前情回顾

• 配置是独立于程序的可配变量，同一份程序在不同配置下会有不同的行为。

• 云原生（Cloud Native）程序的特点

  • 程序的配置，通过设置环境变量传递到容器内部
  • 程序的配置，通过程序启动参数配置生效
  • 程序的配置，通过集中在配置中心进行统一管理（CRUD）

• Devops工程师应该做什么？

  • 容器化公司自研的应用程序（通过Docker进行二次封装）
  • 推动容器化应用，转变为云原生应用（一次构建，到处使用）
  • 使用容器编排框架（kubernetes），合理，规范，专业的编排业务容器

第一章：新一代容器云监控Prometheus的概述

• https://prometheus.io

• https://github.com/prometheus

• prometheus架构图

• 新一代容器云监控系统Prometheus和传统监控Zabbix对比

第二章：实战部署容器云监控必备exporter

1.部署kube-state-metrics

运维主机shkf-245.host.com

1.准备kube-state-metrics镜像

kube-state-metrics官方quay.io地址

[root@shkf6-245 ~]# docker pull quay.io/coreos/kube-state-metrics:v1.5.0
[root@shkf6-245 ~]# docker images |grep kube-state-metrics
quay.io/coreos/kube-state-metrics                 v1.5.0                     91599517197a        11 months ago       31.8MB
[root@shkf6-245 ~]# docker tag 91599517197a harbor.od.com/public/kube-state-metrics:v1.5.0
[root@shkf6-245 ~]# docker push harbor.od.com/public/kube-state-metrics:v1.5.0

2.准备资源配置清单

• rbac

[root@shkf6-245 ~]# mkdir /data/k8s-yaml/kube-state-metrics

[root@shkf6-245 ~]# vi /data/k8s-yaml/kube-state-metrics/rbac.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/kube-state-metrics/rbac.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: kube-state-metrics
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: kube-state-metrics
rules:
- apiGroups:
  - ""
  resources:
  - configmaps
  - secrets
  - nodes
  - pods
  - services
  - resourcequotas
  - replicationcontrollers
  - limitranges
  - persistentvolumeclaims
  - persistentvolumes
  - namespaces
  - endpoints
  verbs:
  - list
  - watch
- apiGroups:
  - policy
  resources:
  - poddisruptionbudgets
  verbs:
  - list
  - watch
- apiGroups:
  - extensions
  resources:
  - daemonsets
  - deployments
  - replicasets
  verbs:
  - list
  - watch
- apiGroups:
  - apps
  resources:
  - statefulsets
  verbs:
  - list
  - watch
- apiGroups:
  - batch
  resources:
  - cronjobs
  - jobs
  verbs:
  - list
  - watch
- apiGroups:
  - autoscaling
  resources:
  - horizontalpodautoscalers
  verbs:
  - list
  - watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/cluster-service: "true"
  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

• Deployment

[root@shkf6-245 ~]# vi /data/k8s-yaml/kube-state-metrics/dp.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/kube-state-metrics/dp.yaml
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  annotations:
    deployment.kubernetes.io/revision: "2"
  labels:
    grafanak8sapp: "true"
    app: kube-state-metrics
  name: kube-state-metrics
  namespace: kube-system
spec:
  selector:
    matchLabels:
      grafanak8sapp: "true"
      app: kube-state-metrics
  strategy:
    rollingUpdate:
      maxSurge: 25%
      maxUnavailable: 25%
    type: RollingUpdate
  template:
    metadata:
      labels:
        grafanak8sapp: "true"
        app: kube-state-metrics
    spec:
      containers:
      - name: kube-state-metrics
        image: harbor.od.com/public/kube-state-metrics:v1.5.0
        imagePullPolicy: IfNotPresent
        ports:
        - containerPort: 8080
          name: http-metrics
          protocol: TCP
        readinessProbe:
          failureThreshold: 3
          httpGet:
            path: /healthz
            port: 8080
            scheme: HTTP
          initialDelaySeconds: 5
          periodSeconds: 10
          successThreshold: 1
          timeoutSeconds: 5
      serviceAccountName: kube-state-metrics

3.应用资源配置清单

[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/kube-state-metrics/rbac.yaml
serviceaccount/kube-state-metrics created
clusterrole.rbac.authorization.k8s.io/kube-state-metrics created
clusterrolebinding.rbac.authorization.k8s.io/kube-state-metrics created
[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/kube-state-metrics/dp.yaml
deployment.extensions/kube-state-metrics created

4.检查启动情况

[root@shkf6-243 ~]# kubectl get pods -n kube-system|grep kube-state-metrics
kube-state-metrics-8669f776c6-n849f     1/1     Running   0          5m13s

[root@shkf6-243 ~]# curl 172.6.244.9:8080/healthz
ok

2.部署node-exporter

运维主机shkf6-245.host.com上：

1.准备node-exporter镜像

node-exporter官方dockerhub地址
node-expoerer官方github地址

[root@shkf6-245 ~]# docker pull prom/node-exporter:v0.15.0
[root@shkf6-245 ~]# docker images|grep node-exporter
prom/node-exporter                                v0.15.0                    12d51ffa2b22        2 years ago         22.8MB
[root@shkf6-245 ~]# docker tag 12d51ffa2b22 harbor.od.com/public/node-exporter:v0.15.0
[root@shkf6-245 ~]# docker push harbor.od.com/public/node-exporter:v0.15.0

