# 启动Rancher容器
[root@fgedu ~]# docker run -d –restart=unless-stopped \
–name rancher \
-p 80:80 -p 443:443 \
-v /Rancher/fgdata/rancher:/var/lib/rancher \
-v /Rancher/fgdata/rancher/log:/var/log/rancher \
-e CATTLE_SYSTEM_DEFAULT_REGISTRY=registry.cn-hangzhou.aliyuncs.com \
-e CATTLE_SYSTEM_CATALOG=bundled \
–privileged \
rancher/rancher:v2.8.5

1234567890abcdef1234567890abcdef1234567890abcdef1234567890abcdef

# 查看Rancher容器状态
[root@fgedu ~]# docker ps -a | grep rancher
1234567890ab rancher/rancher:v2.8.5 “entrypoint.sh” 10 seconds ago Up 9 seconds 0.0.0.0:80->80/tcp, 0.0.0.0:443->443/tcp rancher

# 查看Rancher容器日志
[root@fgedu ~]# docker logs -f rancher
INFO: Starting Rancher
INFO: Rancher is starting
INFO: Waiting for Rancher to be ready…
INFO: Rancher is ready
INFO: Rancher is running

# 访问Rancher Web界面
# 打开浏览器访问：https://192.168.1.100
# 使用初始密码登录后，需要修改密码

# 查看Rancher容器资源使用情况
[root@fgedu ~]# docker stats rancher –no-stream
CONTAINER ID NAME CPU % MEM USAGE / LIMIT MEM % NET I/O BLOCK I/O PIDS
1234567890ab rancher 5.23% 1.2GiB / 15.6GiB 7.69% 12.3MB / 8.9MB 45.6MB / 23.4MB 156

# 查看Rancher容器详细信息
[root@fgedu ~]# docker inspect rancher | grep -A 20 “Mounts”
“Mounts”: [
{
“Type”: “bind”,
“Source”: “/Rancher/fgdata/rancher”,
“Destination”: “/var/lib/rancher”,
“Mode”: “”,
“RW”: true,
“Propagation”: “rprivate”
},
{
“Type”: “bind”,
“Source”: “/Rancher/fgdata/rancher/log”,
“Destination”: “/var/log/rancher”,
“Mode”: “”,
“RW”: true,
“Propagation”: “rprivate”
}
],

# 通过API创建用户
[root@fgedu ~]# curl -k -u “admin:admin-password-1234567890” \
-X POST \
-H “Content-Type: application/json” \
-d ‘{
“username”: “fgedu”,
“password”: “Fgedu@123456”,
“description”: “Rancher数据库管理员”
}’ \
https://192.168.1.100/v3/users

{
“id”: “user-1234567890”,
“type”: “user”,
“links”: {
“self”: “https://192.168.1.100/v3/users/user-1234567890”
},
“username”: “fgedu”,
“description”: “Rancher数据库管理员”,
“created”: “2026-04-10T10:00:00Z”,
“createdBy”: “admin”
}

# 查看用户列表
[root@fgedu ~]# curl -k -u “admin:admin-password-1234567890” \
https://192.168.1.100/v3/users

{
“data”: [
{
“id”: “user-admin”,
“type”: “user”,
“username”: “admin”,
“description”: “System Administrator”
},
{
“id”: “user-1234567890”,
“type”: “user”,
“username”: “fgedu”,
“description”: “Rancher数据库管理员”
}
],
“pagination”: {
“limit”: 100,
“offset”: 0,
“total”: 2
}
}

# 通过API创建角色
[root@fgedu ~]# curl -k -u “admin:admin-password-1234567890” \
-X POST \
-H “Content-Type: application/json” \
-d ‘{
“name”: “fgedu-admin”,
“description”: “Rancher数据库管理员角色”,
“rules”: [
{
“apiGroups”: [“*”],
“resources”: [“*”],
“verbs”: [“*”]
}
]
}’ \
https://192.168.1.100/v3/globalroles

{
“id”: “globalrole-1234567890”,
“type”: “globalRole”,
“links”: {
“self”: “https://192.168.1.100/v3/globalroles/globalrole-1234567890”
},
“name”: “fgedu-admin”,
“description”: “Rancher数据库管理员角色”,
“rules”: [
{
“apiGroups”: [“*”],
“resources”: [“*”],
“verbs”: [“*”]
}
]
}

