K8S 搭建 Prometheus (三) 安装和配置 Alertmanager-发送报警到 qq 邮箱

kubernetes-controller-manager, kubernetes-schedule, kubernetes-kube-proxy 监听端口

vi /etc/kubernetes/manifests/kube-scheduler.yaml
# 修改如下内容：
把 --bind-address=127.0.0.1 变成 --bind-address=192.168.1.111
把两个 httpGet: 字段下的 hosts 由 127.0.0.1 变成 192.168.1.111
把 —port=0 删除
# 注意：192.168.40.130是k8s的master1节点ip

vi /etc/kubernetes/manifests/kube-controller-manager.yaml
把 --bind-address=127.0.0.1 变成 --bind-address=192.168.1.111
把两个 httpGet: 字段下的 hosts 由 127.0.0.1 变成 192.168.1.111
把 —port=0 删除

# 修改之后在k8s各个节点执行
systemctl restart kubelet

# 因为 kube-proxy 默认端口 10249 是监听在 127.0.0.1 上的，需要改成监听到物理节点上，按如下方法修改，线上建议在安装k8s的时候就做修改，这样风险小一些：
kubectl edit configmap kube-proxy -n kube-system
# 把 metricsBindAddress 这段修改成 metricsBindAddress: 0.0.0.0:10249, 然后重新启动 kube-proxy 这个 pod

安装和配置 Alertmanager-发送报警到 qq 邮箱

# 在 master 上操作
mkdir -p /data/yaml/monitor-sa/alertmanager

# 生成一个 etcd-certs，这个在部署 prometheus 需要
kubectl -n monitor-sa create secret generic etcd-certs --from-file=/etc/kubernetes/pki/etcd/server.key  --from-file=/etc/kubernetes/pki/etcd/server.crt --from-file=/etc/kubernetes/pki/etcd/ca.crt

cat alertmanager-cm.yaml
kind: ConfigMap
apiVersion: v1
metadata:
  name: alertmanager
  namespace: monitor-sa
data:
  alertmanager.yml: |-
    global:
      resolve_timeout: 1m
      smtp_smarthost: 'smtp.126.com:25'
      smtp_from: 'klvchen@126.com'
      smtp_auth_username: 'klvchen'
      smtp_auth_password: 'IFZAIDNDGJSDLAEO'
      smtp_require_tls: false
    route:
      group_by: [alertname]
      group_wait: 10s
      group_interval: 10s
      repeat_interval: 10m
      receiver: default-receiver
    receivers:
    - name: 'default-receiver'
      email_configs:
      - to: '1158xxxxx@qq.com'
        send_resolved: true

kubectl apply -f alertmanager-cm.yaml 

cat alertmanager-deploy.yaml
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: alertmanager
  namespace: monitor-sa
  labels:
    app: alertmanager
spec:
  replicas: 1
  selector:
    matchLabels:
      app: alertmanager
  template:
    metadata:
      labels:
        app: alertmanager
      annotations:
        prometheus.io/scrape: 'false'
    spec:
      nodeName: k8s-node1
      serviceAccountName: monitor
      containers:
      - name: alertmanager
        image: harbor.junengcloud.com/monitor/alertmanager:v0.14.0
        imagePullPolicy: IfNotPresent
        args:
        - "--config.file=/etc/alertmanager/alertmanager.yml"
        - "--log.level=debug"
        ports:
        - containerPort: 9093
          protocol: TCP
          name: alertmanager
        volumeMounts:
        - name: alertmanager-config
          mountPath: /etc/alertmanager
        - name: alertmanager-storage
          mountPath: /alertmanager
        - name: localtime
          mountPath: /etc/localtime
      volumes:
        - name: alertmanager-config
          configMap:
            name: alertmanager
        - name: alertmanager-storage
          hostPath:
           path: /data/alertmanager-data
           type: DirectoryOrCreate
        - name: localtime
          hostPath:
           path: /usr/share/zoneinfo/Asia/Shanghai

