# 创建用户和目录
# useradd -r -s /bin/false prometheus
# mkdir -p /fgeudb/prometheus/data /fgeudb/prometheus/config

# 复制文件
# cp prometheus promtool /usr/local/bin/
# cp -r consoles console_libraries /etc/prometheus/
# cp prometheus.yml /fgeudb/prometheus/config/

# 设置权限
# chown -R prometheus:prometheus /fgeudb/prometheus

# 创建systemd服务
# cat > /etc/systemd/system/prometheus.service << EOF [Unit] Description=Prometheus Server After=network.target [Service] User=prometheus Group=prometheus Type=simple ExecStart=/usr/local/bin/prometheus \ --config.file=/fgeudb/prometheus/config/prometheus.yml \ --storage.tsdb.path=/fgeudb/prometheus/data \ --storage.tsdb.retention.time=30d \ --web.listen-address=0.0.0.0:9090 \ --web.enable-admin-api [Install] WantedBy=multi-user.target EOF # 启动服务 # systemctl daemon-reload # systemctl start prometheus # systemctl enable prometheus # 输出示例如下： Created symlink /etc/systemd/system/multi-user.target.wants/prometheus.service → /etc/systemd/system/prometheus.service. # 查看服务状态 # systemctl status prometheus # 输出示例如下： ● prometheus.service - Prometheus Server Loaded: loaded (/etc/systemd/system/prometheus.service; enabled) Active: active (running) since Fri 2026-04-04 10:30:00 CST; 5s ago Main PID: 12345 (prometheus) Tasks: 8 (limit: 4915) Memory: 150.0M CGroup: /system.slice/prometheus.service └─12345 /usr/local/bin/prometheus --config.file=/fgeudb/prometheus/config/prometheus.yml

# 完整配置示例
global:
scrape_interval: 15s
evaluation_interval: 15s
external_labels:
monitor: ‘fgedu-monitor’

alerting:
alertmanagers:
– static_configs:
– targets:
– 192.168.1.51:9093

rule_files:
– /fgeudb/prometheus/rules/*.yml

scrape_configs:
– job_name: ‘prometheus’
static_configs:
– targets: [‘localhost:9090’]
labels:
instance: ‘prometheus-fgedu’

– job_name: ‘node-exporter’
static_configs:
– targets:
– ‘192.168.1.51:9100’
– ‘192.168.1.52:9100’
– ‘192.168.1.53:9100’
labels:
env: ‘production’

– job_name: ‘mysql’
static_configs:
– targets: [‘192.168.1.51:9104’]
labels:
instance: ‘mysql-master’

– job_name: ‘nginx’
static_configs:
– targets: [‘192.168.1.51:9113’]

# 验证配置文件
$ promtool check config /fgeudb/prometheus/config/prometheus.yml

# 输出示例如下：
Checking /fgeudb/prometheus/config/prometheus.yml
SUCCESS: 0 potential warnings or errors found.

告警规则配置

# 创建告警规则文件
$ cat > /fgeudb/prometheus/rules/alerts.yml << EOF groups: - name: node_alerts rules: - alert: NodeDown expr: up == 0 for: 1m labels: severity: critical annotations: summary: "Node {{ \$labels.instance }} is down" description: "Node {{ \$labels.instance }} has been down for more than 1 minute." - alert: HighCPU expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
for: 5m
labels:
severity: warning
annotations:
summary: “High CPU usage on {{ \$labels.instance }}”
description: “CPU usage is above 80% for more than 5 minutes.”

– alert: HighMemory
expr: (1 – (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 85
for: 5m
labels:
severity: warning
annotations:
summary: “High memory usage on {{ \$labels.instance }}”
description: “Memory usage is above 85% for more than 5 minutes.”

– alert: DiskSpaceLow
expr: (node_filesystem_avail_bytes{fstype!=”tmpfs”} / node_filesystem_size_bytes{fstype!=”tmpfs”}) * 100 < 10 for: 5m labels: severity: critical annotations: summary: "Low disk space on {{ \$labels.instance }}" description: "Disk {{ \$labels.mountpoint }} has less than 10% space remaining." EOF # 验证告警规则 $ promtool check rules /fgeudb/prometheus/rules/alerts.yml # 输出示例如下： Checking /fgeudb/prometheus/rules/alerts.yml SUCCESS: 4 rules found.

# 配置存储大小限制
–storage.tsdb.retention.size=50GB

# 查看存储状态
$ curl http://localhost:9090/api/v1/status/tsdb

# 输出示例如下：
{
“status”: “success”,
“data”: {
“headStats”: {
“numSeries”: 12345,
“numLabelValues”: 67890,
“chunkCount”: 123456,
“minTime”: 1712214400000,
“maxTime”: 1712300800000,
“numChunks”: 123456,
“numSamples”: 1234567
},
“seriesCountByMetricName”: [
{
“name”: “node_cpu_seconds_total”,
“value”: 1000
}
]
}
}

高可用配置

# 实例2配置
–web.listen-address=0.0.0.0:9091
–storage.tsdb.path=/fgeudb/prometheus/data2

# 使用Thanos实现长期存储和高可用
$ docker run -d –name thanos-sidecar \
-v /fgeudb/prometheus/data:/prometheus \
thanosio/thanos:v0.35.0 \
sidecar \
–tsdb.path=/prometheus \
–prometheus.url=http://localhost:9090 \
–objstore.config-file=/etc/thanos/bucket.yml