装置Prometheus
wget https://github.com/prometheus...
tar -zxvf prometheus-2.34.0.linux-amd64.tar.gz
mv prometheus-2.34.0.linux-amd64 prometheus
vim prometheus.yml
# my global configglobal: 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 configurationalerting: alertmanagers: - static_configs: - targets: - localhost:9093# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.rule_files: - "rules/host_rules.yml" # - "first_rules.yml" # - "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" # metrics_path defaults to '/metrics' # scheme defaults to 'http'. static_configs: - targets: ["localhost:9090"] - job_name: 'agent-web01' static_configs: - targets: ['172.31.32.104:9100'] - job_name: 'agent-web02' static_configs: - targets: ['172.31.29.223:9100'] - job_name: 'java' static_configs: - targets: ['172.31.29.223:8100'] metrics_path: '/actuator/prometheus'创立规定
mkdir -p /root/prometheus/rules
cat host_rules.yml
groups:- name: 系统资源告警规定 rules: - alert: CPU使用率告警 expr: 100 - (avg by (instance)(irate(node_cpu_seconds_total{mode="idle"}[1m]) )) * 100 > 80 for: 1m labels: user: prometheus severity: warning annotations: description: "服务器: CPU应用超过80%！(以后值: {{ humanize $value }}%)" - alert: 内存使用率告警 expr: (node_memory_MemTotal_bytes - (node_memory_MemFree_bytes+node_memory_Buffers_bytes+node_memory_Cached_bytes )) / node_memory_MemTotal_bytes * 100 > 80 for: 1m labels: user: prometheus severity: warning annotations: description: "服务器: 内存应用超过80%！(以后值: {{ humanize $value }}%)" - alert: 磁盘告警规定 expr: 100 - (node_filesystem_free_bytes{mountpoint="/",fstype=~"ext4|xfs"} / node_filesystem_size_bytes{fstype=~"ext4|xfs"} * 100) > 70 for: 1m labels: user: prometheus severity: warning annotations: description: "服务器: 磁盘应用超过70%！(以后值: {{ humanize $value }}%)"启动
nohup ./prometheus &
效果图
装置alertmanager
wget https://github.com/prometheus...
tar -zxvf alertmanager-0.24.0.linux-amd64.tar.gz
mv alertmanager-0.24.0.linux-amd64 alertmanager
vim alertmanager.yml
具体能够去企业微信后盾查找相干参数
global: resolve_timeout: 2m wechat_api_url: 'https://qyapi.weixin.qq.com/cgi-bin/' wechat_api_secret: '<你的企业微信secret>' wechat_api_corp_id: '<你的企业微信id>'route: group_by: ['alertname'] group_wait: 10s group_interval: 10s repeat_interval: 1h receiver: 'wechat'receivers:- name: 'wechat' wechat_configs: - send_resolved: true to_party: '1' agent_id: '<你的企业微信利用id>'templates: - '/alertmanager/*.tmpl'yaml语法查看
./amtool check-config alertmanager.yml
企业微信报警模板
cat wechat.tmpl
{{ define "wechat.default.message" }}{{- if gt (len .Alerts.Firing) 0 -}}{{- range $index, $alert := .Alerts -}}======== 异样告警 ========告警名称：{{ $alert.Labels.alertname }}告警级别：{{ $alert.Labels.severity }}告警机器：{{ $alert.Labels.instance }} {{ $alert.Labels.device }}告警详情：{{ $alert.Annotations.summary }}告警工夫：{{ $alert.StartsAt.Format "2006-01-02 15:04:05" }}========== END =========={{- end }}{{- end }}{{- if gt (len .Alerts.Resolved) 0 -}}{{- range $index, $alert := .Alerts -}}======== 告警复原 ========告警名称：{{ $alert.Labels.alertname }}告警级别：{{ $alert.Labels.severity }}告警机器：{{ $alert.Labels.instance }}告警详情：{{ $alert.Annotations.summary }}告警工夫：{{ $alert.StartsAt.Format "2006-01-02 15:04:05" }}复原工夫：{{ $alert.EndsAt.Format "2006-01-02 15:04:05" }}========== END =========={{- end }}{{- end }}{{- end }}启动
nohup ./alertmanager &
装置Grafana
wget https://dl.grafana.com/oss/re...
tar -zxvf grafana-8.4.6.linux-amd64.tar.gz
mv grafana-8.4.6.linux-amd64 grafana
配置未更改，走的默认，也能够依据具体情况做相应的配置改变
启动
nohup ./grafana &
配置数据源为Prometheus
因为在本地，所以首选localhost
保留并测试
导入配置
grafana dashboard地址
https://grafana.com/grafana/d...
11074 ------1 Node Exporter for Prometheus Dashboard EN 20201010
1860 -------Node Exporter Full
4701 -------JVM (Micrometer)
参考链接
https://blog.51cto.com/u_15060547/3817600https://www.cnblogs.com/Devinhao/articles/16180018.html本文由博客一文多发平台 OpenWrite 公布！