参考

本地安装docker

安装docker

curl -fsSL https://get.docker.com | bash -s docker --mirror Aliyun

启动docker

service docker start

安装prometheus

namespaces.yaml
apiVersion: v1
kind: Namespace
metadata:
  name: monitoring

prometheus-dep.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus
  namespace: monitoring
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
      annotations:
        prometheus.io/scrape: 'false'
    spec:
      imagePullSecrets:  # 注意修改
        - name: docker-image-resposity
      serviceAccountName: prometheus
      containers:
      - name: prometheus
          # 注意修改
        image: hub-dev.rockontrol.com/docker.io/prom/prometheus@sha256:1224ee30a3be668e0b22444773c4c1b750778af492094b6cd375c780c7526e22
        imagePullPolicy: Always
        command:
          - prometheus
          - --config.file=/etc/prometheus/prometheus.yml
          - --storage.tsdb.retention=1h
        ports:
        - containerPort: 9090
          protocol: TCP
        resources:
          limits:
            memory: 2Gi
        volumeMounts:
        - mountPath: /etc/prometheus/prometheus.yml
          name: prometheus-config
          subPath: prometheus.yml
      volumes:
        - name: prometheus-config
          configMap:
            name: prometheus-config
            items:
              - key: prometheus.yml
                path: prometheus.yml
                mode: 0644

prometheus-cfg.yaml

---
kind: ConfigMap
apiVersion: v1
metadata:
  labels:
    app: prometheus
  name: prometheus-config
  namespace: monitoring
data:
  prometheus.yml: |
    # A scrape configuration for running Prometheus on a Kubernetes cluster.
    # This uses separate scrape configs for cluster components (i.e. API server, node)
    # and services to allow each to use different authentication configs.
    #
    # Kubernetes labels will be added as Prometheus labels on metrics via the
    # `labelmap` relabeling action.
    #
    # If you are using Kubernetes 1.7.2 or earlier, please take note of the comments
    # for the kubernetes-cadvisor job; you will need to edit or remove this job.

    # Scrape config for API servers.
    #
    # Kubernetes exposes API servers as endpoints to the default/kubernetes
    # service so this uses `endpoints` role and uses relabelling to only keep
    # the endpoints associated with the default/kubernetes service using the
    # default named port `https`. This works for single API server deployments as
    # well as HA API server deployments.
    global:
      scrape_interval: 15s
      scrape_timeout: 10s
      evaluation_interval: 1m

    scrape_configs:
    - 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 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'
      # if you want to use metrics on jobs, set the below field to
      # true to prevent Prometheus from setting the `job` label
      # automatically.
      honor_labels: false
      kubernetes_sd_configs:
      - role: pod
      # skip verification so you can do HTTPS to pods
      tls_config:
        insecure_skip_verify: true
      # make sure your labels are in order
      relabel_configs:
      # these labels tell Prometheus to automatically attach source
      # pod and namespace information to each collected sample, so
      # that they'll be exposed in the custom metrics API automatically.
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: namespace
      - source_labels: [__meta_kubernetes_pod_name]
        action: replace
        target_label: pod
      # these labels tell Prometheus to look for
      # prometheus.io/{scrape,path,port} annotations to configure
      # how to scrape
      - 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__
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scheme]
        action: replace
        target_label: __scheme__
        regex: (.+)

prometheus-rbac.yaml

---
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: v1
kind: ServiceAccount
metadata:
  name: prometheus
  namespace: monitoring
---
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
  namespace: monitoring

prometheus-svc.yaml

---
apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: monitoring
  labels:
    app: prometheus
spec:
  type: NodePort
  ports:
    - port: 9090
      targetPort: 9090
      nodePort: 31190
      protocol: TCP
  selector:
    app: prometheus

执行安装prometheus

kubectl create -f .

安装证书

git clone https://gitee.com/laaron/k8s-prom-hpa.git
cd k8s-prom-hpa
touch metrics-ca.key metrics-ca.crt metrics-ca-config.json
make certs

