第三部分：Kubernetes 存储管理实战

docker run -v /data:/data nginx

docker inspect <container_id> | grep Mounts -A 10

# 随机读测试
fio --name=randread --filename=/data/test.file --bs=4k --iodepth=32 --rw=randread --numjobs=4 --time_based --runtime=60 --group_reporting

# 随机写测试
fio --name=randwrite --filename=/data/test.file --bs=4k --iodepth=32 --rw=randwrite --numjobs=4 --time_based --runtime=60 --group_reporting

# 混合读写测试
fio --name=mixed --filename=/data/test.file --bs=4k --iodepth=32 --rw=randrw --rwmixread=70 --numjobs=4 --time_based --runtime=60 --group_reporting

#!/bin/bash
# PVC Pending 排查脚本

PVC_NAME="my-pvc"
echo "=== PVC Pending 排查 ==="

# 1. 查看 PVC 状态
echo "1. 查看 PVC 状态："
kubectl get pvc $PVC_NAME -o yaml

# 2. 查看 PVC 事件
echo "2. 查看 PVC 事件："
kubectl describe pvc $PVC_NAME

# 3. 查看 StorageClass
echo "3. 查看 StorageClass："
kubectl get storageclass
kubectl describe storageclass

# 4. 查看可用 PV
echo "4. 查看可用 PV："
kubectl get pv

# 5. 检查 CSI 驱动状态
echo "5. 检查 CSI 驱动状态："
kubectl get pods -n kube-system | grep -E "(csi|storage)"

# 6. 查看 CSI 驱动日志
echo "6. 查看 CSI 驱动日志："
kubectl logs -n kube-system -l app=csi-driver --tail=50

# 7. 检查节点存储
echo "7. 检查节点存储："
kubectl get nodes -o jsonpath='{.items[0].status.addresses[0].address}' | xargs -I {} ssh {} "df -h"

# 8. 检查存储配额
echo "8. 检查存储配额："
kubectl describe quota --all-namespaces

#!/bin/bash
# Pod 挂载失败排查脚本

POD_NAME="my-pod"
echo "=== Pod 挂载失败排查 ==="

# 1. 查看 Pod 状态
echo "1. 查看 Pod 状态："
kubectl get pod $POD_NAME -o wide

# 2. 查看 Pod 事件
echo "2. 查看 Pod 事件："
kubectl describe pod $POD_NAME

# 3. 查看 Pod 日志
echo "3. 查看 Pod 日志："
kubectl logs $POD_NAME

# 4. 检查 PVC 状态
echo "4. 检查 PVC 状态："
kubectl get pvc
kubectl describe pvc

# 5. 检查 PV 状态
echo "5. 检查 PV 状态："
kubectl get pv
kubectl describe pv

# 6. 检查节点存储
echo "6. 检查节点存储："
NODE_NAME=$(kubectl get pod $POD_NAME -o jsonpath='{.spec.nodeName}')
kubectl get nodes -o jsonpath='{.items[0].status.addresses[0].address}' | xargs -I {} ssh {} "df -h"

# 7. 检查挂载点
echo "7. 检查挂载点："
kubectl get nodes -o jsonpath='{.items[0].status.addresses[0].address}' | xargs -I {} ssh {} "mount | grep -E '(nfs|ceph|local)'"

# 8. 检查 CSI 驱动日志
echo "8. 检查 CSI 驱动日志："
kubectl logs -n kube-system -l app=csi-driver --tail=100

#!/bin/bash
# 存储性能问题排查脚本

echo "=== 存储性能问题排查 ==="

# 1. 创建性能测试 Pod
kubectl apply -f - <<EOF
apiVersion: v1
kind: Pod
metadata:
  name: storage-test
spec:
  containers:
  - name: test
    image: nixery.dev/shell/fio
    command: ["sh", "-c"]
    args:
    - |
      echo "开始存储性能测试..."
      fio --name=randread \
          --filename=/data/test.file \
          --bs=4k \
          --iodepth=32 \
          --rw=randread \
          --numjobs=4 \
          --time_based \
          --runtime=30 \
          --group_reporting
    volumeMounts:
    - name: test-volume
      mountPath: /data
  volumes:
  - name: test-volume
    persistentVolumeClaim:
      claimName: test-pvc
EOF

# 2. 等待 Pod 就绪
kubectl wait --for=condition=Ready pod storage-test --timeout=60s

# 3. 运行性能测试
echo "3. 运行性能测试："
kubectl exec storage-test -- fio --name=randread --filename=/data/test.file --bs=4k --iodepth=32 --rw=randread --numjobs=4 --time_based --runtime=30 --group_reporting

