k8s安装prometheus+grafana

2018_like菜

已于 2022-02-28 09:47:16 修改

阅读量2.4k

点赞数

分类专栏： k8s Prometheus+Grafana 文章标签： kubernetes 运维 docker

于 2021-12-09 19:35:43 首次发布

本文链接：https://blog.csdn.net/u014756339/article/details/121838803

版权

k8s 同时被 2 个专栏收录

22 篇文章 2 订阅

订阅专栏

Prometheus+Grafana

10 篇文章 1 订阅

订阅专栏

另外一种安装方式版本： k8s安装prometheus+grafana（第二弹：prometheus-operator）

总共4大步，4个yaml集合

环境：k8s 1.16 ，推荐1.20都行

版本：node-exporter v0.16.0

prometheus:latest 2021.11月左右下载的

grafana:latest 现在是8.3

去掉nfs ，为什么？人懒不想再装一个nfs服务，挂在本地：

/prometheus/data

/prometheus

/grafana

集群json模板官网下载导入即可：https://grafana.com/grafana/dashboards/13105

原模版是id：

修改模版后id15520

想要要id13105的表格模版修改没成功，网络会不显示需要修改，可能是我安装方式和它不一样

kubectl create namespace ns-monitor 创建ns-monitor空间
kubectl get all -n ns-monitor 查看空间下的服务等等信息

prometheus组件和grafana弄个标签避免难找和改配置机器，nodeport也可以写死端口，这里没写死

kubectl label nodes node名字   标签名=值
kubectl label nodes k8s-node02 IngressProxy=true

创建node-exporter.yaml

kind: DaemonSet
apiVersion: apps/v1
metadata:
  labels:
    app: node-exporter
  name: node-exporter
  namespace: ns-monitor
spec:
  revisionHistoryLimit: 10
  selector:
    matchLabels:
      app: node-exporter
  template:
    metadata:
      labels:
        app: node-exporter
    spec:
      containers:
        - name: node-exporter
          image: prom/node-exporter:v0.16.0
          ports:
            - containerPort: 9100
              protocol: TCP
              name: http
      hostNetwork: true  # 获得Node的物理指标信息
      hostPID: true  # 获得Node的物理指标信息
#      tolerations:  # Master节点
#        - effect: NoSchedule
#          operator: Exists

---
kind: Service
apiVersion: v1
metadata:
  labels:
    app: node-exporter
  name: node-exporter-service
  namespace: ns-monitor
spec:
  ports:
    - name: http
      port: 9100
      nodePort: 31672
      protocol: TCP
  type: NodePort
  selector:
    app: node-exporter

创建prometheus.yaml，如果运行失败看是不是挂在/prometheus目录下没有prometheus.yml配置文件（不是目录，我下面可能创建成了目录，删下目录再创建配置文件），没有就创建，复制prometheus.yaml里的data:
prometheus.yml: |-

下面一行开始直到遇到第一个---结束

apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: prometheus
rules:
  - apiGroups: [""]  # "" indicates the core API group
    resources:
      - nodes
      - nodes/proxy
      - services
      - endpoints
      - pods
    verbs:
      - get
      - watch
      - list
  - apiGroups:
      - extensions
    resources:
      - ingresses
    verbs:
      - get
      - watch
      - list
  - nonResourceURLs: ["/metrics"]
    verbs:
      - get

---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: prometheus
  namespace: ns-monitor
  labels:
    app: prometheus

---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: prometheus
subjects:
  - kind: ServiceAccount
    name: prometheus
    namespace: ns-monitor
roleRef:
  kind: ClusterRole
  name: prometheus
  apiGroup: rbac.authorization.k8s.io

---
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-conf
  namespace: ns-monitor
  labels:
    app: prometheus
data:
  prometheus.yml: |-
    # my global config
    global:
      scrape_interval:     15s  # Set the scrape interval to every 15 seconds. Default is every 1 minute.
      evaluation_interval: 15s  # Evaluate rules every 15 seconds. The default is every 1 minute.
      # scrape_timeout is set to the global default (10s).

