dce容器

回顾

prometheus地址

https://prometheus.io
https:///prometheus

prometheus特点

prometheus架构介绍

prometheus 和zabbix 对比

exporter

监控k8s里的微服务，今天需要4个exporter。

kube-state-metric

收集k8s的基本状态信息的exporter，有几个节点等。

docker pull quay.io/coreos/kube-state-metrics:v1.5.0
docker tag 91599517197a /public/kube-state-metrics:v1.5.0
docker push /public/kube-state-metrics:v1.5.0

vi rbac.yaml
iapiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    /mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: kube-state-metrics
  namespace: kube-system
---
apiVersion: /v1
kind: ClusterRole
metadata:
  labels:
    /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: /v1
kind: ClusterRoleBinding
metadata:
  labels:
    /mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: kube-state-metrics
roleRef:
  apiGroup: 
  kind: ClusterRole
  name: kube-state-metrics
subjects:
- kind: ServiceAccount
  name: kube-state-metrics
  namespace: kube-system


vi dp.yaml
iapiVersion: extensions/v1beta1
kind: Deployment
metadata:
  annotations:
    /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: /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

kubectl apply -f http:///kube-state-metrics/rbac.yaml
kubectl apply -f http:///kube-state-metrics/dp.yaml

curl 172.7.21.11:8080/healthz
ok

node-exporter

收集运算节点上基础设施信息等。部署到所有运算节点上。

去docker hub。
~]# docker pull prom/node-exporter:v0.15.0
docker tag 12d51ffa2b22 /public/node-exporter:v0.15.0
docker push !$
cd /data/k8s-yaml
mkdir node-exporter
cd node-exporter
# 配置一个ds，每一个运算节点都有
vi ds.yaml
ikind: 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: /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

curl 10.4.7.11:9100/metrics

cadvisor

监控容器内部使用资源的工具。

~]# docker pull google/cadvisor:v0.28.3
# 版本更新比较快，内核3.10 用0.28.3 就可以了。0.30 都不能对内核3.10使用。
# 每一个kubelet 上运行一个一个cadvisor，1，9以前的k8s集群，kubelet集成了cadvisor。


vi ds.yaml
iapiVersion: 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: /master
        effect: NoSchedule
      containers:
      - name: cadvisor
        image: /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

# 修改所有运算节点软连接
~]# mount -o remount,rw /sys/fs/cgroup/
~]# ln -s /sys/fs/cgroup/cpu,cpuacct /sys/fs/cgroup/cpuacct,cpu
# 官网
https://kubernetes.io/zh/docs/concepts/configuration/taint-and-toleration/

blackbox-exporter

帮助你探明业务容器是否存活。http的标准操作。

~]# docker pull prom/blackbox-exporter:v0.15.1

vi cm.yaml
iapiVersion: 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
		
vi dp.yaml
ikind: Deployment
apiVersion: extensions/v1beta1
metadata:
  name: blackbox-exporter
  namespace: kube-system
  labels:
    app: blackbox-exporter
  annotations:
    /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: /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
		
vi svc.yaml
ikind: Service
apiVersion: v1
metadata:
  name: blackbox-exporter
  namespace: kube-system
spec:
  selector:
    app: blackbox-exporter
  ports:
    - name: blackbox-port
      protocol: TCP
      port: 9115

vi ingress.yaml
iapiVersion: extensions/v1beta1
kind: Ingress
metadata:
  name: blackbox-exporter
  namespace: kube-system
spec:
  rules:
  - host: 
    http:
      paths:
      - path: /
        backend:
          serviceName: blackbox-exporter
          servicePort: blackbox-port

解析

污点容忍度调度补充

kubeclt create deployment nginx-dp --image=harnor.od.com/public/nginx:v1.7.9 -n kube-public

NoExecute的污点会使得21上的pod会被驱逐。

要下线维修，先加NoExecute的污点，把本身的pod排干，在delete node。

安装部署prometheus-server

如果用kubadmin 部署的话，相当于把k8s的组件以pod形式部署都运算节点，
cadvisor的容忍度就是，容忍这个运算节点的污点。这个污点不让业务pod混了。

docker pull prom/prometheus:v2.14.0
docker push /infra/prometheus:v2.14.0

vi rbac.yaml
iapiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    /mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: prometheus
  namespace: infra
---
apiVersion: /v1
kind: ClusterRole
metadata:
  labels:
    /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: /v1
kind: ClusterRoleBinding
metadata:
  labels:
    /mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: prometheus
roleRef:
  apiGroup: 
  kind: ClusterRole
  name: prometheus
subjects:
- kind: ServiceAccount
  name: prometheus
  namespace: infra
  
vi dp.yaml
iapiVersion: extensions/v1beta1
kind: Deployment
metadata:
  annotations:
    /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: hsdd7-21.host.com
      containers:
      - name: prometheus
        image: /infra/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
        resources:
          requests:
            cpu: "1000m"	# 1000毫核，就是1核
            memory: "1.5Gi"
          limits:
            cpu: "2000m"
            memory: "3Gi"
      imagePullSecrets:
      - name: harbor
      securityContext:
        runAsUser: 0
      serviceAccountName: prometheus
      volumes:
      - name: data
        nfs:
          server: hdss7-200
          path: /data/nfs-volume/prometheus
vi svc.yaml
iapiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: infra
spec:
  ports:
  - port: 9090
    protocol: TCP
    targetPort: 9090
  selector:
    app: prometheus
	
vi ingress.yaml
iapiVersion: extensions/v1beta1
kind: Ingress
metadata:
  annotations:
    kubernetes.io/ingress.class: traefik
  name: prometheus
  namespace: infra
spec:
  rules:
  - host: 
    http:
      paths:
      - path: /
        backend:
          serviceName: prometheus
          servicePort: 9090

