阿里云ECS搭建kubernetes1.11

环境信息

说明

1、使用kubeadm安装集群

虚拟机信息

hostname	memory	cpu	disk	role
node1.com	4G	2C	vda20G vdb20G	master
node1.com	4G	2C	vda20G vdb20G	node

其中vda为系统盘，vdb为docker storage，用于存储容器和镜像

配置主机名

#以下在两个节点执行
hostnamectl set-hostname node1.com
hostnamectl set-hostname node2.com

配置阿里云k8s yum repo

#以下在两个节点执行
cat <<EOF > /etc/yum.repos.d/kubernetes.repo
[kubernetes]
name=Kubernetes
baseurl=http://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64
enabled=
gpgcheck=
repo_gpgcheck=
gpgkey=http://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg
       http://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpg
EOF

yum update -y
yum upgrade
yum clean all
yum makecache

安装docker

#在两个节点执行
yum install -y docker

配置docker-storage为deviceMapper

#在两个节点执行
#创建pv
pvcreate /dev/vdb

#使用上述创建的pv创建docker-vg
vgcreate docker-vg /dev/vdb

#配置docker使用docker-vg作为后端存储
echo VG=docker-vg > /etc/sysconfig/docker-storage-setup
docker-storage-setup

#将docker-vg的docker-pool这个lv扩展到100%
lvextend -l %VG  /dev/docker-vg/docker-pool

#启动docker并设置开机自启
systemctl start docker
systemctl enable docker

安装其他需要的软件

#以下在两个节点执行
yum install -y bridge-utils

关闭防火墙、swap和selinux

#以下在两个节点执行
systemctl stop firewalld && systemctl disable firewalld
swapoff -a
setenforce 

各节点配置主机名解析

#在两个节点执行
cat <<EOF >> /etc/hosts
172.31.2.130 node1.com
172.31.2.131 node2.com
EOF

安装kubelet kubeadm kubectl

#以下在master执行
#查看yum repo中kubelet可用的版本
yum list --showduplicates | grep kubelet

#安装 kubelet-1.11. 、kubeadm-1.11. 和kubectl-1.11.1

yum install -y kubelet-1.11.1
yum install -y kubectl-1.11.1 

yum install -y kubeadm-1.11.1

由于安装kubeadm会自动安装kubectl、kubelet，安装kubeadm-1.11.1依赖安装的kubectl和kubelet版本并不是1.11.1，而是最新的
（1）可以将非1.11.1的组件通过yum remove再重新安装
（2）按照上述顺序先安装Kubectl-1.11.1和kubelet-1.11.1就没有问题

#查看上述安装是否是对应1.11版本
yum list installed | grep "kubernetes"

正确安装完之后如下所示

#配置kubelet开机启动
systemctl enable kubelet

拉取镜像

以下在master执行

docker pull mirrorgooglecontainers/kube-apiserver-amd64:v1.11.1
docker pull mirrorgooglecontainers/pause-amd64:3.1
docker pull mirrorgooglecontainers/kube-controller-manager-amd64:v1.11.1
docker pull mirrorgooglecontainers/kube-scheduler-amd64:v1.11.1
docker pull mirrorgooglecontainers/kube-proxy-amd64:v1.11.1
docker pull mirrorgooglecontainers/etcd-amd64:3.2.
docker pull coredns/coredns:1.1.

docker tag mirrorgooglecontainers/kube-apiserver-amd64:v1.11.1 k8s.gcr.io/kube-apiserver-amd64:v1.11.1
docker tag mirrorgooglecontainers/pause-amd64:3.1 k8s.gcr.io/pause:3.1
docker tag mirrorgooglecontainers/kube-controller-manager-amd64:v1.11.1 k8s.gcr.io/kube-controller-manager-amd64:v1.11.1
docker tag mirrorgooglecontainers/kube-scheduler-amd64:v1.11.1 k8s.gcr.io/kube-scheduler-amd64:v1.11.1
docker tag mirrorgooglecontainers/kube-proxy-amd64:v1.11.1 k8s.gcr.io/kube-proxy-amd64:v1.11.1
docker tag mirrorgooglecontainers/etcd-amd64:3.2. k8s.gcr.io/etcd-amd64:3.2.
docker tag coredns/coredns:1.1. k8s.gcr.io/coredns:1.1.

以下在node执行

docker pull coredns/coredns:1.1.
docker pull mirrorgooglecontainers/pause-amd64:3.1
docker pull mirrorgooglecontainers/kube-proxy-amd64:v1.11.1

docker tag coredns/coredns:1.1. k8s.gcr.io/coredns:1.1.
docker tag mirrorgooglecontainers/pause-amd64:3.1 k8s.gcr.io/pause:3.1
docker tag mirrorgooglecontainers/kube-proxy-amd64:v1.11.1 k8s.gcr.io/kube-proxy-amd64:v1.11.1

使用kubeadm初始化集群

#此处pod-network-cidr地址范围应与下面的flannel yaml中定义的一致
kubeadm init --kubernetes-version=v1.11.1 --pod-network-cidr=10.244.0.0/16

mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config

加入计算节点到集群中

以下在需要加入集群的节点中执行

#获取加入集群需要使用的hash值
openssl x509 -pubkey -in /etc/kubernetes/pki/ca.crt | openssl rsa -pubin -outform der >/dev/null | openssl dgst -sha256 -hex | sed 's/^.* //'

#获取加入集群需要使用的token值
kubeadm token list
#如果上述命令没有token，说明已过期，通过如下命令重新生成

kubeadm token create

#使用kubeadm加入集群 kubeadm join node1.com: --token <token> --discovery-token-ca-cert-hash sha256:<hash>