    # Alertmanager configuration
    alerting:
      alertmanagers:
      - static_configs:
        - targets:
          # - alertmanager:9093

    # Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
    rule_files:
      # - "first_rules.yml"
      # - "second_rules.yml"

    # A scrape configuration containing exactly one endpoint to scrape:
    # Here it's Prometheus itself.
    scrape_configs:
      # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
      - job_name: 'prometheus'
        # metrics_path defaults to '/metrics'
        # scheme defaults to 'http'.
        static_configs:
          - targets: ['localhost:9090']
          
      - job_name: 'grafana'
        static_configs:
          - targets:
              - 'grafana-service.ns-monitor:3000'

      - job_name: 'kubernetes-apiservers'
        kubernetes_sd_configs:
        - role: endpoints
        # Default to scraping over https. If required, just disable this or change to
        # `http`.
        scheme: https
        # This TLS & bearer token file config is used to connect to the actual scrape
        # endpoints for cluster components. This is separate to discovery auth
        # configuration because discovery & scraping are two separate concerns in
        # Prometheus. The discovery auth config is automatic if Prometheus runs inside
        # the cluster. Otherwise, more config options have to be provided within the
        # <kubernetes_sd_config>.
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
          # If your node certificates are self-signed or use a different CA to the
          # master CA, then disable certificate verification below. Note that
          # certificate verification is an integral part of a secure infrastructure
          # so this should only be disabled in a controlled environment. You can
          # disable certificate verification by uncommenting the line below.
          #
          # insecure_skip_verify: true
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        # Keep only the default/kubernetes service endpoints for the https port. This
        # will add targets for each API server which Kubernetes adds an endpoint to
        # the default/kubernetes service.
        relabel_configs:
        - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
          action: keep
          regex: default;kubernetes;https
          
      # Scrape config for nodes (kubelet).
      #
      # Rather than connecting directly to the node, the scrape is proxied though the
      # Kubernetes apiserver.  This means it will work if Prometheus is running out of
      # cluster, or can't connect to nodes for some other reason (e.g. because of
      # firewalling).
      - job_name: 'kubernetes-nodes'
        # Default to scraping over https. If required, just disable this or change to
        # `http`.
        scheme: https
        # This TLS & bearer token file config is used to connect to the actual scrape
        # endpoints for cluster components. This is separate to discovery auth
        # configuration because discovery & scraping are two separate concerns in
        # Prometheus. The discovery auth config is automatic if Prometheus runs inside
        # the cluster. Otherwise, more config options have to be provided within the
        # <kubernetes_sd_config>.
        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

      # Scrape config for Kubelet cAdvisor.
      #
      # This is required for Kubernetes 1.7.3 and later, where cAdvisor metrics
      # (those whose names begin with 'container_') have been removed from the
      # Kubelet metrics endpoint.  This job scrapes the cAdvisor endpoint to
      # retrieve those metrics.
      #
      # In Kubernetes 1.7.0-1.7.2, these metrics are only exposed on the cAdvisor
      # HTTP endpoint; use "replacement: /api/v1/nodes/${1}:4194/proxy/metrics"
      # in that case (and ensure cAdvisor's HTTP server hasn't been disabled with
      # the --cadvisor-port=0 Kubelet flag).
      #
      # This job is not necessary and should be removed in Kubernetes 1.6 and
      # earlier versions, or it will cause the metrics to be scraped twice.
      - job_name: 'kubernetes-cadvisor'
        # Default to scraping over https. If required, just disable this or change to
        # `http`.
        scheme: https
        # This TLS & bearer token file config is used to connect to the actual scrape
        # endpoints for cluster components. This is separate to discovery auth
        # configuration because discovery & scraping are two separate concerns in
        # Prometheus. The discovery auth config is automatic if Prometheus runs inside
        # the cluster. Otherwise, more config options have to be provided within the
        # <kubernetes_sd_config>.
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        kubernetes_sd_configs:
        - role: node
        relabel_configs:
        - action: labelmap
          regex: __meta_kubernetes_node_label_(.+)
        - target_label: __address__
          replacement: kubernetes.default.svc:443
        - source_labels: [__meta_kubernetes_node_name]
          regex: (.+)
          target_label: __metrics_path__
          replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor

      # Scrape config for service endpoints.
      #
      # The relabeling allows the actual service scrape endpoint to be configured
      # via the following annotations:
      #
      # * `prometheus.io/scrape`: Only scrape services that have a value of `true`
      # * `prometheus.io/scheme`: If the metrics endpoint is secured then you will need
      # to set this to `https` & most likely set the `tls_config` of the scrape config.
      # * `prometheus.io/path`: If the metrics path is not `/metrics` override this.
      # * `prometheus.io/port`: If the metrics are exposed on a different port to the
      # service then set this appropriately.
      - 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

      # Example scrape config for probing services via the Blackbox Exporter.
      #
      # The relabeling allows the actual service scrape endpoint to be configured
      # via the following annotations:
      #
      # * `prometheus.io/probe`: Only probe services that have a value of `true`
      - job_name: 'kubernetes-services'
        metrics_path: /probe
        params:
          module: [http_2xx]
        kubernetes_sd_configs:
        - role: service
        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

