一、部署prometheus
先来说明一下需要用到的组件，需要使用pv、pvc存放prometheus的数据,使用pvc存放数据即使pod挂了删除重建也不会丢失数据，使用configmap挂载prometheus的配置文件和告警规则文件，使用service开放对外访问prometheus服务的端口，使用deployment管理prometheus的pod
创建存放prometheus yaml配置的目录
mkdir /opt/prometheus && cd /opt/prometheus
需要先配置prometheus可调用k8s接口的权限
vi rabc.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: prometheus
namespace: prometheus
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: prometheus
rules:
- apiGroups:
- ""
resources:
- nodes
- services
- endpoints
- pods
- nodes/proxy
verbs:
- get
- list
- watch
- apiGroups:
- "extensions"
resources:
- ingresses
verbs:
- get
- list
- watch
- apiGroups:
- ""
resources:
- configmaps
- nodes/metrics
verbs:
- get
- nonResourceURLs:
- /metrics
verbs:
- get
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: prometheus
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: prometheus
subjects:
- kind: ServiceAccount
name: prometheus
namespace: prometheus编辑configmap配置prometheus配置文件和告警规则
vi configmap
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-conf
namespace: prometheus
labels:
app: prometheus
data:
prometheus.yml: |-
global:
scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
# scrape_timeout is set to the global default (10s).
# Alertmanager configuration
alerting:
alertmanagers:
- static_configs:
- targets:
- 10.1.60.124:30093 #配置alertmanagers的接口
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
- "/etc/prometheus/rules/*.yml" #配置规则文件存放路径
# - "second_rules.yml"
# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
# The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
- job_name: 'prometheus' #配置prometheus监控数据接口
# metrics_path defaults to '/metrics'
# scheme defaults to 'http'.
static_configs:
- targets: ['localhost:9090']
#配置consulmanage接入监控主机
- job_name: consulmanagement_node_exporter #配置node_exporter数据监控接口
scrape_interval: 15s
scrape_timeout: 5s
consul_sd_configs:
- server: '10.1.60.118:8500'
token: '5f0efcc4-860a-4d7e-a397-3b06998f3aa7'
refresh_interval: 30s
services: ['selfnode_exporter']
tags: ['linux']
relabel_configs:
- source_labels: [__meta_consul_tags]
regex: .*OFF.*
action: drop
- source_labels: ['__meta_consul_service']
target_label: cservice
- source_labels: ['__meta_consul_service_metadata_vendor']
target_label: vendor
- source_labels: ['__meta_consul_service_metadata_region']
target_label: region
- source_labels: ['__meta_consul_service_metadata_group']
target_label: group
- source_labels: ['__meta_consul_service_metadata_account']
target_label: account
- source_labels: ['__meta_consul_service_metadata_name']
target_label: name
- source_labels: ['__meta_consul_service_metadata_iid']
target_label: iid
- source_labels: ['__meta_consul_service_metadata_exp']
target_label: exp
- source_labels: ['__meta_consul_service_metadata_instance']
target_label: instance
- source_labels: [instance]
target_label: __address__
- job_name: kubernetes_cadvisor #配置cadvisor数据监控接口
kubernetes_sd_configs:
- role: node
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt #配置证书，该路径为prometheus pod内部的路径
insecure_skip_verify: true #必须加入此项配置，不然访问接口会报错
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token #配置token，该路径为prometheus pod内部的路径
relabel_configs:
- 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
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- job_name: kube-state-metrics #配置kube-state-metrics数据监控接口
kubernetes_sd_configs:
- role: endpoints
namespaces:
names:
- ops-monit
relabel_configs:
- source_labels: [__meta_kubernetes_service_label_app_kubernetes_io_name]
regex: kube-state-metrics
replacement: $1
action: keep
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: k8s_namespace
- source_labels: [__meta_kubernetes_service_name]
action: replace
target_label: k8s_sname
---
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-rules
namespace: prometheus
labels:
app: prometheus
data:
node_exporter.yml: |
groups:
- name: 服务器资源监控
rules:
- alert: 内存使用率过高
expr: 100 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 > 80
for: 3m
labels:
severity: 严重告警
annotations:
summary: "{{ $labels.instance }} 内存使用率过高, 请尽快处理！"
description: "{{ $labels.instance }}内存使用率超过80%,当前使用率{{ $value }}%."