2.准备资源配置清单

[root@shkf6-245 ~]# mkdir /data/k8s-yaml/node-exporter
[root@shkf6-245 ~]# vi /data/k8s-yaml/node-exporter/ds.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/node-exporter/ds.yaml
kind: DaemonSet
apiVersion: extensions/v1beta1
metadata:
  name: node-exporter
  namespace: kube-system
  labels:
    daemon: "node-exporter"
    grafanak8sapp: "true"
spec:
  selector:
    matchLabels:
      daemon: "node-exporter"
      grafanak8sapp: "true"
  template:
    metadata:
      name: node-exporter
      labels:
        daemon: "node-exporter"
        grafanak8sapp: "true"
    spec:
      volumes:
      - name: proc
        hostPath: 
          path: /proc
          type: ""
      - name: sys
        hostPath:
          path: /sys
          type: ""
      containers:
      - name: node-exporter
        image: harbor.od.com/public/node-exporter:v0.15.0
        imagePullPolicy: IfNotPresent
        args:
        - --path.procfs=/host_proc
        - --path.sysfs=/host_sys
        ports:
        - name: node-exporter
          hostPort: 9100
          containerPort: 9100
          protocol: TCP
        volumeMounts:
        - name: sys
          readOnly: true
          mountPath: /host_sys
        - name: proc
          readOnly: true
          mountPath: /host_proc
      hostNetwork: true

3.应用资源配置清单

[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/node-exporter/ds.yaml

4.检查启动情况

[root@shkf6-243 ~]# netstat -lntup|grep 9100
tcp6       0      0 :::9100                 :::*                    LISTEN      25846/node_exporter

[root@shkf6-243 ~]# curl localhost:9100/metrics

3.部署cadvisor

运维主机shkf6-245.host.com上：

1.准备cadvisor镜像

cadvisor官方dockerhub地址
cadvisor官方github地址

[root@shkf6-245 ~]# docker pull google/cadvisor:v0.28.3
[root@shkf6-245 ~]# docker images |grep cadvisor
google/cadvisor                                   v0.28.3                    75f88e3ec333        2 years ago         62.2MB
[root@shkf6-245 ~]# docker tag 75f88e3ec333 harbor.od.com/public/cadvisor:v0.28.3
[root@shkf6-245 ~]# docker push harbor.od.com/public/cadvisor:v0.28.3

2.准备资源配置清单

[root@shkf6-245 ~]# mkdir /data/k8s-yaml/cadvisor
[root@shkf6-245 ~]# vi /data/k8s-yaml/cadvisor/ds.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/cadvisor/ds.yaml
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: cadvisor
  namespace: kube-system
  labels:
    app: cadvisor
spec:
  selector:
    matchLabels:
      name: cadvisor
  template:
    metadata:
      labels:
        name: cadvisor
    spec:
      hostNetwork: true
      tolerations:
      - key: node-role.kubernetes.io/master
        effect: NoSchedule
      containers:
      - name: cadvisor
        image: harbor.od.com/public/cadvisor:v0.28.3
        imagePullPolicy: IfNotPresent
        volumeMounts:
        - name: rootfs
          mountPath: /rootfs
          readOnly: true
        - name: var-run
          mountPath: /var/run
        - name: sys
          mountPath: /sys
          readOnly: true
        - name: docker
          mountPath: /var/lib/docker
          readOnly: true
        ports:
          - name: http
            containerPort: 4194
            protocol: TCP
        readinessProbe:
          tcpSocket:
            port: 4194
          initialDelaySeconds: 5
          periodSeconds: 10
        args:
          - --housekeeping_interval=10s
          - --port=4194
      terminationGracePeriodSeconds: 30
      volumes:
      - name: rootfs
        hostPath:
          path: /
      - name: var-run
        hostPath:
          path: /var/run
      - name: sys
        hostPath:
          path: /sys
      - name: docker
        hostPath:
          path: /data/docker

3.修改运算节点软连接

所有运算节点上：

~]# mount -o remount,rw /sys/fs/cgroup/
~]# ln -s /sys/fs/cgroup/cpu,cpuacct /sys/fs/cgroup/cpuacct,cpu

4.应用资源配置清单

任意运算节点上：

[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/cadvisor/ds.yaml

5.检查启动情况

[root@shkf6-243 ~]# netstat -luntp|grep 4194
tcp6       0      0 :::4194                 :::*                    LISTEN      18027/cadvisor 

污点：

https://kubernetes.io/zh/docs/concepts/configuration/taint-and-toleration/

4.部署blackbox-exporter

运维主机shkf6-245.host.com上：

1.准备blackbox-exporter镜像

blackbox-exporter官方dockerhub地址
blackbox-exporter官方github地址

[root@shkf6-245 ~]# docker pull prom/blackbox-exporter:v0.15.1
[root@shkf6-245 ~]# docker images|grep blackbox
prom/blackbox-exporter                            v0.15.1                    81b70b6158be        3 months ago        19.7MB
[root@shkf6-245 ~]# docker tag 81b70b6158be harbor.od.com/public/blackbox-exporter:v0.15.1
[root@shkf6-245 ~]# docker push harbor.od.com/public/blackbox-exporter:v0.15.1

