k8s-prometheus

一、监控指标

监控指标	具体实现	备注
pod	cAdvisor	集成在（kubelet）中
node	node-exporter	daemonset
k8s资源	kube-state-metrics	deployment

二、prometheus yaml文件

prometheus_configmap.yaml

apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: prometheus
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-node-exporters
      honor_timestamps: true
      scrape_interval: 30s
      scrape_timeout: 30s
      metrics_path: /metrics
      scheme: http
      kubernetes_sd_configs:
      - role: node
      relabel_configs:
      - separator: ;
        regex: __meta_kubernetes_node_label_(.+)
        replacement: $1
        action: labelmap
      - source_labels: [__meta_kubernetes_node_name]
        separator: ;
        regex: (.+)
        target_label: __address__
        replacement: ${1}:9100
        action: replace

    - 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

prometheus.yaml

apiVersion: v1
kind: ServiceAccount
metadata:
  name: prometheus-serviceaccount
  namespace: prometheus

---
apiVersion: rbac.authorization.k8s.io/v1beta1
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/v1beta1
kind: ClusterRoleBinding
metadata:
  name: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: prometheus
subjects:
- kind: ServiceAccount
  name: prometheus-serviceaccount
  namespace: prometheus

---
apiVersion: apps/v1 
kind: Deployment
metadata:
  labels:
    name: prometheus-deployment
  name: prometheus
  namespace: prometheus
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus 
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      serviceAccountName: prometheus-serviceaccount
      containers:
      - image: prom/prometheus:v2.13.1
        name: prometheus
        command:
        - "/bin/prometheus"
        args:
        - "--config.file=/prometheus/conf/prometheus.yml"
        - "--storage.tsdb.path=/prometheus/data"
        - "--storage.tsdb.retention=30d"
        ports:
        - containerPort: 9090
          protocol: TCP
        volumeMounts:
        - mountPath: "/prometheus/data"
          name: data
        - mountPath: "/prometheus/conf"
          name: config-volume
        resources:
          requests:
            cpu: 100m
            memory: 100Mi
          limits:
            cpu: 5000m
            memory: 2500Mi
      volumes:
      - emptyDir: {}
        name: data
      - configMap:
          name: prometheus-config
        name: config-volume
      hostAliases:
        - ip: 192.168.0.193 
          hostnames:
            - online-k8s-node1 

---
apiVersion: v1
kind: Service
metadata:
  annotations:
  name: prometheus
  namespace: prometheus
  labels:
    name: prometheus-service
spec:
  ports:
  - name: http
    port: 9090
    protocol: TCP
    targetPort: 9090
  selector:
    app: prometheus
  sessionAffinity: None
  type: NodePort

三、node-exporter

node-exporter-ds.yml

apiVersion: apps/v1
kind: DaemonSet
metadata:
  labels:
    addonmanager.kubernetes.io/mode: Reconcile
    k8s-app: node-exporter
    kubernetes.io/cluster-service: "true"
    version: v0.18.1
  name: node-exporter
  namespace: kube-system
spec:
  revisionHistoryLimit: 10
  selector:
    matchLabels:
      k8s-app: node-exporter
      version: v0.18.1
  template:
    metadata:
      creationTimestamp: null
      labels:
        k8s-app: node-exporter
        version: v0.18.1
    spec:
      tolerations:
      - key: node-role.kubernetes.io/master 
        effect: NoSchedule
        value: ""
        operator: "Equal"
      containers:
      - args:
        - --log.level=info
        - --path.procfs=/host/proc
        - --path.sysfs=/host/sys
        - --path.rootfs=/rootfs
        - --collector.vmstat
        - --collector.vmstat.fields=.*
        - --collector.netstat
        - --collector.netstat.fields=.*
        - --collector.filesystem.ignored-mount-points=^/(proc|tmpfs|shm|sys|var/lib/docker/.+)($|/)
        - --collector.filesystem.ignored-fs-types=^(autofs|tmpfs|shm|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipef
s|securityfs|selinuxfs|squashfs|sysfs|tracefs)$
        image: prom/node-exporter:v0.18.1
        imagePullPolicy: IfNotPresent
        name: prometheus-node-exporter
        ports:
        - containerPort: 9100
          hostPort: 9100
          name: metrics
          protocol: TCP
        resources:
          limits:
            memory: 50Mi
          requests:
            cpu: 100m
            memory: 50Mi
        securityContext:
          privileged: true
          runAsUser: 0
        terminationMessagePath: /dev/termination-log
        terminationMessagePolicy: File
        volumeMounts:
        - mountPath: /host/proc
          name: proc
          readOnly: true
        - mountPath: /host/sys
          name: sys
          readOnly: true
        - mountPath: /rootfs
          name: root
          readOnly: true
      dnsPolicy: ClusterFirst
      hostIPC: true
      hostNetwork: true
      hostPID: true
      restartPolicy: Always
      schedulerName: default-scheduler
      securityContext: {}
      terminationGracePeriodSeconds: 30
      volumes:
      - hostPath:
          path: /proc
          type: ""
        name: proc
      - hostPath:
          path: /sys
          type: ""
        name: sys
      - hostPath:
          path: /
          type: ""
        name: root
  updateStrategy:
    rollingUpdate:
      maxUnavailable: 1
    type: RollingUpdate

kube-state-metrics
yaml文件下载
https://github.com/kubernetes/kube-state-metrics/tree/master/examples/standard
修改对应的镜像即可
例如mirrorgooglecontainers/kube-state-metrics:v1.7.2

四、错误记录

一、主机名解析错误

原因是解析不到主机名导致的，两种解决方案
一、在部署promethus的时候添加hostname

      hostAliases:
        - ip: 192.168.0.111
          hostnames:
            - online-k8s-node2
            - online-k8s-node2

二、修改prometheus配置文件

    - job_name: kubernetes-node-exporters
      honor_timestamps: true
      scrape_interval: 30s
      scrape_timeout: 30s
      metrics_path: /metrics
      scheme: http
      kubernetes_sd_configs:
      - role: node
      relabel_configs:
      - separator: ;
        regex: __meta_kubernetes_node_label_(.+)
        replacement: $1
        action: labelmap
      - source_labels: [__meta_kubernetes_node_address_InternalIP]
        separator: ;
        regex: (.+)
        target_label: __address__
        replacement: ${1}:9100
        action: replace

二、node-exporter 在master节点调度

      tolerations:
      - key: node-role.kubernetes.io/master 
        effect: NoSchedule
        value: ""
        operator: "Equal"

三、设置prometheus保留数据时间

在yaml文件中修改 - "–storage.tsdb.retention=10d"参数

四、pod监控

需要添加annotations
容器需要有pod开放了/metrics

apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: redis
  namespace: kube-system
spec:
  template:
    metadata:
      annotations:
        prometheus.io/scrape: "true"
        prometheus.io/port: "9121"
      labels:
        app: redis
    spec:
      containers:
      - name: redis
        image: redis:4
        resources:
          requests:
            cpu: 100m
            memory: 100Mi
        ports:
        - containerPort: 6379
      - name: redis-exporter
        image: oliver006/redis_exporter:latest
        resources:
          requests:
            cpu: 100m
            memory: 100Mi
        ports:
        - containerPort: 9121

    - 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

五、grafana

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 
  template:
    metadata:
      labels:
        app: grafana
        component: core
    spec:
      containers:
      - image: grafana/grafana:7.0.3
        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

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

添加数据源

导入dashboards

官网下载dashboards，然后导入即可
https://grafana.com/grafana/dashboards