zoukankan      html  css  js  c++  java
  • prometheus-数据展示之grafana部署和数据源配置

    1、监控pods 。   prometheus再部署以后,会自带cAdvisor。结果如下:

    2、K8S集群状态监控。需要使用kube-state-metrics插件。部署以后

     kubernetes.io/cluster-service: "true"  会自动启用监控对象,无需配置
    [root@VM_0_48_centos prometheus]# cat  kube-state-metrics-deployment.yaml
    apiVersion: apps/v1
    kind: Deployment
    metadata:
      name: kube-state-metrics
      namespace: kube-system
      labels:
        k8s-app: kube-state-metrics
        kubernetes.io/cluster-service: "true"
        addonmanager.kubernetes.io/mode: Reconcile
        version: v1.3.0
    spec:
      selector:
        matchLabels:
          k8s-app: kube-state-metrics
          version: v1.3.0
      replicas: 1
      template:
        metadata:
          labels:
            k8s-app: kube-state-metrics
            version: v1.3.0
          annotations:
            scheduler.alpha.kubernetes.io/critical-pod: ''
        spec:
          priorityClassName: system-cluster-critical
          serviceAccountName: kube-state-metrics
          containers:
          - name: kube-state-metrics
            image: quay.io/coreos/kube-state-metrics:v1.3.0
            ports:
            - name: http-metrics
              containerPort: 8080
            - name: telemetry
              containerPort: 8081
            readinessProbe:
              httpGet:
                path: /healthz
                port: 8080
              initialDelaySeconds: 5
              timeoutSeconds: 5
          - name: addon-resizer
            image: k8s.gcr.io/addon-resizer:1.8.5
            resources:
              limits:
                cpu: 100m
                memory: 30Mi
              requests:
                cpu: 100m
                memory: 30Mi
            env:
              - name: MY_POD_NAME
                valueFrom:
                  fieldRef:
                    fieldPath: metadata.name
              - name: MY_POD_NAMESPACE
                valueFrom:
                  fieldRef:
                    fieldPath: metadata.namespace
            volumeMounts:
              - name: config-volume
                mountPath: /etc/config
            command:
              - /pod_nanny
              - --config-dir=/etc/config
              - --container=kube-state-metrics
              - --cpu=100m
              - --extra-cpu=1m
              - --memory=100Mi
              - --extra-memory=2Mi
              - --threshold=5
              - --deployment=kube-state-metrics
          volumes:
            - name: config-volume
              configMap:
                name: kube-state-metrics-config
    ---
    # Config map for resource configuration.
    apiVersion: v1
    kind: ConfigMap
    metadata:
      name: kube-state-metrics-config
      namespace: kube-system
      labels:
        k8s-app: kube-state-metrics
        kubernetes.io/cluster-service: "true"
        addonmanager.kubernetes.io/mode: Reconcile
    data:
      NannyConfiguration: |-
        apiVersion: nannyconfig/v1alpha1
        kind: NannyConfiguration

    部署结果展示:

    [root@VM_0_48_centos prometheus]# kubectl  get  svc  -n  kube-system|grep kube-state-metrics   
    kube-state-metrics     ClusterIP   10.0.0.164   <none>        8080/TCP,8081/TCP        3d

    3、node宿主机监控。由于node_exporter  需要监控宿主机状态,不建议采用容器部署。建议采用二进制部署。解压后。

    [root@VM_0_48_centos prometheus]# cat /usr/lib/systemd/system/node_exporter.service 
    [Unit]
    Description=prometheus
    
    [Service]
    Restart=on-failure
    ExecStart=/opt/prometheus/node_exporter/node_exporter   ####需要改为自己的解压后的目录
    
    [Install]
    WantedBy=multi-user.target
    [root@VM_0_48_centos prometheus]# ps -ef|grep node_exporter 
    root     15748     1  0 09:47 ?        00:00:08 /opt/prometheus/node_exporter/node_exporter
    root     16560  4032  0 18:47 pts/0    00:00:00 grep --color=auto node_exporter
    [root@VM_0_48_centos prometheus]# 
    

      

    4、prometheus启用监控目标

    [root@VM_0_48_centos prometheus]# cat  prometheus-configmap.yaml
    # Prometheus configuration format https://prometheus.io/docs/prometheus/latest/configuration/configuration/
    apiVersion: v1
    kind: ConfigMap
    metadata:
      name: prometheus-config
      namespace: kube-system
      labels:
        kubernetes.io/cluster-service: "true"
        addonmanager.kubernetes.io/mode: EnsureExists
    data:
      prometheus.yml: |
        scrape_configs:
        - job_name: prometheus
          static_configs:
          - targets:
            - localhost:9090
        - job_name: node   #####启动node_exporter
          static_configs:
            - targets: 
              - 172.19.0.48:9100  
              - 172.19.0.14:9100
              - 172.19.0.9:9100
              - 172.19.0.2:9100
    