2.准备资源配置清单

• 创建目录

  [root@shkf6-245 ~]# mkdir /data/k8s-yaml/blackbox-exporter

• ConfigMap

[root@shkf6-245 ~]# vi /data/k8s-yaml/blackbox-exporter/cm.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/blackbox-exporter/cm.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  labels:
    app: blackbox-exporter
  name: blackbox-exporter
  namespace: kube-system
data:
  blackbox.yml: |-
    modules:
      http_2xx:
        prober: http
        timeout: 2s
        http:
          valid_http_versions: ["HTTP/1.1", "HTTP/2"]
          valid_status_codes: [200,301,302]
          method: GET
          preferred_ip_protocol: "ip4"
      tcp_connect:
        prober: tcp
        timeout: 2s

• Deployment

[root@shkf6-245 ~]# vi /data/k8s-yaml/blackbox-exporter/dp.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/blackbox-exporter/dp.yaml
kind: Deployment
apiVersion: extensions/v1beta1
metadata:
  name: blackbox-exporter
  namespace: kube-system
  labels:
    app: blackbox-exporter
  annotations:
    deployment.kubernetes.io/revision: 1
spec:
  replicas: 1
  selector:
    matchLabels:
      app: blackbox-exporter
  template:
    metadata:
      labels:
        app: blackbox-exporter
    spec:
      volumes:
      - name: config
        configMap:
          name: blackbox-exporter
          defaultMode: 420
      containers:
      - name: blackbox-exporter
        image: harbor.od.com/public/blackbox-exporter:v0.15.1
        imagePullPolicy: IfNotPresent
        args:
        - --config.file=/etc/blackbox_exporter/blackbox.yml
        - --log.level=info
        - --web.listen-address=:9115
        ports:
        - name: blackbox-port
          containerPort: 9115
          protocol: TCP
        resources:
          limits:
            cpu: 200m
            memory: 256Mi
          requests:
            cpu: 100m
            memory: 50Mi
        volumeMounts:
        - name: config
          mountPath: /etc/blackbox_exporter
        readinessProbe:
          tcpSocket:
            port: 9115
          initialDelaySeconds: 5
          timeoutSeconds: 5
          periodSeconds: 10
          successThreshold: 1
          failureThreshold: 3

• Service

[root@shkf6-245 ~]# vi /data/k8s-yaml/blackbox-exporter/svc.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/blackbox-exporter/svc.yaml
kind: Service
apiVersion: v1
metadata:
  name: blackbox-exporter
  namespace: kube-system
spec:
  selector:
    app: blackbox-exporter
  ports:
    - name: blackbox-port
      protocol: TCP
      port: 9115

• Ingress

[root@shkf6-245 ~]# vi /data/k8s-yaml/blackbox-exporter/ingress.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/blackbox-exporter/ingress.yaml
apiVersion: extensions/v1beta1
kind: Ingress
metadata:
  name: blackbox-exporter
  namespace: kube-system
spec:
  rules:
  - host: blackbox.od.com
    http:
      paths:
      - path: /
        backend:
          serviceName: blackbox-exporter
          servicePort: blackbox-port

3.应用资源配置清单

[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/blackbox-exporter/cm.yaml
configmap/blackbox-exporter created
[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/blackbox-exporter/dp.yaml
deployment.extensions/blackbox-exporter created
[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/blackbox-exporter/svc.yaml
service/blackbox-exporter created
^[[A[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/blackbox-exporter/ingress.yaml
ingress.extensions/blackbox-exporter created

4.解析域名

[root@shkf6-241 ~]# tail -1 /var/named/od.com.zone 
blackbox           A    192.168.6.66

5.浏览器访问

http://blackbox.od.com/

第三章：实战部署Prometheus及其配置详解

1.部署prometheus

运维主机shkf6-245.host.com上：

1.准备prometheus镜像

prometheus官方dockerhub地址
prometheus官方github地址

[root@shkf6-245 ~]# docker pull prom/prometheus:v2.14.0
[root@shkf6-245 ~]# docker images |grep prometheus
prom/prometheus                                   v2.14.0                    7317640d555e        5 weeks ago         130MB
[root@shkf6-245 ~]# docker tag 7317640d555e harbor.od.com/infra/prometheus:v2.12.0
[root@shkf6-245 ~]# docker push harbor.od.com/infra/prometheus:v2.12.0

2.准备资源配置清单

运维主机shkf6-245.host.com上：

• 创建目录

[root@shkf6-245 ~]# mkdir /data/k8s-yaml/prometheus

• rbac

[root@shkf6-245 ~]# vi /data/k8s-yaml/prometheus/rbac.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/prometheus/rbac.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: prometheus
  namespace: infra
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: prometheus
rules:
- apiGroups:
  - ""
  resources:
  - nodes
  - nodes/metrics
  - services
  - endpoints
  - pods
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - configmaps
  verbs:
  - get
- nonResourceURLs:
  - /metrics
  verbs:
  - get
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: prometheus
subjects:
- kind: ServiceAccount
  name: prometheus
  namespace: infra

