# 查看Pod状态
[root@k8s-master ~]# kubectl get pods -n fgedu-prod
NAME READY STATUS RESTARTS AGE
fgedu-app-abc12-xyz789 0/1 ImagePullBackOff 0 5m
fgedu-app-abc12-abc12 0/1 CrashLoopBackOff 5 10m

# 查看Pod详情
[root@k8s-master ~]# kubectl describe pod fgedu-app-abc12-xyz789 -n fgedu-prod
Events:
Type Reason Age From Message
—- —— —- —- ——-
Normal Pulling 5m (x4 over 5m) kubelet Pulling image “fgedu/app:v1.0”
Warning Failed 5m (x4 over 5m) kubelet Failed to pull image “fgedu/app:v1.0”: rpc error: code = Unknown
Warning Failed 5m (x4 over 5m) kubelet Error: ErrImagePull
Normal BackOff 5m (x6 over 5m) kubelet Back-off pulling image

# 解决方案：检查镜像名称和仓库访问
[root@k8s-master ~]# docker pull 192.168.1.100:30002/fgedu/app:v1.0
v1.0: Pulling from fgedu/app
Digest: sha256:abc123
Status: Downloaded newer image

# 查看CrashLoopBackOff原因
[root@k8s-master ~]# kubectl logs fgedu-app-abc12-abc12 -n fgedu-prod –previous
2026-04-04 23:30:00 ERROR Failed to connect to database: Connection refused
2026-04-04 23:30:00 ERROR Application startup failed

# 检查Service状态
[root@k8s-master ~]# kubectl get svc -n fgedu-prod
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
fgedu-web ClusterIP 10.96.100.100 80/TCP 10m

# 检查Endpoints
[root@k8s-master ~]# kubectl get endpoints fgedu-web -n fgedu-prod
NAME ENDPOINTS AGE
fgedu-web 10m

# 检查Pod标签
[root@k8s-master ~]# kubectl get pods -n fgedu-prod –show-labels
NAME READY STATUS LABELS
fgedu-app-abc12-xyz789 1/1 Running app=fgedu-app

# 修复Service选择器
[root@k8s-master ~]# kubectl patch svc fgedu-web -n fgedu-prod -p ‘{“spec”:{“selector”:{“app”:”fgedu-app”}}}’
service/fgedu-web patched

# 测试DNS解析
[root@k8s-master ~]# kubectl run dns-test –image=busybox –rm -it — nslookup fgedu-web.fgedu-prod
Server: 10.96.0.10
Address 1: 10.96.0.10 kube-dns.kube-system.svc.cluster.local

Name: fgedu-web.fgedu-prod
Address 1: 10.96.100.100学习交流加群风哥微信: itpux-com fgedu-web.fgedu-prod.svc.cluster.local

# 查看PVC状态
[root@k8s-master ~]# kubectl get pvc -n fgedu-prod
NAME STATUS VOLUME CAPACITY ACCESS MODES STORAGECLASS AGE
fgedu-data-pvc Pending fgedu-nfs-storage 5m

# 查看PVC详情
[root@k8s-master ~]# kubectl describe pvc fgedu-data-pvc -n fgedu-prod
Events:
Type Reason Age From Message
—- —— —- —- ——-
Normal WaitForFirstConsumer 5m persistentvolume-controller waiting for first consumer to be created before binding

# 检查StorageClass
[root@k8s-master ~]# kubectl get storageclass
NAME PROVISIONER AGE
fgedu-nfs-storage nfs.fgedu.net.cn 10m

# 检查Provisioner状态
[root@k8s-master ~]# kubectl get pods -n kube-system -l app=nfs-provisioner
NAME READY STATUS RESTARTS AGE
nfs-provisioner-abc12-xyz789 1/1 Running 0 10m

# 手动创建PV测试
[root@k8s-master ~]# cat > test-pv.yaml << 'EOF' apiVersion: v1 kind: PersistentVolume metadata: name: test-pv spec: capacity: storage: 10Gi accessModes: - ReadWriteMany nfs: server: 192.168.1.100 path: /data/k8s-storage EOF [root@k8s-master ~]# kubectl apply -f test-pv.yaml persistentvolume/test-pv created

# 查看节点状态
[root@k8s-master ~]# kubectl get nodes
NAME STATUS ROLES AGE VERSION
k8s-master Ready control-plane 10d v1.28.3
k8s-node1 NotReady 10d v1.28.3
k8s-node2 Ready 10d v1.28.3

# 查看节点详情
[root@k8s-master ~]# kubectl describe node k8s-node1
Conditions:
Type Status LastHeartbeatTime LastTransitionTime Reason Message
—- —— —————– —————— —— ——-
MemoryPressure False Sat, 04 Apr 2026 23:00:00 +0800 Sat, 04 Apr 2026 22:00:00 +0800 KubeletHasSufficientMemory kubelet has sufficient memory
DiskPressure False Sat, 04 Apr 2026 23:00:00 +0800 Sat, 04 Apr 2026 22:00:00 +0800 KubeletHasNoDiskPressure kubelet has no disk pressure
PIDPressure False Sat, 04 Apr 2026 23:00:00 +0800 Sat, 04 Apr 2026 22:00:00 +0800 KubeletHasSufficientPID kubelet has sufficient PID
Ready False Sat, 04 Apr 2026 23:00:00 +0800 Sat, 04 Apr 2026 22:30:00 +0800 KubeletNotReady container runtime not ready

# 登录节点检查kubelet
[root@k8s-node1 ~]# systemctl status kubelet
● kubelet.service – Kubernetes Kubelet Server
Active: inactive (dead)

[root@k8s-node1 ~]# systemctl restart kubelet
[root@k8s-node1 ~]# systemctl status kubelet
● kubelet.service – Kubernetes Kubelet Server
Active: active (running)

# 验证节点恢复
[root@k8s-master ~]# kubectl get nodes
NAME STATUS ROLES AGE VERSION
k8s-master Ready control-plane 10d v1.28.3
k8s-node1 Ready 10d v1.28.3
k8s-node2 Ready 10d v1.28.3