      # Example scrape config for probing ingresses via the Blackbox Exporter.
      #
      # The relabeling allows the actual ingress scrape endpoint to be configured
      # via the following annotations:
      #
      # * `prometheus.io/probe`: Only probe services that have a value of `true`
      - job_name: 'kubernetes-ingresses'
        metrics_path: /probe
        params:
          module: [http_2xx]
        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

      # Example scrape config for pods
      #
      # The relabeling allows the actual pod scrape endpoint to be configured via the
      # following annotations:
      #
      # * `prometheus.io/scrape`: Only scrape pods that have a value of `true`
      # * `prometheus.io/path`: If the metrics path is not `/metrics` override this.
      # * `prometheus.io/port`: Scrape the pod on the indicated port instead of the
      # pod's declared ports (default is a port-free target if none are declared).
      - 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

---
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-rules
  namespace: ns-monitor
  labels:
    app: prometheus
data:
  cpu-usage.rule: |
    groups:
      - name: NodeCPUUsage
        rules:
          - alert: NodeCPUUsage
            expr: (100 - (avg by (instance) (irate(node_cpu{name="node-exporter",mode="idle"}[5m])) * 100)) > 75
            for: 2m
            labels:
              severity: "page"
            annotations:
              summary: "{{$labels.instance}}: High CPU usage detected"
              description: "{{$labels.instance}}: CPU usage is above 75% (current value is: {{ $value }})"



---
kind: Deployment
apiVersion: apps/v1
metadata:
  labels:
    app: prometheus
  name: prometheus
  namespace: ns-monitor
spec:
  replicas: 1
  revisionHistoryLimit: 10
  selector:
    matchLabels:
      app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      serviceAccountName: prometheus
      securityContext:
        runAsUser: 0
      containers:
        - name: prometheus
          image: prom/prometheus:latest
          imagePullPolicy: IfNotPresent
          volumeMounts:
            - mountPath: /prometheus
              name: prometheus1
            - mountPath: /etc/prometheus/prometheus.yml
              name: prometheus2
            - mountPath: /etc/prometheus/rules
              name: prometheus3
          ports:
            - containerPort: 9090
              protocol: TCP
      volumes:
        - name: prometheus1
          hostPath:
            path: /prometheus/data
            type: DirectoryOrCreate
        - name: prometheus2
          hostPath:		
            path: /prometheus/prometheus.yml
        - name: prometheus3
          hostPath:		
            path: /prometheus/rules
      tolerations:
        - key: node-role.kubernetes.io/master
          effect: NoSchedule

      nodeSelector:             #设置node筛选器，在特定label的节点上启动
        IngressProxy: "true"

---
kind: Service
apiVersion: v1
metadata:
  annotations:
    prometheus.io/scrape: 'true'
  labels:
    app: prometheus
  name: prometheus-service
  namespace: ns-monitor
spec:
  ports:
    - port: 9090
      targetPort: 9090
  selector:
    app: prometheus
  type: NodePort

创建grafana.yaml，下载可能失败，手动下载docker pull一下

kind: Deployment
apiVersion: apps/v1
metadata:
  labels:
    app: grafana
  name: grafana
  namespace: ns-monitor
spec:
  replicas: 1
  revisionHistoryLimit: 10
  selector:
    matchLabels:
      app: grafana
  template:
    metadata:
      labels:
        app: grafana
    spec:
      securityContext:
        runAsUser: 0
      containers:
        - name: grafana
          image: grafana/grafana:latest
          imagePullPolicy: IfNotPresent
          env:
            - name: GF_AUTH_BASIC_ENABLED
              value: "true"
            - name: GF_AUTH_ANONYMOUS_ENABLED
              value: "false"
          readinessProbe:
            httpGet:
              path: /login
              port: 3000
          volumeMounts:
            - mountPath: /var/lib/grafana
              name: grafana1
          ports:
            - containerPort: 3000
              protocol: TCP
      volumes:
        - name: grafana1
          hostPath:
            path: /grafana
            type: DirectoryOrCreate


      nodeSelector:             #设置node筛选器，在特定label的节点上启动
        IngressProxy: "true"
---
kind: Service
apiVersion: v1
metadata:
  labels:
    app: grafana
  name: grafana-service
  namespace: ns-monitor
spec:
  ports:
    - port: 3000
      targetPort: 3000
  selector:
    app: grafana
  type: NodePort

kube-state-metrics是什么？

kube-state-metrics通过监听API Server生成有关资源对象的状态指标，比如Deployment、Node、Pod，需要注意的是kube-state-metrics只是简单的提供一个metrics数据，并不会存储这些指标数据，所以我们可以使用Prometheus来抓取这些数据然后存储，主要关注的是业务相关的一些元数据，比如Deployment、Pod、副本状态等；调度了多少个replicas？现在可用的有几个？多少个Pod是running/stopped/terminated状态？Pod重启了多少次？我有多少job在运行中。
安装kube-state-metrics组件