- alert: 服务器宕机
expr: up == 0
for: 1s
labels:
severity: 严重告警
annotations:
summary: "{{$labels.instance}} 服务器宕机, 请尽快处理!"
description: "{{$labels.instance}} 服务器延时超过3分钟,当前状态{{ $value }}. "
- alert: CPU高负荷
expr: 100 - (avg by (instance,job)(irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 90
for: 5m
labels:
severity: 严重告警
annotations:
summary: "{{$labels.instance}} CPU使用率过高,请尽快处理！"
description: "{{$labels.instance}} CPU使用大于90%,当前使用率{{ $value }}%. "
- alert: 磁盘IO性能
expr: avg(irate(node_disk_io_time_seconds_total[1m])) by(instance,job)* 100 > 90
for: 5m
labels:
severity: 严重告警
annotations:
summary: "{{$labels.instance}} 流入磁盘IO使用率过高,请尽快处理！"
description: "{{$labels.instance}} 流入磁盘IO大于90%,当前使用率{{ $value }}%."
- alert: 网络流入
expr: ((sum(rate (node_network_receive_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance,job)) / 100) > 102400
for: 5m
labels:
severity: 严重告警
annotations:
summary: "{{$labels.instance}} 流入网络带宽过高，请尽快处理！"
description: "{{$labels.instance}} 流入网络带宽持续5分钟高于100M. RX带宽使用量{{$value}}."
- alert: 网络流出
expr: ((sum(rate (node_network_transmit_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance,job)) / 100) > 102400
for: 5m
labels:
severity: 严重告警
annotations:
summary: "{{$labels.instance}} 流出网络带宽过高,请尽快处理！"
description: "{{$labels.instance}} 流出网络带宽持续5分钟高于100M. RX带宽使用量{$value}}."
- alert: TCP连接数
expr: node_netstat_Tcp_CurrEstab > 10000
for: 2m
labels:
severity: 严重告警
annotations:
summary: " TCP_ESTABLISHED过高！"
description: "{{$labels.instance}} TCP_ESTABLISHED大于100%,当前使用率{{ $value }}%."
- alert: 磁盘容量
expr: 100-(node_filesystem_free_bytes{fstype=~"ext4|xfs"}/node_filesystem_size_bytes {fstype=~"ext4|xfs"}*100) > 90
for: 1m
labels:
severity: 严重告警
annotations:
summary: "{{$labels.mountpoint}} 磁盘分区使用率过高，请尽快处理！"
description: "{{$labels.instance}} 磁盘分区使用大于90%，当前使用率{{ $value }}%."