• Deployment

[root@shkf6-245 ~]# vi /data/k8s-yaml/prometheus/dp.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/prometheus/dp.yaml
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  annotations:
    deployment.kubernetes.io/revision: "5"
  labels:
    name: prometheus
  name: prometheus
  namespace: infra
spec:
  progressDeadlineSeconds: 600
  replicas: 1
  revisionHistoryLimit: 7
  selector:
    matchLabels:
      app: prometheus
  strategy:
    rollingUpdate:
      maxSurge: 1
      maxUnavailable: 1
    type: RollingUpdate
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      nodeName: shkf6-243.host.com
      containers:
      - name: prometheus
        image: harbor.od.com/infra/prometheus:v2.12.0
        imagePullPolicy: IfNotPresent
        command:
        - /bin/prometheus
        args:
        - --config.file=/data/etc/prometheus.yml
        - --storage.tsdb.path=/data/prom-db
        - --storage.tsdb.min-block-duration=10m
        - --storage.tsdb.retention=72h
        ports:
        - containerPort: 9090
          protocol: TCP
        volumeMounts:
        - mountPath: /data
          name: data
        resources:
          requests:
            cpu: "1000m"
            memory: "1.5Gi"
          limits:
            cpu: "2000m"
            memory: "3Gi"
      imagePullSecrets:
      - name: harbor
      securityContext:
        runAsUser: 0
      serviceAccountName: prometheus
      volumes:
      - name: data
        nfs:
          server: shkf6-245
          path: /data/nfs-volume/prometheus

• Service

[root@shkf6-245 ~]# vi /data/k8s-yaml/prometheus/svc.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/prometheus/svc.yaml
apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: infra
spec:
  ports:
  - port: 9090
    protocol: TCP
    targetPort: 9090
  selector:
    app: prometheus

• Ingress

[root@shkf6-245 ~]# vi /data/k8s-yaml/prometheus/ingress.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/prometheus/ingress.yaml
apiVersion: extensions/v1beta1
kind: Ingress
metadata:
  annotations:
    kubernetes.io/ingress.class: traefik
  name: prometheus
  namespace: infra
spec:
  rules:
  - host: prometheus.od.com
    http:
      paths:
      - path: /
        backend:
          serviceName: prometheus
          servicePort: 9090

3.准备promentheus的配置文件

运维主机shkf6-245.host.com上：

• 拷贝证书

[root@shkf6-245 ~]# mkdir -pv /data/nfs-volume/prometheus/{etc,prom-db}
mkdir: created directory ‘/data/nfs-volume/prometheus/etc’
mkdir: created directory ‘/data/nfs-volume/prometheus/prom-db’
[root@shkf6-245 ~]# cp /opt/certs/ca.pem /data/nfs-volume/prometheus/etc/
[root@shkf6-245 ~]# cp /opt/certs/client.pem /data/nfs-volume/prometheus/etc/
[root@shkf6-245 ~]# cp /opt/certs/client-key.pem /data/nfs-volume/prometheus/etc/

• 准备配置

[root@shkf6-245 ~]# vi /data/nfs-volume/prometheus/etc/prometheus.yml
[root@shkf6-245 ~]# cat /data/nfs-volume/prometheus/etc/prometheus.yml
global:
  scrape_interval:     15s
  evaluation_interval: 15s
scrape_configs:
- job_name: 'etcd'
  tls_config:
    ca_file: /data/etc/ca.pem
    cert_file: /data/etc/client.pem
    key_file: /data/etc/client-key.pem
  scheme: https
  static_configs:
  - targets:
    - '192.168.6.242:2379'
    - '192.168.6.243:2379'
    - '192.168.6.244:2379'
- 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-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
- job_name: 'kubernetes-kubelet'
  kubernetes_sd_configs:
  - role: node
  relabel_configs:
  - action: labelmap
    regex: __meta_kubernetes_node_label_(.+)
  - source_labels: [__meta_kubernetes_node_name]
    regex: (.+)
    target_label: __address__
    replacement: ${1}:10255
- job_name: 'kubernetes-cadvisor'
  kubernetes_sd_configs:
  - role: node
  relabel_configs:
  - action: labelmap
    regex: __meta_kubernetes_node_label_(.+)
  - source_labels: [__meta_kubernetes_node_name]
    regex: (.+)
    target_label: __address__
    replacement: ${1}:4194
- job_name: 'kubernetes-kube-state'
  kubernetes_sd_configs:
  - role: pod
  relabel_configs:
  - 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
  - source_labels: [__meta_kubernetes_pod_label_grafanak8sapp]
    regex: .*true.*
    action: keep
  - source_labels: ['__meta_kubernetes_pod_label_daemon', '__meta_kubernetes_pod_node_name']
    regex: 'node-exporter;(.*)'
    action: replace
    target_label: nodename
- job_name: 'blackbox_http_pod_probe'
  metrics_path: /probe
  kubernetes_sd_configs:
  - role: pod
  params:
    module: [http_2xx]
  relabel_configs:
  - source_labels: [__meta_kubernetes_pod_annotation_blackbox_scheme]
    action: keep
    regex: http
  - source_labels: [__address__, __meta_kubernetes_pod_annotation_blackbox_port,  __meta_kubernetes_pod_annotation_blackbox_path]
    action: replace
    regex: ([^:]+)(?::\d+)?;(\d+);(.+)
    replacement: $1:$2$3
    target_label: __param_target
  - action: replace
    target_label: __address__
    replacement: blackbox-exporter.kube-system:9115
  - source_labels: [__param_target]
    target_label: instance
  - 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
- job_name: 'blackbox_tcp_pod_probe'
  metrics_path: /probe
  kubernetes_sd_configs:
  - role: pod
  params:
    module: [tcp_connect]
  relabel_configs:
  - source_labels: [__meta_kubernetes_pod_annotation_blackbox_scheme]
    action: keep
    regex: tcp
  - source_labels: [__address__, __meta_kubernetes_pod_annotation_blackbox_port]
    action: replace
    regex: ([^:]+)(?::\d+)?;(\d+)
    replacement: $1:$2
    target_label: __param_target
  - action: replace
    target_label: __address__
    replacement: blackbox-exporter.kube-system:9115
  - source_labels: [__param_target]
    target_label: instance
  - 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
- job_name: 'traefik'
  kubernetes_sd_configs:
  - role: pod
  relabel_configs:
  - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scheme]
    action: keep
    regex: traefik
  - 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.应用资源配置清单