创建kube-state-metrics.yaml

---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: kube-state-metrics
  namespace: kube-system
---

apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: kube-state-metrics
rules:
- apiGroups: [""]
  resources: ["configmaps", "secrets","nodes", "pods", "services", "resourcequotas", "replicationcontrollers", "limitranges", "persistentvolumeclaims", "persistentvolumes", "namespaces", "endpoints"]
  verbs: ["list", "watch"]
- apiGroups: ["extensions"]
  resources: ["daemonsets", "deployments", "replicasets", "ingresses"]
  verbs: ["list", "watch"]
- apiGroups: ["apps"]
  resources: ["statefulsets", "daemonsets","deployments", "replicasets"]
  verbs: ["list", "watch"]
- apiGroups: ["batch"]
  resources: ["cronjobs", "jobs"]
  verbs: ["list", "watch"]
- apiGroups: ["autoscaling"]
  resources: ["horizontalpodautoscalers"]
  verbs: ["list", "watch"]
- apiGroups: ["authentication.k8s.io"]
  resources: ["tokenreviews"]
  verbs: ["create"]
- apiGroups: ["authorization.k8s.io"]
  resources: ["subjectaccessreviews"]
  verbs: ["create"]
- apiGroups: ["policy"]
  resources: ["poddisruptionbudgets"]
  verbs: ["list", "watch"]
- apiGroups: ["certificates.k8s.io"]
  resources: ["certificatesigningrequests"]
  verbs: ["list", "watch"]
- apiGroups: ["storage.k8s.io"]
  resources: ["storageclasses", "volumeattachments"]
  verbs: ["list", "watch"]
- apiGroups: ["admissionregistration.k8s.io"]
  resources: ["mutatingwebhookconfigurations", "validatingwebhookconfigurations"]
  verbs: ["list", "watch"]
- apiGroups: ["networking.k8s.io"]
  resources: ["networkpolicies"]
  verbs: ["list", "watch"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: kube-state-metrics
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: kube-state-metrics
subjects:
- kind: ServiceAccount
  name: kube-state-metrics
  namespace: kube-system
 
---
 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: kube-state-metrics
  namespace: kube-system
spec:
  replicas: 1
  selector:
    matchLabels:
      app: kube-state-metrics
  template:
    metadata:
      labels:
        app: kube-state-metrics
    spec:
      serviceAccountName: kube-state-metrics
      containers:
      - name: kube-state-metrics
#        image: gcr.io/google_containers/kube-state-metrics-amd64:v1.3.1
#        image: quay.io/coreos/kube-state-metrics:v1.9.0
        image: registry.cn-shenzhen.aliyuncs.com/starsl/kube-state-metrics:v2.2.1
        ports:
        - containerPort: 8080
---
apiVersion: v1
kind: Service
metadata:
  annotations:
    prometheus.io/scrape: 'true'
  name: kube-state-metrics
  namespace: kube-system
  labels:
    app: kube-state-metrics
spec:
  ports:
  - name: kube-state-metrics
    port: 8080
    protocol: TCP
  selector:
    app: kube-state-metrics

登陆grafana设置 prometheus的源 http://master的ip+prometheus服务NodePort端口

登陆grafana：http://192.168.1.1:43074

源例如：http://192.168.1.1:11676

10000-40000多端口号，是因为解除了端口限制

[root@k8s-master pr]# kubectl get all -n ns-monitor
NAME READY STATUS RESTARTS AGE
pod/grafana-75866b6469-tfkdg 1/1 Running 0 70m
pod/node-exporter-n2sw4 1/1 Running 0 125m
pod/node-exporter-vvvgc 1/1 Running 0 125m
pod/prometheus-55bf48679d-fmgwx 1/1 Running 0 89m

NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
service/grafana-service NodePort 10.111.105.150 <none> 3000:43074/TCP 70m
service/node-exporter-service NodePort 10.101.79.192 <none> 9100:31672/TCP 125m
service/prometheus-service NodePort 10.109.45.147 <none> 9090:11676/TCP 102m

加载模版：13105