blackbox_exporter.yml: |
groups:
- name: Domain
rules:
- alert: 站点可用性
expr: probe_success{job="blackbox_exporter"} == 0
for: 1m
labels:
alertype: domain
severity: critical
annotations:
description: "{{ $labels.env }}_{{ $labels.name }}({{ $labels.project }})：站点无法访问\n> {{ $labels.instance }}"
- alert: 站点1h可用性低于80%
expr: sum_over_time(probe_success{job="blackbox_exporter"}[1h])/count_over_time(probe_success{job="blackbox_exporter"}[1h]) * 100 < 80
for: 3m
labels:
alertype: domain
severity: warning
annotations:
description: "{{ $labels.env }}_{{ $labels.name }}({{ $labels.project }})：站点1h可用性：{{ $value | humanize }}%\n> {{ $labels.instance }}"
- alert: 站点状态异常
expr: (probe_success{job="blackbox_exporter"} == 0 and probe_http_status_code > 499) or probe_http_status_code == 0
for: 1m
labels:
alertype: domain
severity: warning
annotations:
description: "{{ $labels.env }}_{{ $labels.name }}({{ $labels.project }})：站点状态异常：{{ $value }}\n> {{ $labels.instance }}"
- alert: 站点耗时过高
expr: probe_duration_seconds > 0.5
for: 2m
labels:
alertype: domain
severity: warning
annotations:
description: "{{ $labels.env }}_{{ $labels.name }}({{ $labels.project }})：当前站点耗时：{{ $value | humanize }}s\n> {{ $labels.instance }}"
- alert: SSL证书有效期
expr: (probe_ssl_earliest_cert_expiry-time()) / 3600 / 24 < 15
for: 2m
labels:
alertype: domain
severity: warning
annotations:
description: "{{ $labels.env }}_{{ $labels.name }}({{ $labels.project }})：证书有效期剩余{{ $value | humanize }}天\n> {{ $labels.instance }}"
编辑pv、pvc配置
vi pv.yaml
apiVersion: v1
kind: PersistentVolume
metadata:
name: "prometheus-data-pv"
labels:
name: prometheus-data-pv
release: stable
spec:
capacity:
storage: 5Gi
accessModes:
- ReadWriteMany #配置读写方式
persistentVolumeReclaimPolicy: Retain #配置回收策略为Retain，既删除pv保留数据
storageClassName: nfs #使用nfs存储
nfs: #配置nfs路径信息
path: /volume2/k8s-data/prometheus
server: 10.1.13.99vi pvc.yaml
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: prometheus-data-pvc
namespace: prometheus
spec:
accessModes:
- ReadWriteMany
resources:
requests:
storage: 5Gi
selector:
matchLabels:
name: prometheus-data-pv
release: stable
storageClassName: nfs编辑deployment配置
vi deployment.yaml
kind: Deployment
apiVersion: apps/v1
metadata:
labels:
app: prometheus
name: prometheus
namespace: prometheus
spec:
replicas: 1
revisionHistoryLimit: 10
selector:
matchLabels:
app: prometheus
template:
metadata:
labels:
app: prometheus
spec:
serviceAccountName: prometheus #配置serviceaccount权限
securityContext:
runAsUser: 0
containers:
- name: prometheus
image: prom/prometheus:latest
imagePullPolicy: IfNotPresent
command:
- prometheus
- --config.file=/etc/prometheus/prometheus.yml #配置文件目录
- --storage.tsdb.path=/prometheus #配置数据目录
- --web.enable-lifecycle #开启prometheus配置文件热加载
volumeMounts:
- mountPath: /etc/localtime
name: tz-config
- mountPath: /prometheus
name: prometheus-data-volume
- mountPath: /etc/prometheus
name: prometheus-conf-volume
- mountPath: /etc/prometheus/rules
name: prometheus-rules-volume
ports:
- containerPort: 9090
protocol: TCP
volumes:
- name: tz-config #挂载时间配置，与宿主机配置时间同步
hostPath:
path: /usr/share/zoneinfo/Asia/Shanghai
- name: prometheus-data-volume #挂载pvc存放数据
persistentVolumeClaim:
claimName: prometheus-data-pvc
- name: prometheus-conf-volume #通过configmap挂载prometheus配置
configMap:
name: prometheus-conf
- name: prometheus-rules-volume #通过configmap挂载prometheus告警规则配置
configMap:
name: prometheus-rules
tolerations:
- key: node-role.kubernetes.io/master
effect: NoSchedule编辑service配置
vi service.yaml
kind: Service
apiVersion: v1
metadata:
annotations:
prometheus.io/scrape: 'true'
labels:
app: prometheus
name: prometheus-service
namespace: prometheus
spec:
ports:
- port: 9090
targetPort: 9090
nodePort: 30090
selector:
app: prometheus
type: NodePort至此创建prometheus的yaml文件准备完成，接下来先创建命名空间，在创建yaml
kubectl create namespace prometheus
kubectl apply -f rabc.yaml
kubectl apply -f configmap
kubectl apply -f pvc.yaml
kubectl apply -f pv.yaml
kubectl apply -f deployment.yaml
kubectl apply -f service.yaml
查看创建的各项服务是否正常
kubectl get pod,svc,configmap,pv,pvc,sa -n prometheus
通过service服务访问prometheus web检查Prometheus服务
http://10.1.60.124:30090
这里再补充一下关于prometheus热加载，和configmap自动更新的问题
configmap的yaml文件更新配置后使用apply重载，会自动更新挂载了该configmap配置的pod中的配置文件，不过需要一小会才会自动更新，但是如果在pod挂载configmap的配置中加入了subpath配置的话，configmap更新配置后，是不会自动更新pod里挂载的配置，需要将pod删除重建才会更新里面的配置
在配置了热加载的prometheus中，修改了配置文件，可以不用重启prometheus就可以加载新的配置文件，使用以下命令
curl -X POST -Ls http://10.1.60.124:30090/-/reload
查看是否成功重载
kubectl logs prometheus-5b95bdc6b8-tfpwf -n prometheus | grep "Loading configuration file"
二、部署grafana服务
创建grafana只需要deployment、service、pv、pvc服务即可，grafana也需要存储配置信息
先创建grafana的yaml配置文件目录
mkdit /opt/grafana && cd /opt/grafana
创建pvc、pv的yaml配置文件
vi pv.yaml
apiVersion: v1
kind: PersistentVolume
metadata:
name: "grafana-data-pv"
labels:
name: grafana-data-pv
release: stable
spec:
capacity:
storage: 5Gi
accessModes:
- ReadWriteMany
persistentVolumeReclaimPolicy: Retain
storageClassName: nfs
nfs:
path: /volume2/k8s-data/grafana
server: 10.1.13.99vi pvc.yaml
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: grafana-data-pvc
namespace: prometheus
spec:
accessModes:
- ReadWriteMany
resources:
requests:
storage: 5Gi
selector:
matchLabels:
name: grafana-data-pv
release: stable
storageClassName: nfs创建deployment的yaml配置文件
vi deployment.yaml
kind: Deployment
apiVersion: apps/v1
metadata:
labels:
app: grafana
name: grafana
namespace: prometheus
spec:
replicas: 1
revisionHistoryLimit: 10
selector:
matchLabels:
app: grafana
template:
metadata:
labels:
app: grafana
spec:
securityContext:
runAsUser: 0
containers:
- name: grafana
image: grafana/grafana:9.5.2
imagePullPolicy: IfNotPresent
env:
- name: GF_AUTH_BASIC_ENABLED
value: "true"
- name: GF_AUTH_ANONYMOUS_ENABLED
value: "false"
readinessProbe:
httpGet:
path: /login
port: 3000
volumeMounts:
- mountPath: /etc/localtime
name: tz-config
- mountPath: /var/lib/grafana
name: grafana-data-volume
ports:
- containerPort: 3000
protocol: TCP
volumes:
- name: tz-config
hostPath:
path: /usr/share/zoneinfo/Asia/Shanghai
- name: grafana-data-volume
persistentVolumeClaim:
claimName: grafana-data-pvc创建service的yaml配置文件
kind: Service
apiVersion: v1
metadata:
labels:
app: grafana