kubectl apply -f alertmanager-deploy.yaml

cat alertmanager-svc.yaml
---
apiVersion: v1
kind: Service
metadata:
  labels:
    name: alertmanager
    kubernetes.io/cluster-service: 'true'
  name: alertmanager
  namespace: monitor-sa
spec:
  ports:
  - name: alertmanager
    nodePort: 30066
    port: 9093
    protocol: TCP
    targetPort: 9093
  selector:
    app: alertmanager
  sessionAffinity: None
  type: NodePort

kubectl apply -f alertmanager-svc.yaml

# 重新配置 prometheus-server
cd /data/yaml/monitor-sa/prometheus

# 根据实际情况更改 ip
cat prometheus-alertmanager-cfg.yaml

kind: ConfigMap
apiVersion: v1
metadata:
  labels:
    app: prometheus
  name: prometheus-config
  namespace: monitor-sa
data:
  prometheus.yml: |
    rule_files:
    - /etc/prometheus/rules.yml
    alerting:
      alertmanagers:
      - static_configs:
        - targets: ["alertmanager.monitor-sa:9093"]
    global:
      scrape_interval: 15s
      scrape_timeout: 10s
      evaluation_interval: 1m
    scrape_configs:
    - job_name: 'kubernetes-node'
      kubernetes_sd_configs:
      - role: node
      relabel_configs:
      - source_labels: [__address__]
        regex: '(.*):10250'
        replacement: '${1}:9100'
        target_label: __address__
        action: replace
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
    - job_name: 'kubernetes-node-cadvisor'
      kubernetes_sd_configs:
      - role:  node
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      relabel_configs:
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
      - target_label: __address__
        replacement: kubernetes.default.svc:443
      - source_labels: [__meta_kubernetes_node_name]
        regex: (.+)
        target_label: __metrics_path__
        replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
    - job_name: 'kubernetes-apiserver'
      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-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-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:$2
        source_labels:
        - __address__
        - __meta_kubernetes_pod_annotation_prometheus_io_port
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: kubernetes_namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_name
        target_label: kubernetes_pod_name
    - job_name: 'kubernetes-schedule'
      scrape_interval: 5s
      static_configs:
      - targets: ['172.16.16.100:10251']
    - job_name: 'kubernetes-controller-manager'
      scrape_interval: 5s
      static_configs:
      - targets: ['172.16.16.100:10252']
    - job_name: 'kubernetes-kube-proxy'
      scrape_interval: 5s
      static_configs:
      - targets: ['172.16.16.100:10249','172.16.16.101:10249','172.16.16.102:10249']
    - job_name: 'kubernetes-etcd'
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/ca.crt
        cert_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.crt
        key_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.key
      scrape_interval: 5s
      static_configs:
      - targets: ['172.16.16.100:2379']
  rules.yml: |
    groups:
    - name: example
      rules:
      - alert: kube-proxy的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-kube-proxy"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%"
      - alert:  kube-proxy的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-kube-proxy"}[1m]) * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%"
      - alert: scheduler的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-schedule"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%"
      - alert:  scheduler的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-schedule"}[1m]) * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%"
      - alert: controller-manager的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-controller-manager"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%"
      - alert:  controller-manager的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-controller-manager"}[1m]) * 100 > 0
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%"
      - alert: apiserver的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-apiserver"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%"
      - alert:  apiserver的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-apiserver"}[1m]) * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%"
      - alert: etcd的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-etcd"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%"
      - alert:  etcd的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-etcd"}[1m]) * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%"
      - alert: kube-state-metrics的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{k8s_app=~"kube-state-metrics"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过80%"
          value: "{{ $value }}%"
          threshold: "80%"      
      - alert: kube-state-metrics的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{k8s_app=~"kube-state-metrics"}[1m]) * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过90%"