任意运算节点上：

[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/prometheus/rbac.yaml
serviceaccount/prometheus created
clusterrole.rbac.authorization.k8s.io/prometheus created
clusterrolebinding.rbac.authorization.k8s.io/prometheus created
[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/prometheus/dp.yaml
deployment.extensions/prometheus created
[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/prometheus/svc.yaml
service/prometheus created
[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/prometheus/ingress.yaml
ingress.extensions/prometheus created

5.解析域名

在shkf6-241.host.com上：

[root@shkf6-241 ~]# tail -1 /var/named/od.com.zone 
prometheus         A    192.168.6.66

6.浏览器访问

http://prometheus.od.com

7.Prometheus监控内容

Targets（jobs）

1.etcd

监控etcd服务

2.kubernetes-apiserver

监控apiserver服务

3.kubernetes-kubelet

监控kubelet服务

4.kubernetes-kube-state

监控基本信息

• node-exporter

监控Node节点信息

• kube-state-metrics

监控pod信息

5.traefik

监控traefik-ingress-controller

注意：在traefik的pod控制器上加annotations，并重启pod，监控生效

配置范例：

"annotations": {
  "prometheus_io_scheme": "traefik",
  "prometheus_io_path": "/metrics",
  "prometheus_io_port": "8080"
}

6.blackbox*

监控服务是否存活

• blackbox_tcp_pod_porbe

监控tcp协议服务是否存活

注意：在pod控制器上加annotations，并重启pod，监控生效

配置范例：

"annotations": {
  "blackbox_port": "20880",
  "blackbox_scheme": "tcp"
}

• blackbox_http_pod_probe

监控http协议服务是否存活

注意：在pod控制器上加annotations，并重启pod，监控生效

配置范例：

"annotations": {
  "blackbox_path": "/",
  "blackbox_port": "8080",
  "blackbox_scheme": "http"
}

7.kubernetes-pods*

监控JVM信息

注意：在pod控制器上加annotations，并重启pod，监控生效

配置范例：

"annotations": {
  "prometheus_io_scrape": "true",
  "prometheus_io_port": "12346",
  "prometheus_io_path": "/"
}

8.修改traefik服务接入prometheus监控

dashboard上：
kube-system名称空间->daemonset->traefik-ingress-controller->spec->template->metadata下，添加

"annotations": {
  "prometheus_io_scheme": "traefik",
  "prometheus_io_path": "/metrics",
  "prometheus_io_port": "8080"
}

删除pod，重启traefik，观察监控

继续添加blackbox监控配置项

"annotations": {
  "prometheus_io_scheme": "traefik",
  "prometheus_io_path": "/metrics",
  "prometheus_io_port": "8080",
  "blackbox_path": "/",
  "blackbox_port": "8080",
  "blackbox_scheme": "http"
}

9.修改dubbo-service服务接入prometheus监控

dashboard上：
app名称空间->deployment->dubbo-demo-service->spec->template=>metadata下，添加

"annotations": {
  "prometheus_io_scrape": "true",
  "prometheus_io_path": "/",
  "prometheus_io_port": "12346",
  "blackbox_port": "20880",
  "blackbox_scheme": "tcp"
}

删除pod，重启traefik，观察监控

10.修改dubbo-consumer服务接入prometheus监控

app名称空间->deployment->dubbo-demo-consumer->spec->template->metadata下，添加

"annotations": {
  "prometheus_io_scrape": "true",
  "prometheus_io_path": "/",
  "prometheus_io_port": "12346",
  "blackbox_path": "/hello",
  "blackbox_port": "8080",
  "blackbox_scheme": "http"
}

