建网站 多少钱,wordpress加cdn,wordpress怎么做后端,品牌网站设计公司场景说明#xff1a; 因为业务服务器已经完成了三级等保#xff0c;禁止在业务服务器上部署任何应用#xff0c;遂选择一台新的服务器部署prometheus#xff0c;采用blackbox_exporter监控业务服务器的端口与域名状态。
Tensuns项目介绍
https://github.com/starsliao/T…场景说明 因为业务服务器已经完成了三级等保禁止在业务服务器上部署任何应用遂选择一台新的服务器部署prometheus采用blackbox_exporter监控业务服务器的端口与域名状态。
Tensuns项目介绍
https://github.com/starsliao/TenSunS 后羿 - TenSunS(原ConsulManager)是一个使用FlaskVue开发基于Consul的WEB运维平台弥补了Consul官方UI对Services管理的不足并且基于Consul的服务发现与键值存储实现了Prometheus自动发现多云厂商各资源信息基于Blackbox对站点监控的可视化维护以及对自建与云上资源的优雅管理与展示。
安装Tensuns 选择使用docker-compose安装 vim install_Tensuns.sh #!/bin/bash
export PATH$PATH:/sbin:/bin:/usr/sbin:/usr/bin:/usr/local/sbin:/usr/local/bin
tsspath/opt/tensuns
uuiduuidgen
adminpwduuidgen|awk -F- {print $1}
mkdir -p $tsspath/consul/config
cat EOF $tsspath/consul/config/consul.hcl
log_level error
data_dir /consul/data
client_addr 0.0.0.0
ui_config{enabled true
}
ports {grpc -1https -1dns -1grpc_tls -1serf_wan -1
}
peering {enabled false
}
connect {enabled false
}
server true
bootstrap_expect1
acl {enabled truedefault_policy denyenable_token_persistence truetokens {initial_management $uuidagent $uuid}
}
EOF
chmod 777 -R $tsspath/consul/config
cat EOF $tsspath/docker-compose.yaml
version: 3.6
services:consul:image: swr.cn-south-1.myhuaweicloud.com/starsl.cn/consul:latestcontainer_name: consulhostname: consulrestart: alwaysports:- 8500:8500volumes:- $tsspath/consul/data:/consul/data- $tsspath/consul/config:/consul/config- /usr/share/zoneinfo/PRC:/etc/localtimecommand: agentnetworks:- TenSunSflask-consul:image: swr.cn-south-1.myhuaweicloud.com/starsl.cn/flask-consul:latestcontainer_name: flask-consulhostname: flask-consulrestart: alwaysvolumes:- /usr/share/zoneinfo/PRC:/etc/localtimeenvironment:consul_token: $uuidconsul_url: http://consul:8500/v1admin_passwd: $adminpwdlog_level: INFOdepends_on:- consulnetworks:- TenSunSnginx-consul:image: swr.cn-south-1.myhuaweicloud.com/starsl.cn/nginx-consul:latestcontainer_name: nginx-consulhostname: nginx-consulrestart: alwaysports:- 1026:1026volumes:- /usr/share/zoneinfo/PRC:/etc/localtimedepends_on:- flask-consulnetworks:- TenSunSnetworks:TenSunS:name: TenSunSdriver: bridgeipam:driver: default
EOFecho -e \n\033[31;1m正在启动后羿运维平台...\033[0m
cd $tsspath docker-compose up -d
echo -e \n后羿运维平台默认的admin密码是\033[31;1m$adminpwd\033[0m\n修改密码请编辑 $tsspath/docker-compose.yaml 查找并修改变量 admin_passwd 的值\n
echo -e 请使用浏览器访问 http://{你的IP}:1026 并登录使用\n
echo -e \033[31;1mhttp://ip route get 1.2.3.4 | awk {print $NF}|head -1:1026\033[0m\n bash install_Tensuns.sh #执行脚本前先安装docker与docker-compose安装后使用IP:1026登录 安装Alertmanager 安装包下载Download | Prometheus alertmanager-0.26.0.linux-amd64 设置启动脚本 vim /etc/systemd/system/alertmanager.service [Unit]
DescriptionAlertmanager
Wantsnetwork-online.target
Afternetwork-online.target[Service]
Typesimple
ExecStart/opt/alertmanager-0.26.0.linux-amd64/alertmanager \--config.file/opt/alertmanager-0.26.0.linux-amd64/alertmanager.yml \--storage.path/opt/alertmanager-0.26.0.linux-amd64/data
# --web.listen-address:9081
#修改启动端口为9081
ExecReload/bin/kill -HUP $MAINPID
Restartalways[Install]
WantedBymulti-user.target systemctl daemon-reload systemctl start alertmanager systemctl enable alertmanager systemctl status alertmanager Alertmanager配置文件修改 vim alertmanager.yml global:resolve_timeout: 5m smtp_smarthost: smtp.qq.com:465smtp_from: ******qq.comsmtp_auth_username: ******qq.com