          value: "{{ $value }}%"
          threshold: "90%"      
      - alert: coredns的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{k8s_app=~"kube-dns"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过80%"
          value: "{{ $value }}%"
          threshold: "80%"      
      - alert: coredns的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{k8s_app=~"kube-dns"}[1m]) * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过90%"
          value: "{{ $value }}%"
          threshold: "90%"      
      - alert: kube-proxy打开句柄数>600
        expr: process_open_fds{job=~"kubernetes-kube-proxy"}  > 600
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
          value: "{{ $value }}"
      - alert: kube-proxy打开句柄数>1000
        expr: process_open_fds{job=~"kubernetes-kube-proxy"}  > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
          value: "{{ $value }}"
      - alert: kubernetes-schedule打开句柄数>600
        expr: process_open_fds{job=~"kubernetes-schedule"}  > 600
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
          value: "{{ $value }}"
      - alert: kubernetes-schedule打开句柄数>1000
        expr: process_open_fds{job=~"kubernetes-schedule"}  > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
          value: "{{ $value }}"
      - alert: kubernetes-controller-manager打开句柄数>600
        expr: process_open_fds{job=~"kubernetes-controller-manager"}  > 600
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
          value: "{{ $value }}"
      - alert: kubernetes-controller-manager打开句柄数>1000
        expr: process_open_fds{job=~"kubernetes-controller-manager"}  > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
          value: "{{ $value }}"
      - alert: kubernetes-apiserver打开句柄数>600
        expr: process_open_fds{job=~"kubernetes-apiserver"}  > 600
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
          value: "{{ $value }}"
      - alert: kubernetes-apiserver打开句柄数>1000
        expr: process_open_fds{job=~"kubernetes-apiserver"}  > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
          value: "{{ $value }}"
      - alert: kubernetes-etcd打开句柄数>600
        expr: process_open_fds{job=~"kubernetes-etcd"}  > 600
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
          value: "{{ $value }}"
      - alert: kubernetes-etcd打开句柄数>1000
        expr: process_open_fds{job=~"kubernetes-etcd"}  > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
          value: "{{ $value }}"
      - alert: coredns
        expr: process_open_fds{k8s_app=~"kube-dns"}  > 600
        for: 2s
        labels:
          severity: warnning 
        annotations:
          description: "插件{{$labels.k8s_app}}({{$labels.instance}}): 打开句柄数超过600"
          value: "{{ $value }}"
      - alert: coredns
        expr: process_open_fds{k8s_app=~"kube-dns"}  > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "插件{{$labels.k8s_app}}({{$labels.instance}}): 打开句柄数超过1000"
          value: "{{ $value }}"
      - alert: kube-proxy
        expr: process_virtual_memory_bytes{job=~"kubernetes-kube-proxy"}  > 2000000000
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
          value: "{{ $value }}"
      - alert: scheduler
        expr: process_virtual_memory_bytes{job=~"kubernetes-schedule"}  > 2000000000
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
          value: "{{ $value }}"
      - alert: kubernetes-controller-manager
        expr: process_virtual_memory_bytes{job=~"kubernetes-controller-manager"}  > 2000000000
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
          value: "{{ $value }}"
      - alert: kubernetes-apiserver
        expr: process_virtual_memory_bytes{job=~"kubernetes-apiserver"}  > 2000000000
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
          value: "{{ $value }}"
      - alert: kubernetes-etcd
        expr: process_virtual_memory_bytes{job=~"kubernetes-etcd"}  > 2000000000
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
          value: "{{ $value }}"
      - alert: kube-dns
        expr: process_virtual_memory_bytes{k8s_app=~"kube-dns"}  > 2000000000
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "插件{{$labels.k8s_app}}({{$labels.instance}}): 使用虚拟内存超过2G"
          value: "{{ $value }}"
      - alert: HttpRequestsAvg
        expr: sum(rate(rest_client_requests_total{job=~"kubernetes-kube-proxy|kubernetes-kubelet|kubernetes-schedule|kubernetes-control-manager|kubernetes-apiservers"}[1m]))  > 1000
        for: 2s
        labels:
          team: admin
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): TPS超过1000"
          value: "{{ $value }}"
          threshold: "1000"   
      - alert: Pod_restarts
        expr: kube_pod_container_status_restarts_total{namespace=~"kube-system|default|monitor-sa"} > 0
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "在{{$labels.namespace}}名称空间下发现{{$labels.pod}}这个pod下的容器{{$labels.container}}被重启,这个监控指标是由{{$labels.instance}}采集的"
