筆者的整套架K8S集群是通過racher建立的,rancher版本為2.5.14,目前还是测试阶段,因为种种异常,整套架构都面临重建,但是之前我的master节点已经安装过集群,要彻底清理环境,否则会报错,无法安装,原因是master节点已经存在etcd的信息,必须删除,以下脚本为如何清理master的环境。
#!/bin/bash
KUBE_SVC=’
kubelet
kube-scheduler
kube-proxy
kube-controller-manager
kube-apiserver
‘
for kube_svc in ${KUBE_SVC};
do
# 停止服务
if [[ `systemctl is-active ${kube_svc}` == ‘active’ ]]; then
systemctl stop ${kube_svc}
fi
# 禁止服务开机启动
if [[ `systemctl is-enabled ${kube_svc}` == ‘enabled’ ]]; then
systemctl disable ${kube_svc}
fi
done
# 停止所有容器
docker stop $(docker ps -aq)
# 删除所有容器
docker rm -f $(docker ps -qa)
# 删除所有容器卷
docker volume rm $(docker volume ls -q)
# 卸载mount目录
for mount in $(mount | grep tmpfs | grep ‘/var/lib/kubelet’ | awk ‘{ print $3 }’) /var/lib/kubelet /var/lib/rancher;
do
umount $mount;
done
# 备份目录
mv /etc/kubernetes /etc/kubernetes-bak-$(date +”%Y%m%d%H%M”)
mv /var/lib/etcd /var/lib/etcd-bak-$(date +”%Y%m%d%H%M”)
mv /var/lib/rancher /var/lib/rancher-bak-$(date +”%Y%m%d%H%M”)
mv /opt/rke /opt/rke-bak-$(date +”%Y%m%d%H%M”)
# 删除残留路径
rm -rf /etc/ceph \
/etc/cni \
/opt/cni \
/run/secrets/kubernetes.io \
/run/calico \
/run/flannel \
/var/lib/calico \
/var/lib/cni \
/var/lib/kubelet \
/var/log/containers \
/var/log/kube-audit \
/var/log/pods \
/var/run/calico
# 清理网络接口
no_del_net_inter=’
lo
docker0
eth
ens
bond
‘
network_interface=`ls /sys/class/net`
for net_inter in $network_interface;
do
if ! echo “${no_del_net_inter}” | grep -qE ${net_inter:0:3}; then
ip link delete $net_inter
fi
done
# 清理残留进程
port_list=’
80
443
6443
2376
2379
2380
8472
9099
10250
10254
‘
for port in $port_list;
do
pid=`netstat -atlnup | grep $port | awk ‘{print $7}’ | awk -F ‘/’ ‘{print $1}’ | grep -v – | sort -rnk2 | uniq`
if [[ -n $pid ]]; then
kill -9 $pid
fi
done
kube_pid=`ps -ef | grep -v grep | grep kube | awk ‘{print $2}’`
if [[ -n $kube_pid ]]; then
kill -9 $kube_pid
fi
# 清理Iptables表
## 注意:如果节点Iptables有特殊配置,以下命令请谨慎操作
sudo iptables –flush
sudo iptables –flush –table nat
sudo iptables –flush –table filter
sudo iptables –table nat –delete-chain
sudo iptables –table filter –delete-chain
systemctl restart docker
三个master节点和work节点均执行,执行完之后就可以重新安装集群了
———————————–