# 1. 存储架构升级
## 1.1 部署Ceph存储集群
mkdir -p /Kubernetes/app/ceph
cd /Kubernetes/app/ceph
ceph-deploy new fgedu-ceph-01 fgedu-ceph-02 fgedu-ceph-03
cat >> ceph.conf << EOF osd pool default size = 3 osd pool default min size = 2 osd pool default pg num = 128 osd pool default pgp num = 128 EOF ceph-deploy install fgedu-ceph-01 fgedu-ceph-02 fgedu-ceph-03 ceph-deploy mon create-initial ceph-deploy osd create fgedu-ceph-01:/dev/sdb fgedu-ceph-02:/dev/sdb fgedu-ceph-03:/dev/sdb ceph-deploy admin fgedu-ceph-01 fgedu-ceph-02 fgedu-ceph-03 chmod +r /etc/ceph/ceph.client.admin.keyring ## 1.2 配置Ceph存储类 cat > storageclass-ceph.yaml << EOF apiVersion: storage.k8s.io/v1 kind: StorageClass metadata: name: ceph-rbd defaultClass: true，更多视频教程www.fgedu.net.cn。 provisioner: kubernetes.io/rbd parameters: monitors: 192.168.1.101:6789,192.168.1.102:6789,192.168.1.103:6789 adminId: admin adminSecretName: ceph-secret adminSecretNamespace: kube-system pool: rbd userId: kubernetes userSecretName: ceph-user-secret userSecretNamespace: kube-system imageFormat: "2" imageFeatures: layering reclaimPolicy: Retain allowVolumeExpansion: true volumeBindingMode: WaitForFirstConsumer EOF kubectl apply -f storageclass-ceph.yaml # 2. 存储性能优化 ## 2.1 优化内核参数 cat > /etc/sysctl.d/kubernetes-storage.conf << EOF # 存储优化 vm.dirty_background_ratio = 5 vm.dirty_ratio = 10 vm.swappiness = 0 vm.overcommit_memory = 1 # 提高文件系统性能 fs.file-max = 655360 fs.nr_open = 655360 EOF sysctl -p /etc/sysctl.d/kubernetes-storage.conf ## 2.2 优化存储类参数 kubectl patch storageclass ceph-rbd --patch '{ "parameters": { "imageFeatures": "layering,exclusive-lock,object-map,fast-diff,deep-flatten" } }' # 3. 存储容量管理 ## 3.1 配置存储配额 cat > resourcequota-storage.yaml << EOF apiVersion: v1 kind: ResourceQuota metadata: name: storage-quota namespace: fgedu-production spec: hard: requests.storage: "2000Gi" persistentvolumeclaims: "50" EOF kubectl apply -f resourcequota-storage.yaml ## 3.2 配置存储监控 cat > storage-alerts.yaml << EOF apiVersion: monitoring.coreos.com/v1 kind: PrometheusRule metadata: name: storage-alerts namespace: monitoring spec: groups: - name: storage rules: - alert: HighStorageUsage expr: kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes * 100 < 20 for: 5m labels: severity: warning annotations: summary: "High storage usage on {{ $labels.persistentvolumeclaim }}" description: "Storage usage on {{ $labels.persistentvolumeclaim }} is above 80%" - alert: StorageIOError expr: rate(kubelet_volume_stats_io_time_seconds_total[5m]) > 0.1
for: 5m
labels:
severity: warning
annotations:
summary: “Storage IO error on {{ $labels.persistentvolumeclaim }}”
description: “Storage IO errors detected on {{ $labels.persistentvolumeclaim }}”
EOF
kubectl apply -f storage-alerts.yaml
# 4. 数据备份策略
## 4.1 配置定时备份
cat > backup-job.yaml << EOF apiVersion: batch/v1 kind: CronJob metadata: name: database-backup namespace: fgedu-production spec: schedule: "0 2 * * *" concurrencyPolicy: Forbid jobTemplate: spec: template: spec: containers: - name: backup image: mysql:8.0 command: ["/bin/sh", "/scripts/backup.sh"] volumeMounts: - name: backup-script mountPath: /scripts - name: backup-volume mountPath: /backup volumes: - name: backup-script configMap: name: backup-script defaultMode: 0755，更多学习教程公众号风哥教程itpux_com。 - name: backup-volume persistentVolumeClaim: claimName: backup-pvc restartPolicy: OnFailure EOF kubectl apply -f backup-job.yaml # 5. 验证优化效果 ## 5.1 测试存储性能 kubectl run -i --tty --rm debug --image=busybox:1.34 -- dd if=/dev/zero of=/mnt/data/test bs=1M count=1024 ## 5.2 查看存储监控 kubectl port-forward -n monitoring svc/prometheus-server 9090:9090 kubectl port-forward -n monitoring svc/grafana 3000:3000