# 为用户分配角色
[root@fgedu ~]# curl -k -u “admin:admin-password-1234567890” \
-X POST \
-H “Content-Type: application/json” \
-d ‘{
“globalRoleId”: “globalrole-1234567890”,
“userId”: “user-1234567890”
}’ \
https://192.168.1.100/v3/globalrolebindings

{
“id”: “globalrolebinding-1234567890”,
“type”: “globalRoleBinding”,
“links”: {
“self”: “https://192.168.1.100/v3/globalrolebindings/globalrolebinding-1234567890”
},
“globalRoleId”: “globalrole-1234567890”,
“userId”: “user-1234567890”
}

# 通过CLI启用监控
[root@fgedu ~]# kubectl create namespace cattle-monitoring-system
namespace/cattle-monitoring-system created

[root@fgedu ~]# helm repo add rancher-monitoring https://charts.rancher.io
“rancher-monitoring” has been added to your repositories

[root@fgedu ~]# helm repo update
Hang tight while we grab the latest from your chart repositories…
…Successfully got an update from the “rancher-monitoring” chart repository
Update Complete. ⎈Happy Helming!⎈

[root@fgedu ~]# helm install rancher-monitoring rancher-monitoring/rancher-monitoring \
–namespace cattle-monitoring-system \
–set prometheus.prometheusSpec.retention=15d \
–set prometheus.prometheusSpec.storageSpec.volumeClaimTemplate.spec.storageClassName=local-path \
–set prometheus.prometheusSpec.storageSpec.volumeClaimTemplate.spec.resources.requests.storage=50Gi \
–set grafana.persistence.enabled=true \
–set grafana.persistence.size=10Gi \
–set grafana.persistence.storageClassName=local-path

NAME: rancher-monitoring
LAST DEPLOYED: Fri Apr 10 10:00:00 2026
NAMESPACE: cattle-monitoring-system
STATUS: deployed
REVISION: 1
TEST SUITE: None
NOTES:
The Rancher Monitoring Stack has been installed successfully!

Access Grafana:
kubectl -n cattle-monitoring-system port-forward svc/rancher-monitoring-grafana 3000:80

Access Prometheus:
kubectl -n cattle-monitoring-system port-forward svc/rancher-monitoring-prometheus 9090:9090

# 查看监控组件状态
[root@fgedu ~]# kubectl get pods -n cattle-monitoring-system
NAME READY STATUS RESTARTS AGE
rancher-monitoring-operator-1234567890-abcde 1/1 Running 0 2m
rancher-monitoring-prometheus-0 2/2 Running 0 2m
rancher-monitoring-grafana-1234567890-abcde 1/1 Running 0 2m
rancher-monitoring-alertmanager-0 1/1 Running 0 2m
rancher-monitoring-kube-state-metrics-12345678 1/1 Running 0 2m
rancher-monitoring-node-exporter-12345678 1/1 Running 0 2m

– alert: ClusterMemoryUsageHigh
expr: sum(container_memory_working_set_bytes{image!=””}) by (node) / sum(kube_node_status_capacity{resource=”memory”}) by (node) > 0.8
for: 10m
labels:
severity: warning
annotations:
summary: “High memory usage on node {{ $labels.node }}”
description: “Memory usage on node {{ $labels.node }} is above 80% for more than 10 minutes.”

– alert: ClusterDiskUsageHigh
expr: sum(kubelet_volume_stats_used_bytes) by (node) / sum(kubelet_volume_stats_capacity_bytes) by (node) > 0.8
for: 10m
labels:
severity: warning
annotations:
summary: “High disk usage on node {{ $labels.node }}”
description: “Disk usage on node {{ $labels.node }} is above 80% for more than 10 minutes.”
EOF

# 应用告警规则
[root@fgedu ~]# kubectl apply -f /tmp/fgedu-alert-rules.yaml
prometheusrule.monitoring.coreos.com/fgedu-alert-rules created

# 查看告警规则
[root@fgedu ~]# kubectl get prometheusrules -n cattle-monitoring-system
NAME AGE
fgedu-alert-rules 1m
rancher-monitoring 10m

