一、下载Alertmanager
https://prometheus.io/download/
wget https://github.com/prometheus/alertmanager/releases/download/v0.16.0-alpha.0/alertmanager-0.16.0-alpha.0.linux-amd64.tar.gz #解压 tar xf alertmanager-0.16.0-alpha.0.linux-amd64.tar.gz mv alertmanager-0.16.0-alpha.0.linux-amd64 /usr/local/alertmanager #创建数据目录 mkdir -p /data/alertmanager #创建用户 useradd prometheus chown -R prometheus:prometheus /usr/local/alertmanager /data/alertmanager/ #添加启动服务 vim /usr/lib/systemd/system/alertmanager.service [Unit] Description=Alertmanager After=network.target [Service] Type=simple User=prometheus ExecStart=/usr/local/alertmanager/alertmanager --config.file=/usr/local/alertmanager/alertmanager.yml --storage.path=/data/alertmanager Restart=on-failure [Install] WantedBy=multi-user.target #启动服务 systemctl start alertmanager.service #查看端口 [root@k8s-m alertmanger]# ss -lntp|grep 9093
LISTEN 0 128 :::9093 :::* users:(("alertmanager",pid=26298,fd=6))
浏览器访问
http://IP:9093
二、结合prometheus实现监控报警
安装prometheus
https://www.cnblogs.com/zhangb8042/p/10204997.html
#创建一个configmap(监控用的)
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-config2
namespace: kube-system
data:
rules.yml: |
groups:
- name: test-rules
rules:
- alert: InstanceDown
expr: up == 0
for: 2m
labels:
team: node
annotations:
summary: "{{$labels.instance}}: has been down"
description: "{{$labels.instance}}: job {{$labels.job}} has been down "
修改下载的prometheus.deploy.yml的配置文件(挂载上面的configmap)
apiVersion: apps/v1beta2
kind: Deployment
metadata:
labels:
name: prometheus-deployment
name: prometheus
namespace: kube-system
spec:
replicas: 1
selector:
matchLabels:
app: prometheus
template:
metadata:
labels:
app: prometheus
spec:
containers:
- image: prom/prometheus:v2.0.0
name: prometheus
command:
- "/bin/prometheus"
args:
- "--config.file=/etc/prometheus/prometheus.yml"
- "--storage.tsdb.path=/prometheus"
- "--storage.tsdb.retention=24h"
ports:
- containerPort: 9090
protocol: TCP
volumeMounts:
- mountPath: "/prometheus"
name: data
- mountPath: "/etc/prometheus"
name: config-volume
- mountPath: "/etc/rules"
name: rules
resources:
requests:
cpu: 100m
memory: 100Mi
limits:
cpu: 500m
memory: 2500Mi
serviceAccountName: prometheus
volumes:
- name: data
emptyDir: {}
- name: config-volume
configMap:
name: prometheus-config
- name: rules
configMap:
name: prometheus-config2
#修改原先的configmap文件
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-config
namespace: kube-system
data:
prometheus.yml: |
global:
scrape_interval: 15s
evaluation_interval: 15s
scrape_timeout: 15s
external_labels:
monitor: 'codelab_monitor'
alerting:
alertmanagers:
- static_configs:
- targets: ["172.31.0.248:9093"] #alertmanagers地址
rule_files: ## rule配置,首次读取默认加载,之后根据evaluation_interval设定的周期加载
- "/etc/rules/rules.yml"
scrape_configs:
- job_name: 'prometheus' # job_name默认写入timeseries的labels中,可以用于查询使用
scrape_interval: 15s # 抓取周期,默认采用global配置
static_configs: # 静态配置
- targets: ['localhost:9090'] # prometheus所要抓取数据的地址
scrape_configs:
- 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-nodes'
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
- job_name: 'kubernetes-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-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-services'
kubernetes_sd_configs:
- role: service
metrics_path: /probe
params:
module: [http_2xx]
relabel_configs:
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]
action: keep
regex: true
- source_labels: [__address__]
target_label: __param_target
- target_label: __address__
replacement: blackbox-exporter.example.com:9115
- source_labels: [__param_target]
target_label: instance
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_service_name]
target_label: kubernetes_name
- job_name: 'kubernetes-ingresses'