        - job_name: kubernetes-apiservers
          kubernetes_sd_configs:
          - role: endpoints
          relabel_configs:
          - action: keep
            regex: default;kubernetes;https
            source_labels:
            - __meta_kubernetes_namespace
            - __meta_kubernetes_service_name
            - __meta_kubernetes_endpoint_port_name
          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-nodes-kubelet
          kubernetes_sd_configs:
          - role: node
          relabel_configs:
          - action: labelmap
            regex: __meta_kubernetes_node_label_(.+)
          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-nodes-cadvisor
          kubernetes_sd_configs:
          - role: node
          relabel_configs:
          - action: labelmap
            regex: __meta_kubernetes_node_label_(.+)
          - target_label: __metrics_path__
            replacement: /metrics/cadvisor
          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-service-endpoints
          kubernetes_sd_configs:
          - role: endpoints
          relabel_configs:
          - action: keep
            regex: true
            source_labels:
            - __meta_kubernetes_service_annotation_prometheus_io_scrape
          - action: replace
            regex: (https?)
            source_labels:
            - __meta_kubernetes_service_annotation_prometheus_io_scheme
            target_label: __scheme__
          - action: replace
            regex: (.+)
            source_labels:
            - __meta_kubernetes_service_annotation_prometheus_io_path
            target_label: __metrics_path__
          - action: replace
            regex: ([^:]+)(?::d+)?;(d+)
            replacement: $1:$2
            source_labels:
            - __address__
            - __meta_kubernetes_service_annotation_prometheus_io_port
            target_label: __address__
          - action: labelmap
            regex: __meta_kubernetes_service_label_(.+)
          - action: replace
            source_labels:
            - __meta_kubernetes_namespace
            target_label: kubernetes_namespace
          - action: replace
            source_labels:
            - __meta_kubernetes_service_name
            target_label: kubernetes_name
    
        - job_name: kubernetes-services
          kubernetes_sd_configs:
          - role: service
          metrics_path: /probe
          params:
            module:
            - http_2xx
          relabel_configs:
          - action: keep
            regex: true
            source_labels:
            - __meta_kubernetes_service_annotation_prometheus_io_probe
          - source_labels:
            - __address__
            target_label: __param_target
          - replacement: blackbox
            target_label: __address__
          - 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-pods
          kubernetes_sd_configs:
          - role: pod
          relabel_configs:
          - action: keep
            regex: true
            source_labels:
            - __meta_kubernetes_pod_annotation_prometheus_io_scrape
          - action: replace
            regex: (.+)
            source_labels:
            - __meta_kubernetes_pod_annotation_prometheus_io_path
            target_label: __metrics_path__
          - action: replace
            regex: ([^:]+)(?::d+)?;(d+)
            replacement: $1:$2
            source_labels:
            - __address__
            - __meta_kubernetes_pod_annotation_prometheus_io_port
            target_label: __address__
          - action: labelmap
            regex: __meta_kubernetes_pod_label_(.+)
          - action: replace
            source_labels:
            - __meta_kubernetes_namespace
            target_label: kubernetes_namespace
          - action: replace
            source_labels:
            - __meta_kubernetes_pod_name
            target_label: kubernetes_pod_name
        alerting:
          alertmanagers:
          - static_configs:
              - targets: ["alertmanager:80"] 
        rule_files:
        - "/etc/config/alert_rules/*.yml"

    5、结果展示

    6、grafana  部署

    docker run -d --name=grafana -p 3000:3000 grafana/grafana 
    
    [root@VM_0_48_centos prometheus]# docker ps -a|grep grafana 
    6ea8d2852906        grafana/grafana                                                       "/run.sh"                5 hours ago         Up 5 hours                 0.0.0.0:3000->3000/tcp   grafana
    [root@VM_0_48_centos prometheus]# 

    6、登录grafana  配置数据源展示结果

    7 、导入展示

    推荐模板:
    •集群资源监控:3119
    •资源状态监控:6417
    •Node监控:9276

    8、结果展示:

  • 相关阅读:
    描述一下 JVM 加载 class 文件的原理机制?
    Java 中会存在内存泄漏吗,请简单描述
    关于同步机制的一些见解
    Mybatis 一对一,一对多,多对一,多对多的理解
    关于JavaBean实现Serializable接口的见解
    Python 文件I/O
    Python 模块
    Python 函数
    Python time tzset()方法
    Python time time()方法
  • 原文地址:https://www.cnblogs.com/xiajq/p/11354041.html
Copyright © 2011-2022 走看看