删除pod，重启traefik，观察监控

第四章：实战部署容器云监控展示平台Grafana

运维主机shkf6-245.host.com上：

1.准备grafana镜像

grafana官方dockerhub地址
grafana官方github地址
grafana官网

[root@shkf6-245 ~]# docker pull grafana/grafana:5.4.2
[root@shkf6-245 ~]# docker images |grep grafana
grafana/grafana                                   5.4.2                      6f18ddf9e552        12 months ago       243MB
[root@shkf6-245 ~]# docker tag 6f18ddf9e552 harbor.od.com/infra/grafana:v5.4.2
[root@shkf6-245 ~]# docker push harbor.od.com/infra/grafana:v5.4.2

2.准备资源配置清单

• RBAC

[root@shkf6-245 ~]# vi /data/k8s-yaml/grafana/rbac.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/grafana/rbac.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: grafana
rules:
- apiGroups:
  - "*"
  resources:
  - namespaces
  - deployments
  - pods
  verbs:
  - get
  - list
  - watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    addonmanager.kubernetes.io/mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: grafana
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: grafana
subjects:
- kind: User
  name: k8s-node

• Deployment

[root@shkf6-245 ~]# mkdir /data/nfs-volume/grafana

[root@shkf6-245 ~]# vi /data/k8s-yaml/grafana/dp.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/grafana/dp.yaml
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  labels:
    app: grafana
    name: grafana
  name: grafana
  namespace: infra
spec:
  progressDeadlineSeconds: 600
  replicas: 1
  revisionHistoryLimit: 7
  selector:
    matchLabels:
      name: grafana
  strategy:
    rollingUpdate:
      maxSurge: 1
      maxUnavailable: 1
    type: RollingUpdate
  template:
    metadata:
      labels:
        app: grafana
        name: grafana
    spec:
      containers:
      - name: grafana
        image: harbor.od.com/infra/grafana:v5.4.2
        imagePullPolicy: IfNotPresent
        ports:
        - containerPort: 3000
          protocol: TCP
        volumeMounts:
        - mountPath: /var/lib/grafana
          name: data
      imagePullSecrets:
      - name: harbor
      securityContext:
        runAsUser: 0
      volumes:
      - nfs:
          server: shkf6-245
          path: /data/nfs-volume/grafana
        name: data

• Service

[root@shkf6-245 ~]# vi /data/k8s-yaml/grafana/svc.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/grafana/svc.yaml
apiVersion: v1
kind: Service
metadata:
  name: grafana
  namespace: infra
spec:
  ports:
  - port: 3000
    protocol: TCP
    targetPort: 3000
  selector:
    app: grafana

• Ingress

[root@shkf6-245 ~]# vi /data/k8s-yaml/grafana/ingress.yaml
[root@shkf6-245 ~]# cat /data/k8s-yaml/grafana/ingress.yaml
apiVersion: extensions/v1beta1
kind: Ingress
metadata:
  name: grafana
  namespace: infra
spec:
  rules:
  - host: grafana.od.com
    http:
      paths:
      - path: /
        backend:
          serviceName: grafana
          servicePort: 3000

3.应用资源配置清单

任意运算节点上：

[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/grafana/rbac.yaml
clusterrole.rbac.authorization.k8s.io/grafana created
clusterrolebinding.rbac.authorization.k8s.io/grafana created
[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/grafana/dp.yaml
deployment.extensions/grafana created
[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/grafana/svc.yaml
service/grafana created
[root@shkf6-243 ~]# kubectl apply -f http://k8s-yaml.od.com/grafana/ingress.yaml
ingress.extensions/grafana created

4.解析域名

[root@shkf6-241 ~]# tail -1 /var/named/od.com.zone 
grafana            A    192.168.6.66

5.浏览器访问

http://grafana.od.com

• 用户名：admin
• 密 码：admin

登录后需要修改管理员密码

6.配置grafana页面

1外观

Configuration -> Preferences

• UI Theme

Light

• Home Dashboard

Default

• Timezone

Local browser time

save

2.插件

Configuration -> Plugins

• Kubernetes App

安装方法一：

grafana-cli plugins install grafana-kubernetes-app

安装方法二：

下载地址

[root@shkf6-245 ~]# cd /data/nfs-volume/grafana/plugins
[root@shkf6-245 plugins]# wget https://grafana.com/api/plugins/grafana-kubernetes-app/versions/1.0.1/download -O grafana-kubernetes-app.zip
[root@shkf6-245 plugins]# unzip grafana-kubernetes-app.zip