此时kubectl get nodes如下，因为还没有配置网络插件

配置Flannel网路插件

#新建kube-flannel.yaml文件
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1beta1
metadata:
  name: flannel
rules:
  - apiGroups:
      - ""
    resources:
      - pods
    verbs:
      - get
  - apiGroups:
      - ""
    resources:
      - nodes
    verbs:
      - list
      - watch
  - apiGroups:
      - ""
    resources:
      - nodes/status
    verbs:
      - patch
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1beta1
metadata:
  name: flannel
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: flannel
subjects:
- kind: ServiceAccount
  name: flannel
  namespace: kube-system
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: flannel
  namespace: kube-system
---
kind: ConfigMap
apiVersion: v1
metadata:
  name: kube-flannel-cfg
  namespace: kube-system
  labels:
    tier: node
    app: flannel
data:
  cni-conf.json: |
    {
      "name": "cbr0",
      "plugins": [
        {
          "type": "flannel",
          "delegate": {
            "hairpinMode": true,
            "isDefaultGateway": true
          }
        },
        {
          "type": "portmap",
          "capabilities": {
            "portMappings": true
          }
        }
      ]
    }
  net-conf.json: |
    {
      "Network": "10.244.0.0/16",
      "Backend": {
        "Type": "vxlan"
      }
    }
---
apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
  name: kube-flannel-ds
  namespace: kube-system
  labels:
    tier: node
    app: flannel
spec:
  template:
    metadata:
      labels:
        tier: node
        app: flannel
    spec:
      hostNetwork: true
      nodeSelector:
        beta.kubernetes.io/arch: amd64
      tolerations:
      - key: node-role.kubernetes.io/master
        operator: Exists
        effect: NoSchedule
      serviceAccountName: flannel
      initContainers:
      - name: install-cni
        image: registry.cn-shanghai.aliyuncs.com/gcr-k8s/flannel:v0.10.0-amd64
        command:
        - cp
        args:
        - -f
        - /etc/kube-flannel/cni-conf.json
        - /etc/cni/net.d/-flannel.conflist
        volumeMounts:
        - name: cni
          mountPath: /etc/cni/net.d
        - name: flannel-cfg
          mountPath: /etc/kube-flannel/
      containers:
      - name: kube-flannel
        image: registry.cn-shanghai.aliyuncs.com/gcr-k8s/flannel:v0.10.0-amd64
        command:
        - /opt/bin/flanneld
        args:
        - --ip-masq
        - --kube-subnet-mgr
        - --iface=eth0
        resources:
          requests:
            cpu: "100m"
            memory: "50Mi"
          limits:
            cpu: "100m"
            memory: "50Mi"
        securityContext:
          privileged: true
        env:
        - name: POD_NAME
          valueFrom:
            fieldRef:
              fieldPath: metadata.name
        - name: POD_NAMESPACE
          valueFrom:
            fieldRef:
              fieldPath: metadata.namespace
        volumeMounts:
        - name: run
          mountPath: /run
        - name: flannel-cfg
          mountPath: /etc/kube-flannel/
      volumes:
        - name: run
          hostPath:
            path: /run
        - name: cni
          hostPath:
            path: /etc/cni/net.d
        - name: flannel-cfg
          configMap:
            name: kube-flannel-cfg

#使用kubectl创建kube-flannel ds
kubectl apply -f kube-flannel.yaml
#部署完成查看flannel pod和节点的状态

部署测试应用

#部署nginx deployment
kubectl create -f https://kubernetes.io/docs/user-guide/nginx-deployment.yaml

#expose deployment，类型为NodePort
kubectl expose  deployment nginx-deployment --type=NodePort

设置master参与调度

#取消master节点的taints污点属性
kubectl taint node node1.com node-role.kubernetes.io/master-

安装过程中遇到的问题

1、kubectl kubelet kubeadm的版本不一致导致安装失败

#通过一条命令yum install -y kubectl-1.11. kubelet-1.11. kubeadm-1.11. 报依赖问题无法安装
#需要通过逐一使用yum进行安装
yum install -y kubelet-1.11.
yum install -y kubectl-1.11.
yum install -y kubeadm-1.11.1

#逐一安装之后，通过以下命令发现版本不是1.11.1
yum list installed | grep "kubernetes"

#将不是1.11.1版本的remove之后，重新install即可
#原因可能是yum install kubeadm-1.11.1时会附带安装高版本的kubelet 和 kubectl

2、flannel pod启动失败，CrashLoopBackOff，通过kubectl logs {pod_name}如下

I0815 ::37.646559        main.go:] Could not find valid interface matching ens32: error looking up interface ens32: route ip+net: no such network interface
E0815 ::37.646628        main.go:] Failed to find interface to use that matches the interfaces and/or regexes provided

需要查看虚拟机的网卡名称，如下，为eth0，并与flannel pod的yaml文件中--iface=eth0 arg保持一致

3、部署nginx后，无法通过公网ip:nodePort访问

需要在阿里云控制台中为对应的实例配置安全组规则：开放30000-32767端口

4、docker-storage出现问题时可以通过如下方式重置docker-storage

#重置docker-storage
rm -rf /etc/sysconfig/docker-storage
rm -rf /var/lib/docker
#报如下错误
rm: cannot remove ‘/var/lib/docker/devicemapper’: Device or resource busy
rm: cannot remove ‘/var/lib/docker/containers’: Device or resource busy

#通过
umount /var/lib/docker/devicemapper
umount /var/lib/docker/containers
#即可删除/var/lib/docker目录

docker-storage-setup --reset

#配置docker使用docker-vg作为后端存储
echo VG=docker-vg > /etc/sysconfig/docker-storage-setup
docker-storage-setup