name: grafana-service
namespace: prometheus
spec:
ports:
- port: 3000
targetPort: 3000
nodePort: 30300
selector:
app: grafana
type: NodePort至此创建grafana的yaml文件准备完成，接下来使用yaml文件创建各个服务
kubectl apply -f pvc.yaml
kubectl apply -f pv.yaml
kubectl apply -f deployment.yaml
kubectl apply -f service.yaml
查看创建的各项服务是否正常
kubectl get pod,pv,pvc,svc -n prometheus
通过service访问grafana web 服务
初始账户和密码为admin/admin，登录后会要求更改密码
http://10.1.60.124:30300
三、部署 prometheus-webhook-dingtalk
使用钉钉发送告警信息，所以部署prometheus-webhook-dingtalk服务，需要使用到deployment、configmap、service服务
创建prometheus-webhook-dingtalk yaml文件目录
mkdir /opt/prometheus-webhook-dingtalk && cd /opt/prometheus-webhook-dingtalk
编辑configmap的yaml文件
vi configmap.yaml
apiVersion: v1 #该configmap有两个配置文件，一个是dingtalk服务的配置文件，一个是关于告警消息的模板文件
data:
config.yml: |- #配置文件
templates:
- /etc/prometheus-webhook-dingtalk/template.tmpl #配置模板文件存放目录
targets:
webhook1:
#钉钉机器人webhook设置
url: https://oapi.dingtalk.com/robot/send?access_token=cfe1e0d1cfb457a31b20d6005785f5c7367542d5bd82725eb1b2f6738d0be418
# secret for signature
secret: SEC60b0e5076407b1d1d97c26afa2acb54edf7270b9e23826a65c3f085e48c5dcfd
template.tmpl: |- #配置告警消息模板文件
{{ define "__subject" }}
[{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}]
{{ end }}
{{ define "__alert_list" }}{{ range . }}
---
{{ if .Labels.owner }}@{{ .Labels.owner }}{{ end }}
**告警主题**: {{ .Annotations.summary }}
**告警类型**: {{ .Labels.alertname }}
**告警级别**: {{ .Labels.severity }}
**告警主机**: {{ .Labels.instance }}
**告警信息**: {{ index .Annotations "description" }}
**告警时间**: {{ dateInZone "2006.01.02 15:04:05" (.StartsAt) "Asia/Shanghai" }}
{{ end }}{{ end }}
{{ define "__resolved_list" }}{{ range . }}
---
{{ if .Labels.owner }}@{{ .Labels.owner }}{{ end }}
**告警主题**: {{ .Annotations.summary }}
**告警类型**: {{ .Labels.alertname }}
**告警级别**: {{ .Labels.severity }}
**告警主机**: {{ .Labels.instance }}
**告警信息**: {{ index .Annotations "description" }}
**告警时间**: {{ dateInZone "2006.01.02 15:04:05" (.StartsAt) "Asia/Shanghai" }}
**恢复时间**: {{ dateInZone "2006.01.02 15:04:05" (.EndsAt) "Asia/Shanghai" }}
{{ end }}{{ end }}
{{ define "default.title" }}
{{ template "__subject" . }}
{{ end }}
{{ define "default.content" }}
{{ if gt (len .Alerts.Firing) 0 }}
**====侦测到{{ .Alerts.Firing | len }}个故障====**
{{ template "__alert_list" .Alerts.Firing }}
---
{{ end }}
{{ if gt (len .Alerts.Resolved) 0 }}
**====恢复{{ .Alerts.Resolved | len }}个故障====**
{{ template "__resolved_list" .Alerts.Resolved }}
{{ end }}
{{ end }}
{{ define "ding.link.title" }}{{ template "default.title" . }}{{ end }}
{{ define "ding.link.content" }}{{ template "default.content" . }}{{ end }}
{{ template "default.title" . }}
{{ template "default.content" . }}
kind: ConfigMap
metadata:
name: dingtalk-conf
namespace: prometheus编辑deployment的yaml文件
vi deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: dingtalk
namespace: prometheus
labels:
app: dingtalk
spec:
replicas: 1
selector:
matchLabels:
app: dingtalk
template:
metadata:
labels:
app: dingtalk
spec:
restartPolicy: "Always"
containers:
- name: dingtalk
image: timonwong/prometheus-webhook-dingtalk
