# 步骤1：准备监控服务器
$ hostnamectl set-hostname monitor.fgedu.net.cn
$ ip addr add 192.168.1.50/24 dev eth0
$ systemctl restart network

# 步骤2：安装Prometheus
$ cd /tidb/app
$ wget https://github.com/prometheus/prometheus/releases/download/v2.45.0/prometheus-2.45.0.linux-amd64.tar.gz
$ tar -xzf prometheus-2.45.0.linux-amd64.tar.gz
$ mv prometheus-2.45.0.linux-amd64 prometheus

# 步骤3：安装AlertManager
$ wget https://github.com/prometheus/alertmanager/releases/download/v0.25.0/alertmanager-0.25.0.linux-amd64.tar.gz
$ tar -xzf alertmanager-0.25.0.linux-amd64.tar.gz
$ mv alertmanager-0.25.0.linux-amd64 alertmanager

# 步骤4：安装Grafana
$ wget https://dl.grafana.com/oss/release/grafana-10.0.3.linux-amd64.tar.gz
$ tar -xzf grafana-10.0.3.linux-amd64.tar.gz
$ mv grafana-10.0.3 grafana

# 步骤5：安装Node Exporter
$ wget https://github.com/prometheus/node_exporter/releases/download/v1.6.0/node_exporter-1.6.0.linux-amd64.tar.gz
$ tar -xzf node_exporter-1.6.0.linux-amd64.tar.gz
$ mv node_exporter-1.6.0.linux-amd64/node_exporter /tidb/app/bin/

# 步骤6：配置系统服务
$ cat > /etc/systemd/system/prometheus.service << EOF [Unit] Description=Prometheus After=network.target [Service] Type=simple ExecStart=/tidb/app/prometheus/prometheus --config.file=/tidb/app/prometheus/prometheus.yml Restart=on-failure [Install] WantedBy=multi-user.target EOF $ cat > /etc/systemd/system/alertmanager.service << EOF [Unit] Description=AlertManager After=network.target [Service] Type=simple ExecStart=/tidb/app/alertmanager/alertmanager --config.file=/tidb/app/alertmanager/alertmanager.yml Restart=on-failure [Install] WantedBy=multi-user.target EOF $ cat > /etc/systemd/system/grafana-server.service << EOF [Unit] Description=Grafana Server After=network.target [Service] Type=simple ExecStart=/tidb/app/grafana/bin/grafana-server --homepath=/tidb/app/grafana Restart=on-failure [Install] WantedBy=multi-user.target EOF $ cat > /etc/systemd/system/node_exporter.service << EOF [Unit] Description=Node Exporter After=network.target [Service] Type=simple ExecStart=/tidb/app/bin/node_exporter Restart=on-failure [Install] WantedBy=multi-user.target EOF # 步骤7：启动服务 $ systemctl daemon-reload $ systemctl enable prometheus alertmanager grafana-server node_exporter $ systemctl start prometheus alertmanager grafana-server node_exporter # 步骤8：验证服务状态 $ systemctl status prometheus alertmanager grafana-server node_exporter # 输出示例 ● prometheus.service - Prometheus Loaded: loaded (/etc/systemd/system/prometheus.service; enabled; vendor preset: disabled) Active: active (running) since Wed 2026-04-09 10:00:00 CST; 5min ago Main PID: 12345 (prometheus) Tasks: 10 Memory: 256.0M CPU: 10% CGroup: /system.slice/prometheus.service └─12345 /tidb/app/prometheus/prometheus --config.file=/tidb/app/prometheus/prometheus.yml ● alertmanager.service - AlertManager Loaded: loaded (/etc/systemd/system/alertmanager.service; enabled; vendor preset: disabled) Active: active (running) since Wed 2026-04-09 10:00:00 CST; 5min ago Main PID: 12346 (alertmanager) Tasks: 5 Memory: 64.0M CPU: 2% CGroup: /system.slice/alertmanager.service └─12346 /tidb/app/alertmanager/alertmanager --config.file=/tidb/app/alertmanager/alertmanager.yml ● grafana-server.service - Grafana Server Loaded: loaded (/etc/systemd/system/grafana-server.service; enabled; vendor preset: disabled) Active: active (running) since Wed 2026-04-09 10:00:00 CST; 5min ago Main PID: 12347 (grafana-server) Tasks: 15 Memory: 128.0M CPU: 5% CGroup: /system.slice/grafana-server.service └─12347 /tidb/app/grafana/bin/grafana-server --homepath=/tidb/app/grafana ● node_exporter.service - Node Exporter Loaded: loaded (/etc/systemd/system/node_exporter.service; enabled; vendor preset: disabled) Active: active (running) since Wed 2026-04-09 10:00:00 CST; 5min ago Main PID: 12348 (node_exporter) Tasks: 3 Memory: 16.0M CPU: 1% CGroup: /system.slice/node_exporter.service └─12348 /tidb/app/bin/node_exporter