# 查看告警规则详情
[root@fgedu ~]# kubectl get prometheusrules fgedu-alert-rules -n cattle-monitoring-system -o yaml
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
annotations:
kubectl.kubernetes.io/last-applied-configuration: |
{“apiVersion”:”monitoring.coreos.com/v1″,”kind”:”PrometheusRule”,”metadata”:{“annotations”:{},”labels”:{“release”:”rancher-monitoring”},”name”:”fgedu-alert-rules”,”namespace”:”cattle-monitoring-system”},”spec”:{“groups”:[{“name”:”fgedu-cluster-alerts”,”rules”:[{“alert”:”ClusterPodNotReady”,”annotations”:{“description”:”Pod {{ $labels.pod }} in namespace {{ $labels.namespace }} has been not ready for more than 5 minutes.”,”summary”:”Pod {{ $labels.pod }} is not ready”},”expr”:”kube_pod_status_ready{condition=\”true\”} == 0″,”for”:”5m”,”labels”:{“severity”:”warning”}},{“alert”:”ClusterNodeNotReady”,”annotations”:{“description”:”Node {{ $labels.node }} has been not ready for more than 5 minutes.”,”summary”:”Node {{ $labels.node }} is not ready”},”expr”:”kube_node_status_ready{condition=\”true\”} == 0″,”for”:”5m”,”labels”:{“severity”:”critical”}},{“alert”:”ClusterCPUUsageHigh”,”annotations”:{“description”:”CPU usage on node {{ $labels.node }} is above 80% for more than 10 minutes.”,”summary”:”High CPU usage on node {{ $labels.node }}”},”expr”:”sum(rate(container_cpu_usage_seconds_total{image!=\”\”}[5m])) by (node) / sum(kube_node_status_capacity{resource=\”cpu\”}) by (node) > 0.8″,”for”:”10m”,”labels”:{“severity”:”warning”}},{“alert”:”ClusterMemoryUsageHigh”,”annotations”:{“description”:”Memory usage on node {{ $labels.node }} is above 80% for more than 10 minutes.”,”summary”:”High memory usage on node {{ $labels.node }}”},”expr”:”sum(container_memory_working_set_bytes{image!=\”\”}) by (node) / sum(kube_node_status_capacity{resource=\”memory\”}) by (node) > 0.8″,”for”:”10m”,”labels”:{“severity”:”warning”}},{“alert”:”ClusterDiskUsageHigh”,”annotations”:{“description”:”Disk usage on node {{ $labels.node }} is above 80% for more than 10 minutes.”,”summary”:”High disk usage on node {{ $labels.node }}”},”expr”:”sum(kubelet_volume_stats_used_bytes) by (node) / sum(kubelet_volume_stats_capacity_bytes) by (node) > 0.8″,”for”:”10m”,”labels”:{“severity”:”warning”}}]}]}}
creationTimestamp: “2026-04-10T10:00:00Z”
generation: 1
labels:
release: rancher-monitoring
name: fgedu-alert-rules
namespace: cattle-monitoring-system
resourceVersion: “12345678”
uid: abcdef12-3456-7890-abcd-ef1234567890
spec:
groups:
– name: fgedu-cluster-alerts
rules:
– alert: ClusterPodNotReady
annotations:
description: Pod {{ $labels.pod }} in namespace {{ $labels.namespace }} has
been not ready for more than 5 minutes.
summary: Pod {{ $labels.pod }} is not ready
expr: kube_pod_status_ready{condition=”true”} == 0
for: 5m
labels:
severity: warning
– alert: ClusterNodeNotReady
annotations:
description: Node {{ $labels.node }} has been not ready for more than 5
minutes.
summary: Node {{ $labels.node }} is not ready
expr: kube_node_status_ready{condition=”true”} == 0
for: 5m
labels:
severity: critical
– alert: ClusterCPUUsageHigh
annotations:
description: CPU usage on node {{ $labels.node }} is above 80% for more
than 10 minutes.
summary: High CPU usage on node {{ $labels.node }}
expr: sum(rate(container_cpu_usage_seconds_total{image!=””}[5m])) by (node)
/ sum(kube_node_status_capacity{resource=”cpu”}) by (node) > 0.8
for: 10m
labels:
severity: warning
– alert: ClusterMemoryUsageHigh
annotations:
description: Memory usage on node {{ $labels.node }} is above 80% for more
than 10 minutes.
summary: High memory usage on node {{ $labels.node }}
expr: sum(container_memory_working_set_bytes{image!=””}) by (node) /
sum(kube_node_status_capacity{resource=”memory”}) by (node) > 0.8
for: 10m
labels:
severity: warning
– alert: ClusterDiskUsageHigh
annotations:
description: Disk usage on node {{ $labels.node }} is above 80% for more
than 10 minutes.
summary: High disk usage on node {{ $labels.node }}
expr: sum(kubelet_volume_stats_used_bytes) by (node) / sum(kubelet_volume_stats_capacity_bytes)
by (node) > 0.8
for: 10m
labels:
severity: warning