磁盘压力提示
解决步骤
1.登录主机 整个根文件系统已经占用100
2.在根目录下执行 du -h --max-depth=1
3.查到var/lib目录下占用了很大的磁盘空间
4.依次递归查找占用空间最大的子目录
5.执行rm -fr 目录 磁盘空间不会立即进行释放
6.需要等待一段时间才会把磁盘资源释放出来
Rancher重新添加主机节点
rancher添加节点不成功 需要首先清理环境
由于历史原因已经安装过程中的多次尝试,但是安装环境不纯净,会产生各种各样的问题(比如下面的etcd证书问题)
#!/bin/zsh
systemctl disable kubelet.service
systemctl disable kube-scheduler.service
systemctl disable kube-proxy.service
systemctl disable kube-controller-manager.service
systemctl disable kube-apiserver.service
systemctl stop kubelet.service
systemctl stop kube-scheduler.service
systemctl stop kube-proxy.service
systemctl stop kube-controller-manager.service
systemctl stop kube-apiserver.service
# 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/pods \
/var/run/calico
# 清理网络接口
network_interface=`ls /sys/class/net`
for net_inter in $network_interface;
do
if ! echo $net_inter | grep -qiE 'lo|docker0|eth*|ens*';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
pro_pid=`ps -ef |grep -v grep |grep kube|awk '{print $2}'`
if [[ -n $pro_pid ]];then
kill -9 $pro_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
清理rke
#!/bin/zsh
kubeadm reset
sudo apt-get purge kubeadm kubectl kubelet kubernetes-cni kube*
sudo apt-get autoremove
sudo rm -rf ~/.kube
清理kubeadm
清理后添加主机成功
查找占用资源的进程