          value: "{{ $value }}"
          threshold: "0"
      - alert: Pod_waiting
        expr: kube_pod_container_status_waiting_reason{namespace=~"kube-system|default"} == 1
        for: 2s
        labels:
          team: admin
        annotations:
          description: "空间{{$labels.namespace}}({{$labels.instance}}): 发现{{$labels.pod}}下的{{$labels.container}}启动异常等待中"
          value: "{{ $value }}"
          threshold: "1"   
      - alert: Pod_terminated
        expr: kube_pod_container_status_terminated_reason{namespace=~"kube-system|default|monitor-sa"} == 1
        for: 2s
        labels:
          team: admin
        annotations:
          description: "空间{{$labels.namespace}}({{$labels.instance}}): 发现{{$labels.pod}}下的{{$labels.container}}被删除"
          value: "{{ $value }}"
          threshold: "1"
      - alert: Etcd_leader
        expr: etcd_server_has_leader{job="kubernetes-etcd"} == 0
        for: 2s
        labels:
          team: admin
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 当前没有leader"
          value: "{{ $value }}"
          threshold: "0"
      - alert: Etcd_leader_changes
        expr: rate(etcd_server_leader_changes_seen_total{job="kubernetes-etcd"}[1m]) > 0
        for: 2s
        labels:
          team: admin
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 当前leader已发生改变"
          value: "{{ $value }}"
          threshold: "0"
      - alert: Etcd_failed
        expr: rate(etcd_server_proposals_failed_total{job="kubernetes-etcd"}[1m]) > 0
        for: 2s
        labels:
          team: admin
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 服务失败"
          value: "{{ $value }}"
          threshold: "0"
      - alert: Etcd_db_total_size
        expr: etcd_debugging_mvcc_db_total_size_in_bytes{job="kubernetes-etcd"} > 10000000000
        for: 2s
        labels:
          team: admin
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}})：db空间超过10G"
          value: "{{ $value }}"
          threshold: "10G"
      - alert: Endpoint_ready
        expr: kube_endpoint_address_not_ready{namespace=~"kube-system|default"} == 1
        for: 2s
        labels:
          team: admin
        annotations:
          description: "空间{{$labels.namespace}}({{$labels.instance}}): 发现{{$labels.endpoint}}不可用"
          value: "{{ $value }}"
          threshold: "1"
    - name: 物理节点状态-监控告警
      rules:
      - alert: 物理节点cpu使用率
        expr: 100-avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by(instance)*100 > 90
        for: 2s
        labels:
          severity: ccritical
        annotations:
          summary: "{{ $labels.instance }}cpu使用率过高"
          description: "{{ $labels.instance }}的cpu使用率超过90%,当前使用率[{{ $value }}],需要排查处理" 
      - alert: 物理节点内存使用率
        expr: (node_memory_MemTotal_bytes - (node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes)) / node_memory_MemTotal_bytes * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          summary: "{{ $labels.instance }}内存使用率过高"
          description: "{{ $labels.instance }}的内存使用率超过90%,当前使用率[{{ $value }}],需要排查处理"
      - alert: InstanceDown
        expr: up == 0
        for: 2s
        labels:
          severity: critical
        annotations:   
          summary: "{{ $labels.instance }}: 服务器宕机"
          description: "{{ $labels.instance }}: 服务器延时超过2分钟"
      - alert: 物理节点磁盘的IO性能
        expr: 100-(avg(irate(node_disk_io_time_seconds_total[1m])) by(instance)* 100) < 60
        for: 2s
        labels:
          severity: critical
        annotations:
          summary: "{{$labels.mountpoint}} 流入磁盘IO使用率过高！"
          description: "{{$labels.mountpoint }} 流入磁盘IO大于60%(目前使用:{{$value}})"
      - alert: 入网流量带宽
        expr: ((sum(rate (node_network_receive_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance)) / 100) > 102400
        for: 2s
        labels:
          severity: critical
        annotations:
          summary: "{{$labels.mountpoint}} 流入网络带宽过高！"
          description: "{{$labels.mountpoint }}流入网络带宽持续5分钟高于100M. RX带宽使用率{{$value}}"
      - alert: 出网流量带宽
        expr: ((sum(rate (node_network_transmit_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance)) / 100) > 102400
        for: 2s
        labels:
          severity: critical
        annotations:
          summary: "{{$labels.mountpoint}} 流出网络带宽过高！"
          description: "{{$labels.mountpoint }}流出网络带宽持续5分钟高于100M. RX带宽使用率{{$value}}"
      - alert: TCP会话
        expr: node_netstat_Tcp_CurrEstab > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          summary: "{{$labels.mountpoint}} TCP_ESTABLISHED过高！"
          description: "{{$labels.mountpoint }} TCP_ESTABLISHED大于1000%(目前使用:{{$value}}%)"
      - alert: 磁盘容量
        expr: 100-(node_filesystem_free_bytes{fstype=~"ext4|xfs"}/node_filesystem_size_bytes {fstype=~"ext4|xfs"}*100) > 80
        for: 2s
        labels:
          severity: critical
        annotations:
          summary: "{{$labels.mountpoint}} 磁盘分区使用率过高！"
          description: "{{$labels.mountpoint }} 磁盘分区使用大于80%(目前使用:{{$value}}%)"

