此篇文档为生产系统K8S环境迁移服务，在全部文档中编号为8,内容为使用promethus进行监控，使用grafana进行数据展示,alertmanager进行报警

数据收集模块

kube-state-metrics

kube-state-metrics,监控k8s基本状态信息的exporter,如pod运行数，deployment发版历史等

镜像准备

docker pull quay.io/coreos/kube-state-metrics:v1.5.0

rbac.yaml

apiVersion: v1
kind: Service
metadata:
  name: kube-state-metrics
  namespace: kube-system
  labels:
    k8s-app: kube-state-metrics
  annotations:
    prometheus.io/scrape: 'true'
spec:
  ports:
  - name: http-metrics
    port: 8080
    targetPort: http-metrics
    protocol: TCP
  - name: telemetry
    port: 8081
    targetPort: telemetry
    protocol: TCP
  selector:
    k8s-app: kube-state-metrics
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: kube-state-metrics
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
# kubernetes versions before 1.8.0 should use rbac.authorization.k8s.io/v1beta1
kind: Role
metadata:
  namespace: kube-system
  name: kube-state-metrics-resizer
rules:
- apiGroups: [""]
  resources:
  - pods
  verbs: ["get"]
- apiGroups: ["extensions"]
  resources:
  - deployments
  resourceNames: ["kube-state-metrics"]
  verbs: ["get", "update"]
---
apiVersion: rbac.authorization.k8s.io/v1
# kubernetes versions before 1.8.0 should use rbac.authorization.k8s.io/v1beta1
kind: RoleBinding
metadata:
  name: kube-state-metrics
  namespace: kube-system
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: kube-state-metrics-resizer
subjects:
- kind: ServiceAccount
  name: kube-state-metrics
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
# kubernetes versions before 1.8.0 should use rbac.authorization.k8s.io/v1beta1
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
  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"]
- apiGroups: ["policy"]
  resources:
  - poddisruptionbudgets
  verbs: ["list", "watch"]
---
apiVersion: rbac.authorization.k8s.io/v1
# kubernetes versions before 1.8.0 should use rbac.authorization.k8s.io/v1beta1
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  

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: quay.io/coreos/kube-state-metrics:v1.5.0
        imagePullPolicy: IfNotPresent
        ports:
        - containerPort: 8080
          name: http-metrice
          protocol: TCP
        volumeMounts:
        - mountPath: /etc/localtime
          name: localtime
        readinessProbe:
          failureThreshold: 3
          httpGet:
            path: /healthz
            port: 8080
            scheme: HTTP
          initialDelaySeconds: 5
          periodSeconds: 10
          successThreshold: 1
          timeoutSeconds: 5
      serviceAccountName: kube-state-metrics
      volumes:
      - name: localtime
        hostPath:
          path: /etc/localtime
          type: ""

node-exporter

node-exporter,收集node相关基础信息的exporter，如node机cpu,内存，磁盘信息

镜像准备

docker pull prom/node-exporter:v0.15.0

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: ""
      - name: root
        hostPath:
          path: /
          type: ""
      containers:
      - name: node-exporter
        image: prom/node-exporter:v0.15.0
        imagePullPolicy: IfNotPresent
        args:
        - --path.procfs=/host_proc
        - --path.sysfs=/host_sys
        - --collector.filesystem.ignored-mount-points
        - "^/(sys|proc|dev|host|etc|host/var/lib/docker/containers|host/var/lib/docker/overlay2|host/run/docker/netns|host/var/lib/docker/aufs|host/server/docker/overlay2)($$|/)"
        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
        - name: root
          readOnly: true
          mountPath: /host
      hostNetwork: true

cadvisor

cadvisor,监控容器内部使用资源的exporter，如pod内cpu使用信息

镜像准备

docker pull google/cadvisor:v0.28.3

安装前准备

在所有node上运行

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

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.ylls.com/public/cadvisor:0.28.3
        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
        - name: localtime
          mountPath: /etc/localtime
        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: /server/docker
      - name: localtime
        hostPath:
          path: /etc/localtime
          type: ""

