apt-get update

swapoff -a

root@gpu-10-0-1-24:~# freetotal        used        free      shared  buff/cache   available
Mem:      528016312     6131652   343432968     6595072   178451692   512492696
Swap:             0           0           0

systemctl stop firewalld
systemctl disable firewalld

setenforce 0

kubeadm init --pod-network-cidr=10.244.0.0/16 --apiserver-advertise-address=10.0.1.18 --kubernetes-version=v1.11.1 --ignore-preflight-errors=all //--skip-preflight-checks选项已经弃用

[preflight] Activating the kubelet service
failure loading ca certificate: couldn't load the private key file /etc/kubernetes/pki/ca.key: open /etc/kubernetes/pki/ca.key: no such file or directory

sudo: unable to resolve host gpu-10-0-1-18

getenforce

kubeadm join 10.0.0.39:6443 --token 4g0p8w.w5p29ukwvitim2ti
--discovery-token-ca-cert-hash sha256:21d0adbfcb409dca97e655641573b2ee51c
77a212f194e20a307cb459e5f77c8

kubeadm token list

kubeadm token create --print-join-command

apt-get update && apt-get install -y apt-transport-https curl
curl -s https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key add -
cat <<EOF >/etc/apt/sources.list.d/kubernetes.list
deb https://apt.kubernetes.io/ kubernetes-xenial main
EOF
apt-get update
apt-get install -y kubelet kubeadm kubectl
apt-mark hold kubelet kubeadm kubectl

kubectl get pods -n kube-system | grep flannel

kubectl get pods -n kube-system -o wide | grep gpu-10-0-1-24

root@cpu-10-0-3-9:~# ks init xps-kubeflow
INFO Using context "kubernetes-admin@kubernetes" from kubeconfig file "/root/.kube/config"
INFO Creating environment "default" with namespace "default", pointing to "version:v1.8.0" cluster at address "https://10.0.3.9:6443"
INFO Generating ksonnet-lib data at path '/root/xps-kubeflow/lib/ksonnet-lib/v1.8.0'

root@cpu-10-0-3-9:~/xps-k8s# kubectl create -f xps_crd.yaml
customresourcedefinition.apiextensions.k8s.io/xps.tencent.com created

kubectl get crd

Pod sandbox changed, it will be killed and re-created.

docker run --security-opt=no-new-privileges --cap-drop=ALL --network=none -it -v /var/lib/kubelet/device-plugins:/var/lib/kubelet/device-plugins nvidia/k8s-device-plugin:1.11

emptydir只在pod范围内共享 所以只要保证一个pod一个容器就行

kubectl taint nodes --all node-role.kubernetes.io/master-

kubectl get mxjobs.kubeflow.org