• Clock Pannel

安装方法一：

grafana-cli plugins install grafana-clock-panel

安装方法二：

下载地址

• Pie Chart

安装方法一：

grafana-cli plugins install grafana-piechart-panel

安装方法二：

下载地址

• D3 Gauge
  安装方法一：

grafana-cli plugins install briangann-gauge-panel

安装方法二：

下载地址

• Discrete

安装方法一：

grafana-cli plugins install natel-discrete-panel

安装方法二：

下载地址

• 重启grafana的pod

• 依次enable插件

7.配置grafana数据源

Configuration -> Data Sources
选择prometheus

• HTTP

• Auth

• TLS Auth Details

• Save & Test

8.配置Kubernetes集群Dashboard

• Configuration -> pligins -> Kubernetes

  Enable

kubernetes -> +New Cluster

• Add a new cluster

• HTTP

• Auth

将ca.pem、client.pem和client-key.pem粘贴至文本框内

• Prometheus Read

• Save

注意：

K8S Container中，所有Pannel的
pod_name -> container_label_io_kubernetes_pod_name

第五章：实战通过Alertmanager组件进行监控告警

1.准备Alertmanager镜像

在运维主机上：

[root@shkf6-245 ~]# docker pull docker.io/prom/alertmanager:v0.14.0
[root@shkf6-245 ~]# docker images |grep alertmanager
prom/alertmanager                                 v0.14.0                    23744b2d645c        22 months ago       31.9MB
[root@shkf6-245 ~]# docker tag 23744b2d645c harbor.od.com/infra/alertmanager:v0.14.0
[root@shkf6-245 ~]# docker push harbor.od.com/infra/alertmanager:v0.14.0

2.准备资源配置清单

• ConfigMap

[root@shkf6-245 ~]# vi /data/k8s-yaml/alertmanager/cm.yaml 
[root@shkf6-245 ~]# cat /data/k8s-yaml/alertmanager/cm.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: alertmanager-config
  namespace: infra
data:
  config.yml: |-
    global:
      resolve_timeout: 5m
      smtp_smarthost: 'smtp.qq.com:465'
      smtp_from: '1210353303@qq.com'
      smtp_auth_username: '1210353303@qq.com'
      smtp_auth_password: 'pzrjjrntflqeigae'
      smtp_require_tls: false
    route:
      group_by: ['alertname', 'cluster']
      group_wait: 30s

      group_interval: 5m

      repeat_interval: 5m

      receiver: default

    receivers:
    - name: 'default'
      email_configs:
      - to: 'liyanzhao@mcake.com'
        send_resolved: true

• Deployment

[root@shkf6-245 ~]# cat /data/k8s-yaml/alertmanager/dp.yaml 
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: alertmanager
  namespace: infra
spec:
  replicas: 1
  selector:
    matchLabels:
      app: alertmanager
  template:
    metadata:
      labels:
        app: alertmanager
    spec:
      containers:
      - name: alertmanager
        image: harbor.od.com/infra/alertmanager:v0.14.0
        args:
          - "--config.file=/etc/alertmanager/config.yml"
          - "--storage.path=/alertmanager"
        ports:
        - name: alertmanager
          containerPort: 9093
        volumeMounts:
        - name: alertmanager-cm
          mountPath: /etc/alertmanager
      volumes:
      - name: alertmanager-cm
        configMap:
          name: alertmanager-config
      imagePullSecrets:
      - name: harbor

• Service

[root@shkf6-245 ~]# cat /data/k8s-yaml/alertmanager/svc.yaml 
apiVersion: v1
kind: Service
metadata:
  name: alertmanager
  namespace: infra
spec:
  selector: 
    app: alertmanager
  ports:
    - port: 80
      targetPort: 9093

3.应用资源配置清单

[root@shkf6-243 ~]# kubectl apply -f  http://k8s-yaml.od.com/alertmanager/cm.yaml
[root@shkf6-243 ~]# kubectl apply -f  http://k8s-yaml.od.com/alertmanager/dp.yaml
[root@shkf6-243 ~]# kubectl apply -f  http://k8s-yaml.od.com/alertmanager/svc.yaml