black-box-exporter

black-box-exporter,探查业务容器是否存活

镜像准备

docker pull bitnami/blackbox-exporter:0.15.1

cm.yaml

apiVersion: v1
kind: ConfigMap
metadata:
  name: blackbox-exporter
  namespace: kube-system
  labels:
    app: blackbox-exporter
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

dp.yaml

apiVersion: extensions/v1beta1
kind: Deployment
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
      - name: localtime
        hostPath:
          path: /etc/localtime
          type: ""
      containers:
      - name: blackbox-exporter
        image: prom/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: 128Mi
        volumeMounts:
        - name: config
          mountPath: /etc/blackbox_exporter
        - name: localtime
          mountPath: /etc/localtime
        readinessProbe:
          tcpSocket:
            port: 9115
          initialDelaySeconds: 5
          timeoutSeconds: 5
          periodSeconds: 10
          successThreshold: 1
          failureThreshold: 3

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.yaml

apiVersion: extensions/v1beta1
kind: Ingress
metadata:
  name: blackbox-exporter
  namespace: kube-system
spec:
  rules:
  - host: blackbox.ylls.com
    http:
      paths:
      - path: /
        backend:
          serviceName: blackbox-exporter
          servicePort: blackbox-port

promethus

镜像准备

docker pull prom/prometheus:v2.14.0

安装前准备

mkdir /server/nfs/prometheus/{etc,prom-db}

cp ca.pem client.pem client-key.pem /server/nfs/prometheus/etc/

promethus的配置文件

prometheus.yml 放入/server/nfs/prometheus/etc/

global:
  scrape_interval:     15s
  evaluation_interval: 15s
scrape_configs:
- job_name: 'etcd'
  tls_config:
    ca_file: /data/etc/ca.pem
    cert_file: /data/etc/prometheus.pem
    key_file: /data/etc/prometheus-key.pem
  scheme: https
  static_configs:
  - targets:
    - '10.0.0.11:2379'
    - '10.0.0.12:2379'
    - '10.0.0.13:2379'
- 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
alerting:
  alertmanagers:
    - static_configs:
        - targets: ["alertmanager"]
rule_files:
 - "/data/etc/rules.yml"

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

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:
      containers:
      - name: prometheus
        image: prom/prometheus:v2.14.0
        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
        - name: localtime
          mountPath: /etc/localtime
        resources:
          requests:
            cpu: "1000m"
            memory: "1Gi"
          limits:
            cpu: "2000m"
            memory: "2Gi"
      imagePullSecrets:
      - name: harbor
      securityContext:
        runAsUser: 0
      serviceAccountName: prometheus
      volumes:
      - name: localtime
        hostPath:
          path: /etc/localtime
          type: ""
      - name: data
        nfs:
          server: 10.0.0.11
          path: /server/nfs/prometheus

svc.yaml

apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: infra
spec:
  ports:
  - port: 9090
    protocol: TCP
    targetPort: 9090
  selector:
    app: prometheus

ingress.yaml

apiVersion: extensions/v1beta1
kind: Ingress
metadata:
  annotations:
    kubernetes.io/ingress.class: traefik
  name: prometheus
  namespace: infra
spec:
  rules:
  - host: prometheus.ylls.com
    http:
      paths:
      - path: /
        backend:
          serviceName: prometheus
          servicePort: 9090

几种自动发现监控的情况配置

修改traefik的ds,在template中与labels平级加一段annotations（注节），重启pod生效

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

在任意pod控制器中加入,并修改端口，path监控服务是否存活
tcp
"annotations": {
     "blackbox_port": "20880",
     "blackbox_scheme": "tcp"
    }