kubernetes_sd_configs:
- role: ingress
relabel_configs:
- source_labels: [__meta_kubernetes_ingress_annotation_prometheus_io_probe]
action: keep
regex: true
- source_labels: [__meta_kubernetes_ingress_scheme,__address__,__meta_kubernetes_ingress_path]
regex: (.+);(.+);(.+)
replacement: ${1}://${2}${3}
target_label: __param_target
- target_label: __address__
replacement: blackbox-exporter.example.com:9115
- source_labels: [__param_target]
target_label: instance
- action: labelmap
regex: __meta_kubernetes_ingress_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_ingress_name]
target_label: kubernetes_name
- 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
#重新导入所有文件
#查看prometheus页面的监控与报警项
#配置alertmanager的报警设置(我暂时使用的是email,支持微信和钉钉)
修改alertmanager.yml文件
[root@k8s-m prometheus]# cat /usr/local/alertmanager/alertmanager.yml
global:
resolve_timeout: 5m #处理超时时间,默认为5min
smtp_smarthost: 'smtp.163.com:25' # 邮箱smtp服务器代理
smtp_from: 'xxxx@163.com' # 发送邮箱名称
smtp_auth_username: 'xxxx@163.com' # 邮箱名称
smtp_auth_password: 'xxxxxxxxx' #邮箱密码
route:
group_by: ['alertname'] # 报警分组名称
group_wait: 10s # 最初即第一次等待多久时间发送一组警报的通知
group_interval: 10s # 在发送新警报前的等待时间
repeat_interval: 1m # 发送重复警报的周期
receiver: 'email' # 发送警报的接收者的名称,以下receivers name的名称
receivers:
- name: 'email' # 警报
email_configs: # 邮箱配置
- to: '18305944341@163.com' # 接收警报的email配置
inhibit_rules:
- source_match:
severity: 'critical'
target_match:
severity: 'warning'
equal: ['alertname', 'dev', 'instance']
#重启alertmanager
systemctl restart alertmanager.service
#干掉node端的kubelet
#过一会查看prometheus(出现问题了)
#查看alertmanager
#查看邮箱
#配置钉钉报警
一、下载prometheus-webhook-dingtalk插件
wget https://github.com/timonwong/prometheus-webhook-dingtalk/releases/download/v0.3.0/prometheus-webhook-dingtalk-0.3.0.linux-amd64.tar.gz tar xf prometheus-webhook-dingtalk-0.3.0.linux-amd64.tar.gz mv prometheus-webhook-dingtalk-0.3.0.linux-amd64 /usr/local ln -s /usr/local/prometheus-webhook-dingtalk-0.3.0.linux-amd64 /usr/local/prometheus-webhook-dingtalk cp default.tmpl{,.default} vim default.tmpl#修改报警模板 {{ define "__subject" }}[{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .GroupLabels.SortedPairs.Values | join " " }} {{ if gt (len .CommonLabels) (len .GroupLabels) }}({{ with .CommonLabels.Remove .GroupLabels.Names }}{{ .Values | join " " }}{{ end }}){{ end }}{{ end }} {{ define "__alertmanagerURL" }}{{ .ExternalURL }}/#/alerts?receiver={{ .Receiver }}{{ end }} {{ define "__text_alert_list" }}{{ range . }} **Labels** {{ range .Labels.SortedPairs }}> - {{ .Name }}: {{ .Value | markdown | html }} {{ end }} **Annotations** {{ range .Annotations.SortedPairs }}> - {{ .Name }}: {{ .Value | markdown | html }} {{ end }} **Source:** [{{ .GeneratorURL }}]({{ .GeneratorURL }}) {{ end }}{{ end }} {{ define "ding.link.title" }}{{ template "__subject" . }}{{ end }} {{ define "ding.link.content" }}#### \[{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}\] **[{{ index .GroupLabels "alertname" }}]({{ template "__alertmanagerURL" . }})** {{ template "__text_alert_list" .Alerts.Firing }} {{ end }} #启动prometheus-webhook-dingtalk /usr/local/prometheus-webhook-dingtalk/prometheus-webhook-dingtalk --web.listen-address="0.0.0.0:8060" --ding.profile="ops_dingding=https://oapi.dingtalk.com/robot/send?access_token=xxxxxxxxxxxxx" #钉钉机器人wehook地址
#2、修改alertmanager.yml文件
[root@k8s-m alertmanager]# cat alertmanager.yml global: resolve_timeout: 5m route: receiver: webhook group_wait: 30s group_interval: 5m repeat_interval: 4h group_by: [alertname] routes: - receiver: webhook group_wait: 10s match: team: node receivers: - name: webhook webhook_configs: - url: http://localhost:8060/dingtalk/ops_dingding/send send_resolved: true #重启alertmanager systemctl restart alertmanager.service
#钉钉报警查看