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:
    - '10.4.7.12:2379'
    - '10.4.7.21:2379'
    - '10.4.7.22:2379'
- 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

target 就是job的集合，job通过label，可以定义哪些pod 收集到我的job里。
node_cpu，这个监控指标交函数，是exporter定义的，可以给它传递参数，就是传递标签。

配置prometheus监控业务容器

给元数据添加以下说明：
"annotations": {
  "prometheus_io_scheme": "traefik",
  "prometheus_io_path": "/metrics",
  "prometheus_io_port": "8080"
}
修改traefik的ds，在template的label下边添加。

一个业务容器，被prom自动发现，检测这个容器是否一直存活，找endpoint，实际请求blackbox，把业务容器的地址和端口当成参数，传递给blackbox，blackbox去curl业务容器，返回给prom。

修改dubbo服务的dp。修改完scale从0到1.
blackbox
tcp
"annotations": {
  "blackbox_port": "20880",
  "blackbox_scheme": "tcp"
}
http
"annotations": {
  "blackbox_path": "/",
  "blackbox_port": "8080",
  "blackbox_scheme": "http"
}

安装部署配置grafana

~]# docker pull grafana/grafana:5.4.2
# 安装插件，安装完之后重启pod。
vi rbac.yaml
iapiVersion: /v1
kind: ClusterRole
metadata:
  labels:
    /mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: grafana
rules:
- apiGroups:
  - "*"
  resources:
  - namespaces
  - deployments
  - pods
  verbs:
  - get
  - list
  - watch
---
apiVersion: /v1
kind: ClusterRoleBinding
metadata:
  labels:
    /mode: Reconcile
    kubernetes.io/cluster-service: "true"
  name: grafana
roleRef:
  apiGroup: 
  kind: ClusterRole
  name: grafana
subjects:
- kind: User
  name: k8s-node
  
vi dp.yaml
iapiVersion: 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: /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: hdss7-200
          path: /data/nfs-volume/grafana
        name: data

vi svc.yaml
iapiVersion: v1
kind: Service
metadata:
  name: grafana
  namespace: infra
spec:
  ports:
  - port: 3000
    protocol: TCP
    targetPort: 3000
  selector:
    app: grafana
	
vi ingress.yaml
iapiVersion: extensions/v1beta1
kind: Ingress
metadata:
  name: grafana
  namespace: infra
spec:
  rules:
  - host: 
    http:
      paths:
      - path: /
        backend:
          serviceName: grafana
          servicePort: 3000
		  
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

重启pod---进入浏览器---修改密码---修改preferences
add source data--- 配置plugin里的k8s

cat /opt/certs/ca.pem
cat /opt/certs/client.pem
cat /opt/certs/client-key.pem

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

故障整理

1、机器挂机，节点down掉
重启服务，看日志，发现docker没有启动，后来发现vip的nginx没有启动，重启所有服务。
2、harbor挂掉
重新执行， 启动nginx。

部署alertmanager

# 0.19.0 有问题，，再测试测试。先用0.14.0
~]# docker pull /prom/alertmanager:v0.14.0
vi cm.yaml
iapiVersion: 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: ':25'
      smtp_from: '[e-mail]'
      smtp_auth_username: '[e-mail]'
      smtp_auth_password: 'xxx'
      smtp_require_tls: false
    # 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=LatncyHigh 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能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信息。
      group_wait: 30s

      # 当第一个报警发送后，等待'group_interval'时间来发送新的一组报警信息。
      group_interval: 5m

      # 如果一个报警信息已经发送成功了，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route匹配，则发送给默认的接收器
      receiver: default

    receivers:
    - name: 'default'
      email_configs:
      - to: '393353713@'

vi dp.yaml
iapiVersion: 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: /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
	  
vi svc.yaml
iapiVersion: v1
kind: Service
metadata:
  name: alertmanager
  namespace: infra
spec:
  selector: 
    app: alertmanager
  ports:
    - port: 80
      targetPort: 9093


vi /data/nfs-volume/prometheus/etc/rules.yml
igroups:
- 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 }}%)"
	  
prometheus.yml

alerting:
  alertmanagers:
    - static_configs:
        - targets: ["alertmanager"]   # 这个是svc的名字，如果alert跟prometheus不在一个名称空间，还需要添加名称空间的名字。
rule_files:
 - "/data/etc/rules.yml"