#SMTP授权码smtp_auth_password: kxtokczppbtabfbismtp_require_tls: false#邮件模板
templates:- /opt/alertmanager-0.26.0.linux-amd64/alertsend.tmpl
route:group_by: [alertname]group_wait: 30sgroup_interval: 2mrepeat_interval: 10mreceiver: email receivers:
- name: emailemail_configs:- to: *****qq.com html: {{ template email.to.html . }}send_resolved: true inhibit_rules: - source_match:severity: criticaltarget_match:severity: warning
#触发severity为critical的告警时抑制[ name, env,project]都相等的warning告警equal: [ name, env,project] 配置邮件模板 vim /opt/alertmanager-0.26.0.linux-amd64/alertsend.tmpl {{ define email.to.html }}
{{ range .Alerts }}
告警程序: 域名IP端口检查告警 br
告警级别: {{ .Labels.severity }} 级 br
告警类型: {{ .Labels.alertname }} br
故障主机: {{ .Labels.instance }} br
故障项目: {{ .Labels.project }} br
故障环境: {{ .Labels.env }} br
告警详情: {{ .Annotations.description }} br
{{ end }}Prometheus配置修改 vim /opt/prometheus-2.46.0.linux-amd64/prometheus.yml 注意token: 0eed6b85-6c5a-40a9-b02d-4de1eeea8319的值与Tensuns上的一致。 # my global config
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:- 127.0.0.1:9093# Load rules once and periodically evaluate them according to the global evaluation_interval.
rule_files:- rules.yml# - second_rules.yml# A scrape configuration containing exactly one endpoint to scrape:
# Here its Prometheus itself.
scrape_configs:# The job name is added as a label jobjob_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: blackbox_exporterscrape_interval: 15sscrape_timeout: 5smetrics_path: /probeconsul_sd_configs:
# - server: consul:8500- server: 127.0.0.1:8500token: 0eed6b85-6c5a-40a9-b02d-4de1eeea8319services: [blackbox_exporter]relabel_configs:- source_labels: [__meta_consul_service_metadata_instance]target_label: __param_target- source_labels: [__meta_consul_service_metadata_module]target_label: __param_module- source_labels: [__meta_consul_service_metadata_module]target_label: module- source_labels: [__meta_consul_service_metadata_company]target_label: company- source_labels: [__meta_consul_service_metadata_env]target_label: env- source_labels: [__meta_consul_service_metadata_name]target_label: name- source_labels: [__meta_consul_service_metadata_project]target_label: project- source_labels: [__param_target]target_label: instance- target_label: __address__replacement: 127.0.0.1:9115添加告警规则rules.yml vim /opt/prometheus-2.46.0.linux-amd64/rules.yml groups:- name: Domainrules:- alert: 站点可用性expr: probe_success{jobblackbox_exporter} 0for: 1mlabels:alertype: domainseverity: criticalannotations: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{jobblackbox_exporter}[1h])/count_over_time(probe_success{jobblackbox_exporter}[1h]) * 100 80for: 3mlabels:alertype: domainseverity: warningannotations: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{jobblackbox_exporter} 0 and probe_http_status_code 499) or probe_http_status_code 0for: 1mlabels:alertype: domainseverity: warningannotations: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 0.5for: 2mlabels:alertype: domainseverity: warningannotations: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 15for: 2mlabels:alertype: domainseverity: warningannotations:description: {{ $labels.env }}_{{ $labels.name }}({{ $labels.project }})证书有效期剩余{{ $value | humanize }}天\n {{ $labels.instance }} Tensuns结果验证
登录Tensun添加需要被监控资源列表 登录Grafana配置数据源与dashboard dashboard选择ID9965
alertmanager查看被触发的告警信息 登录邮箱查看告警邮件