4.报警规则

[root@shkf6-245 ~]# vi /data/nfs-volume/prometheus/etc/rules.yml
groups:
- name: hostStatsAlert
  rules:
  - alert: hostCpuUsageAlert
    expr: sum(avg without (cpu)(irate(node_cpu{mode!='idle'}[5m]))) by (instance) > 0.85
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "{{ $labels.instance }} CPU usage above 85% (current value: {{ $value }}%)"
  - alert: hostMemUsageAlert
    expr: (node_memory_MemTotal - node_memory_MemAvailable)/node_memory_MemTotal > 0.85
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "{{ $labels.instance }} MEM usage above 85% (current value: {{ $value }}%)"
  - alert: OutOfInodes
    expr: node_filesystem_free{fstype="overlay",mountpoint ="/"} / node_filesystem_size{fstype="overlay",mountpoint ="/"} * 100 < 10
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Out of inodes (instance {{ $labels.instance }})"
      description: "Disk is almost running out of available inodes (< 10% left) (current value: {{ $value }})"
  - alert: OutOfDiskSpace
    expr: node_filesystem_free{fstype="overlay",mountpoint ="/rootfs"} / node_filesystem_size{fstype="overlay",mountpoint ="/rootfs"} * 100 < 10
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Out of disk space (instance {{ $labels.instance }})"
      description: "Disk is almost full (< 10% left) (current value: {{ $value }})"
  - alert: UnusualNetworkThroughputIn
    expr: sum by (instance) (irate(node_network_receive_bytes[2m])) / 1024 / 1024 > 100
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Unusual network throughput in (instance {{ $labels.instance }})"
      description: "Host network interfaces are probably receiving too much data (> 100 MB/s) (current value: {{ $value }})"
  - alert: UnusualNetworkThroughputOut
    expr: sum by (instance) (irate(node_network_transmit_bytes[2m])) / 1024 / 1024 > 100
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Unusual network throughput out (instance {{ $labels.instance }})"
      description: "Host network interfaces are probably sending too much data (> 100 MB/s) (current value: {{ $value }})"
  - alert: UnusualDiskReadRate
    expr: sum by (instance) (irate(node_disk_bytes_read[2m])) / 1024 / 1024 > 50
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Unusual disk read rate (instance {{ $labels.instance }})"
      description: "Disk is probably reading too much data (> 50 MB/s) (current value: {{ $value }})"
  - alert: UnusualDiskWriteRate
    expr: sum by (instance) (irate(node_disk_bytes_written[2m])) / 1024 / 1024 > 50
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Unusual disk write rate (instance {{ $labels.instance }})"
      description: "Disk is probably writing too much data (> 50 MB/s) (current value: {{ $value }})"
  - alert: UnusualDiskReadLatency
    expr: rate(node_disk_read_time_ms[1m]) / rate(node_disk_reads_completed[1m]) > 100
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Unusual disk read latency (instance {{ $labels.instance }})"
      description: "Disk latency is growing (read operations > 100ms) (current value: {{ $value }})"
  - alert: UnusualDiskWriteLatency
    expr: rate(node_disk_write_time_ms[1m]) / rate(node_disk_writes_completedl[1m]) > 100
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Unusual disk write latency (instance {{ $labels.instance }})"
      description: "Disk latency is growing (write operations > 100ms) (current value: {{ $value }})"
- name: http_status
  rules:
  - alert: ProbeFailed
    expr: probe_success == 0
    for: 1m
    labels:
      severity: error
    annotations:
      summary: "Probe failed (instance {{ $labels.instance }})"
      description: "Probe failed (current value: {{ $value }})"
  - alert: StatusCode
    expr: probe_http_status_code <= 199 OR probe_http_status_code >= 400
    for: 1m
    labels:
      severity: error
    annotations:
      summary: "Status Code (instance {{ $labels.instance }})"
      description: "HTTP status code is not 200-399 (current value: {{ $value }})"
  - alert: SslCertificateWillExpireSoon
    expr: probe_ssl_earliest_cert_expiry - time() < 86400 * 30
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "SSL certificate will expire soon (instance {{ $labels.instance }})"
      description: "SSL certificate expires in 30 days (current value: {{ $value }})"
  - alert: SslCertificateHasExpired
    expr: probe_ssl_earliest_cert_expiry - time()  <= 0
    for: 5m
    labels:
      severity: error
    annotations:
      summary: "SSL certificate has expired (instance {{ $labels.instance }})"
      description: "SSL certificate has expired already (current value: {{ $value }})"
  - alert: BlackboxSlowPing
    expr: probe_icmp_duration_seconds > 2
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Blackbox slow ping (instance {{ $labels.instance }})"
      description: "Blackbox ping took more than 2s (current value: {{ $value }})"
  - alert: BlackboxSlowRequests
    expr: probe_http_duration_seconds > 2 
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Blackbox slow requests (instance {{ $labels.instance }})"
      description: "Blackbox request took more than 2s (current value: {{ $value }})"
  - alert: PodCpuUsagePercent
    expr: sum(sum(label_replace(irate(container_cpu_usage_seconds_total[1m]),"pod","$1","container_label_io_kubernetes_pod_name", "(.*)"))by(pod) / on(pod) group_right kube_pod_container_resource_limits_cpu_cores *100 )by(container,namespace,node,pod,severity) > 80
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "Pod cpu usage percent has exceeded 80% (current value: {{ $value }}%)"

5.prometheus加载报警规则

• 在结尾把报警配置追加上

[root@shkf6-245 ~]# vim /data/nfs-volume/prometheus/etc/prometheus.yml 

alerting:
  alertmanagers:
    - static_configs:
        - targets: ["alertmanager"]
rule_files:
 - "/data/etc/rules.yml"

• 平滑重启prometheus

[root@shkf6-243 ~]# ps -ef|grep prometheus
root     14240 14221  1 Dec24 ?        00:15:22 traefik traefik --api --kubernetes --logLevel=INFO --insecureskipverify=true --kubernetes.endpoint=https://192.168.6.66:7443 --accesslog --accesslog.filepath=/var/log/traefik_access.log --traefiklog --traefiklog.filepath=/var/log/traefik.log --metrics.prometheus
root     23839 23821 11 Dec24 ?        02:57:21 /bin/prometheus --config.file=/data/etc/prometheus.yml --storage.tsdb.path=/data/prom-db --storage.tsdb.min-block-duration=10m --storage.tsdb.retention=72h
root     25825 23546  0 10:28 pts/1    00:00:00 grep --color=auto prometheus
[root@shkf6-243 ~]# kill -SIGHUP 23839

6.验证报警

a.副本数缩为0

b.等待1分钟，查看邮件

7.钉钉报警

https://github.com/cnych/alertmanager-dingtalk-hook

https://www.cnblogs.com/wangxu01/articles/11654836.html