正式安装custom-metrics

修改镜像

apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: custom-metrics-apiserver
  name: custom-metrics-apiserver
  namespace: monitoring
spec:
  replicas: 1
  selector:
    matchLabels:
      app: custom-metrics-apiserver
  template:
    metadata:
      labels:
        app: custom-metrics-apiserver
      name: custom-metrics-apiserver
    spec:
      imagePullSecrets: # 注意这里
        - name: docker-image-resposity
      serviceAccountName: custom-metrics-apiserver
      containers:
      - name: custom-metrics-apiserver
          # 注意这里
        image: hub-dev.rockontrol.com/docker.io/directxman12/k8s-prometheus-adapter@sha256:c2fda7697892d33f6dd52b84cddca013754ba268808abda3dfb3b85cc9f6bd56
        args:
        - /adapter
        - --secure-port=6443
        - --tls-cert-file=/var/run/serving-cert/serving.crt
        - --tls-private-key-file=/var/run/serving-cert/serving.key
        - --logtostderr=true
        - --prometheus-url=http://prometheus.monitoring.svc:9090/
        - --metrics-relist-interval=30s
        - --v=10
        - --config=/etc/adapter/config.yaml
        ports:
        - containerPort: 6443
        volumeMounts:
        - mountPath: /var/run/serving-cert
          name: volume-serving-cert
          readOnly: true
        - mountPath: /etc/adapter/
          name: config
          readOnly: true
      volumes:
      - name: volume-serving-cert
        secret:
          secretName: cm-adapter-serving-certs
      - name: config
        configMap:
          name: adapter-config

其他的yaml文件下载

将以上文件执行

kubectl create -f .

测试接口

kubectl get --raw "/apis/custom.metrics.k8s.io/v1beta1" | jq  .

查看所有pods的fs使用情况

kubectl get --raw "/apis/custom.metrics.k8s.io/v1beta1/namespaces/monitoring/pods/*/kubelet_container_log_filesystem_used_bytes" | jq .

至此custom.metrics已配置成功

实例tomcat

apiVersion: apps/v1
kind: Deployment
metadata:
  name: demo-tomcat
  namespace: nginx-ingress
  labels:
    app: demo-tom
spec:
  replicas: 1
  selector:
    matchLabels:
      app: demo-tomcat-pod
  template:
    metadata:
      labels:
        app: demo-tomcat-pod
    spec:
      imagePullSecrets:
        - name: docker-image-resposity
      containers:
      - name: demo-tomcat
        image: tomcat:latest。 # 注意这里
        ports:
          - containerPort: 8080
        resources: # 注意这里
          limits:
            cpu: 500m
          requests:
            cpu: 200m


---
apiVersion: v1
kind: Service
metadata:
  name: tomcat-test-svc
  namespace: nginx-ingress
spec:
  type: NodePort
  ports:
    - port: 8080
      targetPort: 8080
  selector:
    app: demo-tomcat-pod

---
apiVersion: networking.k8s.io/v1beta1
kind: Ingress
metadata:
  name: tomcat-test-ingress
  namespace: nginx-ingress
  labels:
    ingres-controller: nginx
  annotations:
    kubernets.io/ingress.class: nginx
spec:
  rules:
  - host: www.lijiacai.cnba
    http:
      paths:
      - path: /
        backend:
          serviceName: tomcat-test-svc
          servicePort: 8080

配置自动扩容

apiVersion: autoscaling/v2beta2
kind: HorizontalPodAutoscaler
metadata:
  name: podinfo
  namespace: nginx-ingress
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: demo-tomcat
  minReplicas: 2
  maxReplicas: 10
  metrics:
    - type: Pods
      pods:
        metric:
          name: http_requests
        target:
          type: AverageValue
          averageValue: 10

查看统计结果

kubectl get --raw "/apis/custom.metrics.k8s.io/v1beta1/namespaces/nginx-ingress/pods/*/http_requests" | jq .

注意namespaces后面是命令空间名称

浏览结果

{
  "kind": "MetricValueList",
  "apiVersion": "custom.metrics.k8s.io/v1beta1",
  "metadata": {
    "selfLink": "/apis/custom.metrics.k8s.io/v1beta1/namespaces/default/pods/%2A/http_requests"
  },
  "items": [
    {
      "describedObject": {
        "kind": "Pod",
        "namespace": "default",
        "name": "podinfo-6b86c8ccc9-kv5g9",
        "apiVersion": "/__internal"
      },
      "metricName": "http_requests",
      "timestamp": "2018-01-10T16:49:07Z",
      "value": "901m"
    },
    {
      "describedObject": {
        "kind": "Pod",
        "namespace": "default",
        "name": "podinfo-6b86c8ccc9-nm7bl",
        "apiVersion": "/__internal"
      },
      "metricName": "http_requests",
      "timestamp": "2018-01-10T16:49:07Z",
      "value": "898m"
    }
  ]
}

安装过程的异常处理

docker: Error response from daemon: error creating aufs mount to /master_docker/aufs/mnt/f6ae09e0d17ec8ffe2a62d4b6951b8ebf7cebefa9c8da8aabc32399c34ec8a4d-init: file too large.

修改/etc/docker/daemon.json，选择使用aufs，然后重启docker

{
  “storage-driver”: “vfs”
}

service docker restart

Can’t load /root/.rnd into RNG

cd /root
openssl rand -writerand .rnd