# 4. 检查节点 I/O 状态
echo "4. 检查节点 I/O 状态："
kubectl get nodes -o jsonpath='{.items[0].status.addresses[0].address}' | xargs -I {} ssh {} "iostat -x 1 5"

# 5. 检查网络延迟（NFS）
echo "5. 检查网络延迟："
kubectl exec storage-test -- ping -c 10 nfs-server

# 6. 检查文件系统类型
echo "6. 检查文件系统类型："
kubectl exec storage-test -- df -T /data

# 7. 检查 I/O 调度器
echo "7. 检查 I/O 调度器："
kubectl get nodes -o jsonpath='{.items[0].status.addresses[0].address}' | xargs -I {} ssh {} "cat /sys/block/sda/queue/scheduler"

# 8. 清理测试 Pod
kubectl delete pod storage-test

#!/bin/bash
# Kubernetes 存储实验环境搭建脚本

set -e

echo "开始搭建 Kubernetes 存储实验环境..."

# 1. 创建实验集群
kind create cluster --name storage-test --config - <<EOF
kind: Cluster
apiVersion: kind.x-k8s.io/v1alpha4
nodes:
- role: control-plane
- role: worker
- role: worker
networking:
  podSubnet: "10.244.0.0/16"
  serviceSubnet: "10.96.0.0/12"
EOF

# 2. 等待集群就绪
kubectl wait --for=condition=Ready node --all --timeout=60s

# 3. 安装 NFS 服务器（用于测试）
kubectl apply -f - <<EOF
apiVersion: apps/v1
kind: Deployment
metadata:
  name: nfs-server
spec:
  replicas: 1
  selector:
    matchLabels:
      app: nfs-server
  template:
    metadata:
      labels:
        app: nfs-server
    spec:
      containers:
      - name: nfs-server
        image: k8s.gcr.io/volume-nfs:0.8
        ports:
        - containerPort: 2049
        volumeMounts:
        - name: nfs-data
          mountPath: /exports
      volumes:
      - name: nfs-data
        emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
  name: nfs-server
spec:
  selector:
    app: nfs-server
  ports:
  - port: 2049
    targetPort: 2049
EOF

# 4. 等待 NFS 服务器就绪
kubectl wait --for=condition=Ready pod -l app=nfs-server --timeout=60s

# 5. 创建 NFS PV
kubectl apply -f - <<EOF
apiVersion: v1
kind: PersistentVolume
metadata:
  name: nfs-pv
spec:
  capacity:
    storage: 10Gi
  accessModes:
    - ReadWriteMany
  persistentVolumeReclaimPolicy: Retain
  nfs:
    server: nfs-server
    path: /exports
EOF

# 6. 创建 NFS StorageClass
kubectl apply -f - <<EOF
apiVersion: storage.k8s.io/v1
kind: StorageClass
metadata:
  name: nfs-storage
provisioner: kubernetes.io/no-provisioner
volumeBindingMode: WaitForFirstConsumer
EOF

# 7. 安装测试工具
kubectl apply -f - <<EOF
apiVersion: apps/v1
kind: Deployment
metadata:
  name: storage-tools
spec:
  replicas: 1
  selector:
    matchLabels:
      app: storage-tools
  template:
    metadata:
      labels:
        app: storage-tools
    spec:
      containers:
      - name: tools
        image: nixery.dev/shell/fio
        command: ["sleep", "3600"]
EOF

echo "Kubernetes 存储实验环境搭建完成！"
echo "运行 'kubectl get pv' 查看 PV 状态"
echo "运行 'kubectl get pvc' 查看 PVC 状态"

# 创建测试用例
kubectl apply -f - <<EOF
# 测试用例1：基础 PVC 绑定
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: test-pvc-1
spec:
  accessModes:
    - ReadWriteOnce
  resources:
    requests:
      storage: 1Gi
  storageClassName: nfs-storage
---
# 测试用例2：多访问模式 PVC
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: test-pvc-2
spec:
  accessModes:
    - ReadWriteMany
  resources:
    requests:
      storage: 2Gi
  storageClassName: nfs-storage
---
# 测试用例3：大容量 PVC
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: test-pvc-3
spec:
  accessModes:
    - ReadWriteOnce
  resources:
    requests:
      storage: 5Gi
  storageClassName: nfs-storage
EOF