kubectl delete -f prometheus-cfg.yaml
kubectl apply -f prometheus-alertmanager-cfg.yaml


cat prometheus-alertmanager-deploy.yaml
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus-server
  namespace: monitor-sa
  labels:
    app: prometheus
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
      component: server
  template:
    metadata:
      labels:
        app: prometheus
        component: server
      annotations:
        prometheus.io/scrape: 'false'
    spec:
      nodeName: k8s-node1
      serviceAccountName: monitor
      containers:
      - name: prometheus
        image: harbor.junengcloud.com/monitor/prometheus:v2.2.1
        imagePullPolicy: IfNotPresent
        command:
        - "/bin/prometheus"
        args:
        - "--config.file=/etc/prometheus/prometheus.yml"
        - "--storage.tsdb.path=/prometheus"
        - "--storage.tsdb.retention=24h"
        - "--web.enable-lifecycle"
        ports:
        - containerPort: 9090
          protocol: TCP
        volumeMounts:
        - mountPath: /etc/prometheus
          name: prometheus-config
        - mountPath: /prometheus/
          name: prometheus-storage-volume
        - name: k8s-certs
          mountPath: /var/run/secrets/kubernetes.io/k8s-certs/etcd/
        - name: localtime
          mountPath: /etc/localtime
      volumes:
        - name: prometheus-config
          configMap:
            name: prometheus-config
        - name: prometheus-storage-volume
          hostPath:
           path: /data/prometheus-data
           type: Directory
        - name: k8s-certs
          secret:
           secretName: etcd-certs
        - name: localtime
          hostPath:
           path: /usr/share/zoneinfo/Asia/Shanghai

# 通过 kubectl apply 更新 yaml 文件
kubectl apply -f prometheus-alertmanager-deploy.yaml