# 创建备份目录
mkdir -p /KubeSphere/backup/etcd
# 目录创建成功

# 执行ETCD备份
ETCDCTL_API=3 etcdctl snapshot save /KubeSphere/backup/etcd/etcd-snapshot-$(date +%Y%m%d%H%M%S).db \
–endpoints=https://192.168.1.10:2379 \
–cacert=/etc/kubernetes/pki/etcd/ca.crt \
–cert=/etc/kubernetes/pki/etcd/server.crt \
–key=/etc/kubernetes/pki/etcd/server.key
Snapshot saved at /KubeSphere/backup/etcd/etcd-snapshot-20231001100000.db

# 验证备份文件
，
ls -lh /KubeSphere/backup/etcd/
total 1024M
-rw-r–r– 1 root root 1024M Oct 1 10:00 etcd-snapshot-20231001100000.db

# 检查备份文件完整性
ETCDCTL_API=3 etcdctl snapshot status /KubeSphere/backup/etcd/etcd-snapshot-20231001100000.db
2023-10-01 10:05:00.000000 I | etcdctl: snapshot file is valid: 1024 MB

# 停止控制平面组件
systemctl stop kube-apiserver kube-controller-manager kube-scheduler
# 组件停止成功

# 停止ETCD服务
systemctl stop etcd
# ETCD服务停止成功

# 备份当前ETCD数据目录
mv /var/lib/etcd /var/lib/etcd.bak
# 备份成功

# 从备份中恢复ETCD数据
ETCDCTL_API=3 etcdctl snapshot restore /KubeSphere/backup/etcd/etcd-snapshot-20231001100000.db \
–data-dir=/var/lib/etcd \
–name=etcd-0 \
–initial-cluster=etcd-0=https://192.168.1.10:2380 \
–initial-cluster-token=etcd-cluster-1 \
–initial-advertise-peer-urls=https://192.168.1.10:2380
2023-10-01 10:10:00.000000 I | etcdserver/membership: added member 8e9e05c52164694d [https://192.168.1.10:2380] to cluster cdf818194e3a8c32

# 更改ETCD数据目录权限
chown -R etcd:etcd /var/lib/etcd
# 权限更改成功

# 启动ETCD服务
systemctl start etcd
# ETCD服务启动成功

# 启动控制平面组件
systemctl start kube-apiserver kube-controller-manager kube-scheduler
# 组件启动成功

# 验证控制平面状态
kubectl get componentstatuses
NAME STATUS MESSAGE ERROR
scheduler Healthy ok
controller-manager Healthy ok
etcd-0 Healthy {“health”:”true”}

# 创建ETCD备份脚本
cat > /KubeSphere/scripts/etcd-backup.sh << EOF
#!/bin/bash
# etcd-backup.sh
# from:www.itpux.com.qq113257174.wx:itpux-com
# web: http://www.fgedu.net.cn

# 备份目录
BACKUP_DIR=”/KubeSphere/backup/etcd”
mkdir -p $BACKUP_DIR

# 备份文件名
BACKUP_FILE=”$BACKUP_DIR/etcd-snapshot-$(date +%Y%m%d%H%M%S).db”

# ETCD配置
ETCD_ENDPOINTS=”https://192.168.1.10:2379″
ETCD_CACERT=”/etc/kubernetes/pki/etcd/ca.crt”
ETCD_CERT=”/etc/kubernetes/pki/etcd/server.crt”
ETCD_KEY=”/etc/kubernetes/pki/etcd/server.key”

# 执行备份
ETCDCTL_API=3 etcdctl snapshot save $BACKUP_FILE \
–endpoints=$ETCD_ENDPOINTS \
–cacert=$ETCD_CACERT \
–cert=$ETCD_CERT \
–key=$ETCD_KEY

# 验证备份
if [ $? -eq 0 ]; then
echo “ETCD备份成功: $BACKUP_FILE”
# 清理过期备份（保留7天）
find $BACKUP_DIR -name “etcd-snapshot-*.db” -mtime +7 -delete
else
echo “ETCD备份失败”
exit 1
fi
EOF
chmod +x /KubeSphere/scripts/etcd-backup.sh

# 设置定时备份任务
crontab -e
# 添加以下内容：
0 0 * * * /KubeSphere/scripts/etcd-backup.sh >> /KubeSphere/logs/etcd-backup.log 2>&1

# 创建自动化恢复脚本
cat > /KubeSphere/scripts/etcd-restore.sh << EOF
#!/bin/bash
# etcd-restore.sh
# from:www.itpux.com.qq113257174.wx:itpux-com
# web: http://www.fgedu.net.cn

# 备份目录
BACKUP_DIR=”/KubeSphere/backup/etcd”

# 获取最新的备份
LATEST_BACKUP=$(ls -t $BACKUP_DIR/etcd-snapshot-*.db | head -1)

if [ -z “$LATEST_BACKUP” ]; then
echo “没有找到备份文件”
exit 1
fi

echo “使用备份文件: $LATEST_BACKUP”

# 停止控制平面组件
systemctl stop kube-apiserver kube-controller-manager kube-scheduler

# 停止ETCD服务
systemctl stop etcd

# 备份当前ETCD数据目录
mv /var/lib/etcd /var/lib/etcd.bak.$(date +%Y%m%d%H%M%S)

# 从备份中恢复ETCD数据
ETCDCTL_API=3 etcdctl snapshot restore $LATEST_BACKUP \
–data-dir=/var/lib/etcd \
–name=etcd-0 \
–initial-cluster=etcd-0=https://192.168.1.10:2380 \
–initial-cluster-token=etcd-cluster-1 \
–initial-advertise-peer-urls=https://192.168.1.10:2380

# 更改ETCD数据目录权限
chown -R etcd:etcd /var/lib/etcd

# 启动ETCD服务
systemctl start etcd

# 启动控制平面组件
systemctl start kube-apiserver kube-controller-manager kube-scheduler

# 验证控制平面状态
echo “等待30秒后验证控制平面状态…”
sleep 30
kubectl get componentstatuses
EOF
chmod +x /KubeSphere/scripts/etcd-restore.sh

# 执行自动化恢复
/KubeSphere/scripts/etcd-restore.sh
使用备份文件: /KubeSphere/backup/etcd/etcd-snapshot-20231001100000.db
等待30秒后验证控制平面状态…
NAME STATUS MESSAGE ERROR
scheduler Healthy ok
controller-manager Healthy ok
etcd-0 Healthy {“health”:”true”}