interval: 15s
        scrape_configs:
    
        - 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'
          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
    
        - job_name: 'kubernetes-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-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-services'
          kubernetes_sd_configs:
          - role: service
          metrics_path: /probe
          params:
            module: [http_2xx]
          relabel_configs:
          - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]
            action: keep
            regex: true
          - source_labels: [__address__]
            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_service_label_(.+)
          - source_labels: [__meta_kubernetes_namespace]
            target_label: kubernetes_namespace
          - source_labels: [__meta_kubernetes_service_name]
            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

4 部署 prometheus.deploy.yml

[root@k8smaster prometheus]# cat  prometheus.deploy.yml
    ---
    apiVersion: apps/v1
    kind: Deployment
    metadata:
      labels:
        name: prometheus-deployment
      name: prometheus
      namespace: kube-system
    spec:
      replicas: 1
      selector:
        matchLabels:
          app: prometheus
      template:
        metadata:
          labels:
            app: prometheus
        spec:
          containers:
          - image: prom/prometheus:v2.0.0
            name: prometheus
            command:
            - "/bin/prometheus"
            args:
            - "--config.file=/etc/prometheus/prometheus.yml"
            - "--storage.tsdb.path=/prometheus"
            - "--storage.tsdb.retention=24h"
            ports:
            - containerPort: 9090
              protocol: TCP
            volumeMounts:
            - mountPath: "/prometheus"
              name: data
            - mountPath: "/etc/prometheus"
              name: config-volume
            resources:
              requests:
                cpu: 100m
                memory: 100Mi
              limits:
                cpu: 500m
                memory: 2500Mi
          serviceAccountName: prometheus
          volumes:
          - name: data
            emptyDir: {}
          - name: config-volume
            configMap:
              name: prometheus-config

[root@k8smaster prometheus]# kubectl create -f prometheus.deploy.yml

5 部署 prometheus.svc.yml

[root@k8smaster prometheus]# cat  prometheus.svc.yml
    ---
    kind: Service
    apiVersion: v1
    metadata:
      labels:
        app: prometheus
      name: prometheus
      namespace: kube-system
    spec:
      type: NodePort
      ports:
      - port: 9090
        targetPort: 9090
        nodePort: 30003
      selector:
        app: prometheus

[root@k8smaster prometheus]# kubectl create -f prometheus.svc.yml

# 二 部署grafana #

1 部署grafana-deploy.yaml

[root@k8smaster grafana]# cat grafana-deploy.yaml
    apiVersion: apps/v1
    kind: Deployment
    metadata:
      name: grafana-core
      namespace: kube-system
      labels:
        app: grafana
        component: core
    spec:
      replicas: 1
      selector:
        matchLabels:
          app: grafana
          component: core
      template:
        metadata:
          labels:
            app: grafana
            component: core
        spec:
          containers:
          - image: grafana/grafana:4.2.0
            name: grafana-core
            imagePullPolicy: IfNotPresent
            # env:
            resources:
              # keep request = limit to keep this container in guaranteed class
              limits:
                cpu: 100m
                memory: 100Mi
              requests:
                cpu: 100m
                memory: 100Mi
            env:
              # The following env variables set up basic auth twith the default admin user and admin password.
              - name: GF_AUTH_BASIC_ENABLED
                value: "true"
              - name: GF_AUTH_ANONYMOUS_ENABLED
                value: "false"
              # - name: GF_AUTH_ANONYMOUS_ORG_ROLE
              #   value: Admin
              # does not really work, because of template variables in exported dashboards:
              # - name: GF_DASHBOARDS_JSON_ENABLED
              #   value: "true"
            readinessProbe:
              httpGet:
                path: /login
                port: 3000
              # initialDelaySeconds: 30
              # timeoutSeconds: 1
            volumeMounts:
            - name: grafana-persistent-storage
              mountPath: /var
          volumes:
          - name: grafana-persistent-storage
            emptyDir: {}

[root@k8smaster grafana]# kubectl create -f grafana-deploy.yaml

2 部署 grafana-svc.yaml

[root@k8smaster grafana]# cat  grafana-svc.yaml
    apiVersion: v1
    kind: Service
    metadata:
      name: grafana
      namespace: kube-system
      labels:
        app: grafana
        component: core
    spec:
      type: NodePort
      ports:
        - port: 3000
      selector:
        app: grafana
        component: core

[root@k8smaster grafana]# kubectl create -f grafana-svc.yaml

3 部署 grafana-ing.yaml

[root@k8smaster grafana]# cat  grafana-ing.yaml
    apiVersion: extensions/v1beta1
    kind: Ingress
    metadata:
       name: grafana
       namespace: kube-system
    spec:
       rules:
       - host: k8s.grafana
         http:
           paths:
           - path: /
             backend:
              serviceName: grafana
              servicePort: 3000

# 可以域名访问grafana
    [root@k8smaster grafana]# kubectl create -f grafana-ing.yaml

# 三 配置 #

# 查看服务
    kubectl get svc -n kube-system

使用上面的端口进行访问grafana，按如下进行配置数据源和模板

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpYW5nd2VubWFpbA_size_16_color_FFFFFF_t_70][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpYW5nd2VubWFpbA_size_16_color_FFFFFF_t_70 1][]

配好之后就可以使用了

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpYW5nd2VubWFpbA_size_16_color_FFFFFF_t_70 2][]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpYW5nd2VubWFpbA_size_16_color_FFFFFF_t_70]: /images/20221005/c1f0850421564c858f06ea622a071ccc.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpYW5nd2VubWFpbA_size_16_color_FFFFFF_t_70 1]: /images/20221005/ef54c480c42641e6af4590cad9c62ec0.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpYW5nd2VubWFpbA_size_16_color_FFFFFF_t_70 2]: /images/20221005/d84df289e78b4654ad02f0cfd297ea92.png