imagePullPolicy: "IfNotPresent"
volumeMounts:
- name: dingtalk-conf
mountPath: /etc/prometheus-webhook-dingtalk/
resources:
limits:
cpu: "400m"
memory: "500Mi"
requests:
cpu: "100m"
memory: "100Mi"
ports:
- containerPort: 8060
name: http
protocol: TCP
readinessProbe:
failureThreshold: 3
periodSeconds: 5
initialDelaySeconds: 30
successThreshold: 1
tcpSocket:
port: 8060
livenessProbe:
tcpSocket:
port: 8060
initialDelaySeconds: 30
periodSeconds: 10
volumes:
- name: dingtalk-conf #因为只使用了一个configmap服务，所以告警消息模板和配置文件都会挂载到同一目录中
configMap:
name: dingtalk-conf编辑service的yaml文件
vi service.yaml
apiVersion: v1
kind: Service
metadata:
name: dingtalk
namespace: prometheus
spec:
selector:
app: dingtalk
ports:
- name: http
protocol: TCP
port: 8060
targetPort: 8060
nodePort: 30806
type: NodePort至此创建prometheus-webhook-dingtalk的yaml文件准备完成，接下来使用yaml文件创建各个服务
kubectl apply -f configmap.yaml
kubectl apply -f deployment.yaml
kubectl apply -f service.yaml
查看创建的各项服务是否正常
kubectl get pod,configmap,svc -n prometheus
对于prometheus-webhook-dingtalk服务就只是用来将alertmanager告警的信息通过模板在推送到钉钉上，并不存储数据
四、部署alertmanager服务
部署alertmanager服务需要使用到configmap、deployment、serivce服务
创建存放alertmanager yaml配置文件的目录
mkdir /opt/alertmanager && cd /opt/alertmanager
编辑configmap的yaml文件
vi configmap.yaml
apiVersion: v1
data:
alertmanager.yml: |-
route:
group_by: ['dingding']
group_wait: 30s
group_interval: 5m
repeat_interval: 1h
receiver: 'web.hook'
routes:
- receiver: 'web.hook'
match_re:
alertname: ".*"
receivers:
- name: 'web.hook'
webhook_configs:
- url: 'http://10.1.60.124:30806/dingtalk/webhook1/send' #配置prometheus-webhook-dingtalk的服务接口
send_resolved: true
inhibit_rules:
- source_match:
severity: 'critical'
target_match:
severity: 'warning'
equal: ['alertname', 'dev', 'instance']
kind: ConfigMap
metadata:
name: alertmanager-conf
namespace: prometheus编辑deployment的yaml文件
vi deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: alertmanager
namespace: prometheus
labels:
app: alertmanager
spec:
replicas: 1
selector:
matchLabels:
app: alertmanager
template:
metadata:
labels:
app: alertmanager
spec:
containers:
- name: alertmanager
image: "prom/alertmanager"
imagePullPolicy: "IfNotPresent"
ports:
- containerPort: 9093
readinessProbe:
httpGet:
path: /#/status
port: 9093
initialDelaySeconds: 30
timeoutSeconds: 30
volumeMounts:
- name: config-volume
mountPath: /etc/alertmanager
- name: tz-config
mountPath: /etc/localtime
resources:
limits:
cpu: 10m
memory: 50Mi
requests:
cpu: 10m
memory: 50Mi
volumes:
- name: config-volume
configMap:
name: alertmanager-conf
- name: tz-config
hostPath:
path: /usr/share/zoneinfo/Asia/Shanghai编辑service的yaml文件
vi service.yaml
apiVersion: v1
kind: Service
metadata:
name: svc-alertmanager
namespace: prometheus
spec:
type: NodePort
ports:
- port: 9093
protocol: TCP
targetPort: 9093
nodePort: 30093
selector:
app: alertmanager至此创建alertmanager的yaml文件准备完成，接下来使用yaml文件创建各个服务
kubectl apply -f configmap.yaml
kubectl apply -f deployment.yaml
kubectl apply -f service.yaml
查看创建的各项服务是否正常
kubectl get pod,configmap,svc -n prometheus
至此关于在k8s内部署整个prometheus监控通过钉钉告警已经完成 ，关于告警的测试就自行测试，我这边测试过是没有问题的
