# 运行Prometheus容器
$ podman run -d –name fgedu-prometheus \
–cpus 2 \
–memory 4g \
-v /Podman/fgdata/prometheus/conf:/etc/prometheus:z \
-v /Podman/fgdata/prometheus/data:/prometheus:z \
-p 9090:9090 \
docker.io/prom/prometheus:v2.43.0

# 配置Prometheus
$ cat > /Podman/fgdata/prometheus/conf/prometheus.yml << EOF global: scrape_interval: 15s evaluation_interval: 15s rule_files: - "alerts.yml" scrape_configs: - job_name: "prometheus" static_configs: - targets: ["localhost:9090"] - job_name: "node" static_configs: - targets: ["192.168.1.10:9100"] - job_name: "cadvisor" static_configs: - targets: ["192.168.1.10:8080"] - job_name: "podman" static_configs: - targets: ["192.168.1.10:9101"] EOF # 配置告警规则 $ cat > /Podman/fgdata/prometheus/conf/alerts.yml << EOF groups: - name: container_alerts rules: - alert: ContainerHighCPU expr: (sum(rate(container_cpu_usage_seconds_total{name!=""}[5m])) by (name) / sum(container_spec_cpu_quota{name!=""} / container_spec_cpu_period{name!=""}) by (name)) * 100 > 80
for: 5m
labels:
severity: warning
annotations:
summary: “Container high CPU usage”
description: “Container {{ labels.name }} has CPU usage above 80% for 5 minutes”

– alert: ContainerHighMemory
expr: (sum(container_memory_usage_bytes{name!=””}) by (name) / sum(container_spec_memory_limit_bytes{name!=””}) by (name)) * 100 > 85
for: 5m
labels:
severity: warning
annotations:
summary: “Container high memory usage”
description: “Container {{ labels.name }} has memory usage above 85% for 5 minutes”

– alert: ContainerRestarted
expr: changes(container_start_time_seconds{name!=””}[1h]) > 3
labels:
severity: critical
annotations:
summary: “Container restarted”
description: “Container {{ labels.name }} has restarted more than 3 times in the last hour”
EOF

# 重启Prometheus
$ podman restart fgedu-prometheus

# 查看容器状态
$ podman ps

# 输出日志
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
7890123456ab docker.io/prom/prometheus /bin/prometheus 2 minutes ago Up 2 minutes ago 0.0.0.0:9090->9090/tcp fgedu-prometheus

# 运行Grafana容器
$ podman run -d –name fgedu-grafana \
–cpus 2 \
–memory 4g \
-v /Podman/fgdata/grafana/data:/var/lib/grafana:z \
-v /Podman/fgdata/grafana/conf:/etc/grafana:z \
-p 3000:3000 \
docker.io/grafana/grafana:9.5.0

# 配置Grafana
$ cat > /Podman/fgdata/grafana/conf/grafana.ini << EOF [server] http_port = 3000 domain = localhost [database] type = sqlite3 [security] admin_user = admin admin_password = admin [auth] login_maximum_inactive_lifetime_days = 30 [analytics] check_for_updates = true [log] mode = console level = info EOF # 重启Grafana $ podman restart fgedu-grafana # 查看容器状态 $ podman ps # 输出日志 CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES 1234567890ab docker.io/grafana/grafana grafana-server 2 minutes ago Up 2 minutes ago 0.0.0.0:3000->3000/tcp fgedu-grafana

# 运行Alertmanager容器
$ podman run -d –name fgedu-alertmanager \
–cpus 1 \
–memory 2g \
-v /Podman/fgdata/alertmanager/conf:/etc/alertmanager:z \
-p 9093:9093 \
docker.io/prom/alertmanager:v0.25.0

# 配置Alertmanager
$ cat > /Podman/fgdata/alertmanager/conf/alertmanager.yml << EOF global: resolve_timeout: 5m smtp_smarthost: 'smtp.example.com:587' smtp_from: 'alertmanager@example.com' smtp_auth_username: 'alertmanager' smtp_auth_password: 'password' route: group_by: ['alertname'] group_wait: 30s group_interval: 5m repeat_interval: 1h receiver: 'email' receivers: - name: 'email' email_configs: - to: 'admin@example.com' send_resolved: true - name: 'wechat' wechat_configs: - corp_id: 'your_corp_id' api_url: 'https://qyapi.weixin.qq.com/cgi-bin/' to_party: '1' agent_id: 'your_agent_id' api_secret: 'your_api_secret' send_resolved: true inhibit_rules: - source_match: severity: 'critical' target_match: severity: 'warning' equal: ['alertname', 'dev', 'instance'] EOF # 重启Alertmanager $ podman restart fgedu-alertmanager # 查看容器状态 $ podman ps # 输出日志 CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES 9876543210ab docker.io/prom/alertmanager /bin/alertmanager 2 minutes ago Up 2 minutes ago 0.0.0.0:9093->9093/tcp fgedu-alertmanager

# 更新Prometheus配置，添加Alertmanager
$ cat > /Podman/fgdata/prometheus/conf/prometheus.yml << EOF global: scrape_interval: 15s evaluation_interval: 15s rule_files: - "alerts.yml" alerting: alertmanagers: - static_configs: - targets: ['192.168.1.10:9093'] scrape_configs: - job_name: "prometheus" static_configs: - targets: ["localhost:9090"] - job_name: "node" static_configs: - targets: ["192.168.1.10:9100"] - job_name: "cadvisor" static_configs: - targets: ["192.168.1.10:8080"] - job_name: "podman" static_configs: - targets: ["192.168.1.10:9101"] EOF # 重启Prometheus $ podman restart fgedu-prometheus

# 运行Node Exporter容器
$ podman run -d –name fgedu-node-exporter \
–cpus 1 \
–memory 1g \
-v /proc:/host/proc:ro \
-v /sys:/host/sys:ro \
-v /:/rootfs:ro \
-p 9100:9100 \
docker.io/prom/node-exporter:v1.5.0 \
–path.procfs=/host/proc \
–path.rootfs=/rootfs \
–path.sysfs=/host/sys \
–collector.filesystem.mount-points-exclude=”^/(sys|proc|dev|host|etc)($|/)”

# 查看容器状态
$ podman ps

# 输出日志
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
7890123456ab docker.io/prom/node-exporter /bin/node_exporter 2 minutes ago Up 2 minutes ago 0.0.0.0:9100->9100/tcp fgedu-node-exporter

# 测试Node Exporter
$ curl http://localhost:9100/metrics

# 输出日志（部分）
# HELP node_cpu_seconds_total Seconds the CPUs spent in each mode.
# TYPE node_cpu_seconds_total counter
node_cpu_seconds_total{cpu=”0″,mode=”idle”} 12345.67
node_cpu_seconds_total{cpu=”0″,mode=”iowait”} 123.45
node_cpu_seconds_total{cpu=”0″,mode=”irq”} 0.0
node_cpu_seconds_total{cpu=”0″,mode=”nice”} 0.0
node_cpu_seconds_total{cpu=”0″,mode=”softirq”} 0.0
node_cpu_seconds_total{cpu=”0″,mode=”steal”} 0.0
node_cpu_seconds_total{cpu=”0″,mode=”system”} 123.45
node_cpu_seconds_total{cpu=”0″,mode=”user”} 1234.56