# 访问Grafana
http://192.168.1.50:3000

# 查看TiDB Overview面板
– 集群状态：健康
– QPS：1000
– 延迟：1ms
– 错误率：0%

# 查看TiKV面板
– 存储使用：500GB/1TB
– 读写延迟：0.5ms/1ms
– 并发请求：1000

# 查看PD面板
– 集群状态：健康
– 调度：正常
– 存储容量：1TB

# 访问TiDB Dashboard
http://192.168.1.10:2379/dashboard

# 查看集群拓扑
– TiDB节点：2个
– TiKV节点：3个
– PD节点：3个
– TiFlash节点：2个

# 分析慢SQL
1. 点击”SQL分析” -> “慢查询历史”
2. 查看慢SQL列表
3. 分析执行计划
4. 优化SQL语句

# 生成诊断报告
1. 点击”诊断报告” -> “生成报告”
2. 等待报告生成
3. 查看报告内容
4. 按照建议进行优化

# 步骤1：配置AlertManager
$ cat > /tidb/app/alertmanager/alertmanager.yml << EOF global: resolve_timeout: 5m smtp_smarthost: 'smtp.example.com:587' smtp_from: 'alertmanager@fgedu.net.cn' smtp_auth_username: 'alertmanager' smtp_auth_password: 'password' route: group_by: ['alertname', 'cluster', 'service'] group_wait: 30s group_interval: 5m repeat_interval: 1h receiver: 'email' routes: - match: severity: critical receiver: 'email' receivers: - name: 'email' email_configs: - to: 'admin@fgedu.net.cn' send_resolved: true EOF # 步骤2：配置TiDB告警规则 $ mkdir -p /tidb/app/prometheus/alerts $ cat > /tidb/app/prometheus/alerts/tidb.yml << EOF groups: - name: tidb rules: - alert: TiDBDown expr: up{job="tidb"} == 0 for: 5m labels: severity: critical annotations: summary: "TiDB down" description: "TiDB instance {{ labels.instance }} is down" - alert: TiDBHighQPS expr: sum(rate(tidb_server_qps[5m])) by (instance) > 10000
for: 5m
labels:
severity: warning
annotations:
summary: “TiDB high QPS”
description: “TiDB instance {{ labels.instance }} has high QPS: {{ value }}”

– alert: TiDBHighErrorRate
expr: sum(rate(tidb_server_errors_total[5m])) by (instance) / sum(rate(tidb_server_qps[5m])) by (instance) > 0.01
for: 5m
labels:
severity: warning
annotations:
summary: “TiDB high error rate”
description: “TiDB instance {{ labels.instance }} has high error rate: {{ value }}”
EOF

# 步骤3：重新加载Prometheus配置
$ curl -X POST http://localhost:9090/-/reload

# 步骤4：测试告警
$ curl -X POST http://localhost:9093/api/v1/alerts -d ‘[{
“labels”: {
“alertname”: “TestAlert”,
“severity”: “critical”,
“instance”: “test.fgedu.net.cn”
},
“annotations”: {
“summary”: “Test alert”,
“description”: “This is a test alert”
}
}]’

# 步骤5：查看告警状态
$ curl http://localhost:9093/api/v1/alerts

# 输出示例
{
“status”: “success”,
“data”: {
“alerts”: [
{
“status”: “firing”,
“labels”: {
“alertname”: “TestAlert”,
“instance”: “test.fgedu.net.cn”,
“severity”: “critical”
},
“annotations”: {
“description”: “This is a test alert”,
“summary”: “Test alert”
},
“startsAt”: “2026-04-09T02:00:00Z”,
“endsAt”: null,
“generatorURL”: “”
}
]
}
}