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


在java的pod控制器中加入，监控jvm

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

grafana

镜像准备

docker pull grafana/grafana:5.4.2

安装前准备

mdkir /server/nfs/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

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.ylls.com/public/grafana:5.4.2
        imagePullPolicy: IfNotPresent
        ports:
        - containerPort: 3000
          protocol: TCP
        volumeMounts:
        - mountPath: /var/lib/grafana
          name: data
        - name: localtime
          mountPath: /etc/localtime
      imagePullSecrets:
      - name: harbor
      securityContext:
        runAsUser: 0
      volumes:
      - name: localtime
        hostPath:
          path: /etc/localtime
          type: ""
      - nfs:
          server: 10.0.0.11
          path: /server/nfs/grafana
        name: data

svc.yaml

apiVersion: v1
kind: Service
metadata:
  name: grafana
  namespace: infra
spec:
  ports:
  - port: 3000
    protocol: TCP
    targetPort: 3000
  selector:
    app: grafana

ingress.yaml

apiVersion: extensions/v1beta1
kind: Ingress
metadata:
  name: grafana
  namespace: infra
spec:
  rules:
  - host: grafana.ylls.com
    http:
      paths:
      - path: /
        backend:
          serviceName: grafana
          servicePort: 3000

grafana默认用户名admin,默认密码admin

安装后配置

安装插件

进入grafana所运行pod的bash，执行以下操作后重启生效（数据已经落盘）

grafana-cli plugins install  grafana-kubernetes-app
grafana-cli plugins install  grafana-clock-panel
grafana-cli plugins install  grafana-piechart-panel
grafana-cli plugins install  briangann-gauge-panel
grafana-cli plugins install  natel-discrete-panel

添加数据源

这部分操作简单，教程也多，这里只作个简单记录，dashboard部分个人习惯不一样，也略过

add data source

prometheus

url http://prometheus.ylls.com

Auth  Tls client auth, with ca cert

贴入 ca,client,client-key

config -> plugins -> kubernetes -> enable

kubernetes

new cluster config

name kubernetes

url https://10.0.0.11:7443(apiserver的vip地址)
access  server

auth  Tls client auth, with ca cert

贴入key

datasource   prometheus

config -> data source -> kubernetes -> save&test

alertmanager

镜像准备

docker pull docker.io/prom/alertmanager:v0.14.0

报警配置文件rules.yml

放入/server/nfs/promethus/etc/

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 }}%)"

cm.yaml

apiVersion: v1
kind: ConfigMap
metadata:
  name: alertmanager-config
  namespace: infra
data:
  config.yml: |-
    global:
      #在没有报警的情况下声明为已解决的时间
      resolve_timeout: 5m
      #配置邮件发送信息
      smtp_smarthost: 'smtp.163.com:25'
      smtp_from : 'alylls@163.com'
      smtp_auth_username: 'alylls@163.com'
      smtp_auth_password: '123456'
      smtp_require_tls: false
    #在所有报警信息进入后的根路由，用来设置报警的分发策略
    route:     #这里的标签列表是接收到报警信息后的重新分组标签，例如，接收到的报警信息里面有许多具有cluster=A和alertname=LathcyHigh这样的标签的报警信息将会批量被聚合到一个分组里面
      group_by: ['alertname','cluster']
      #当一个新的报警分组被创建后，需要等待至少group_wait时间来初始化通知，这种方式可以确保您有足够的时间为同一分组来获取多个警报，然后一起触发这个报警
      group_wait: 30s
      #当第一个报警发送后，等待'group_interval'时间来发送一组新报警
      group_interval: 5m
      #当第一个报警发送后，等待'repeat_interval'时间来重新发送他们
      repeat_interval: 5m
      #默认的receiver:如果一个报警没有被一个router匹配，则发送给默认的接收器
      receiver: default
    receivers:
    - name: 'default'
      email_configs:
      - to: 'alylls@163.com'
        send_resolved: true

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.ylls.com/public/alertmanager:0.14.0
        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

svc.yaml

apiVersion: v1
kind: Service
metadata:
  name: alertmanager
  namespace: infra
spec:
  selector:
    app: alertmanager
  ports:
    - port: 80
      targetPort: 9093