阿里雲ECS搭建kubernetes1.11

環境信息

說明

1、使用kubeadm安裝集群

 

 

虛擬機信息

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

其中vda為系統盤，vdb為docker storage，用於存儲容器和鏡像

配置主機名

#以下在兩個節點執行
hostnamectl set-hostname node1.com
hostnamectl set-hostname node2.com

 

配置阿里雲k8s yum repo

#以下在兩個節點執行
cat <<EOF > /etc/yum.repos.d/kubernetes.repo
[kubernetes]
name=Kubernetes
baseurl=http://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64
enabled=1
gpgcheck=0
repo_gpgcheck=0
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

 

安裝docker

#在兩個節點執行
yum install -y docker

 

配置docker-storage為deviceMapper

#在兩個節點執行
#創建pv 
pvcreate /dev/vdb

#使用上述創建的pv創建docker-vg
vgcreate docker-vg /dev/vdb

#配置docker使用docker-vg作為后端存儲
echo VG=docker-vg > /etc/sysconfig/docker-storage-setup
docker-storage-setup

#將docker-vg的docker-pool這個lv擴展到100%
lvextend -l 100%VG  /dev/docker-vg/docker-pool

#啟動docker並設置開機自啟
systemctl start docker
systemctl enable docker

 

安裝其他需要的軟件

#以下在兩個節點執行
yum install -y bridge-utils

 

關閉防火牆、swap和selinux

#以下在兩個節點執行
systemctl stop firewalld && systemctl disable firewalld
swapoff -a
setenforce 0

 

各節點配置主機名解析

#在兩個節點執行
cat <<EOF >> /etc/hosts
172.31.2.130 node1.com
172.31.2.131 node2.com
EOF

 

安裝kubelet kubeadm kubectl

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

 

#安裝 kubelet-1.11.1 、kubeadm-1.11.1 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

由於安裝kubeadm會自動安裝kubectl、kubelet，安裝kubeadm-1.11.1依賴安裝的kubectl和kubelet版本並不是1.11.1，而是最新的
（1）可以將非1.11.1的組件通過yum remove再重新安裝
（2）按照上述順序先安裝Kubectl-1.11.1和kubelet-1.11.1就沒有問題

#查看上述安裝是否是對應1.11版本
yum list installed | grep "kubernetes"

正確安裝完之后如下所示

#配置kubelet開機啟動
systemctl enable kubelet

 

拉取鏡像

以下在master執行

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-amd64:3.2.18
docker pull coredns/coredns:1.1.3


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-amd64:3.2.18 k8s.gcr.io/etcd-amd64:3.2.18
docker tag coredns/coredns:1.1.3 k8s.gcr.io/coredns:1.1.3

以下在node執行

docker pull coredns/coredns:1.1.3
docker pull mirrorgooglecontainers/pause-amd64:3.1
docker pull mirrorgooglecontainers/kube-proxy-amd64:v1.11.1

docker tag coredns/coredns:1.1.3 k8s.gcr.io/coredns:1.1.3
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

#此處pod-network-cidr地址范圍應與下面的flannel yaml中定義的一致
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

 

加入計算節點到集群中

以下在需要加入集群的節點中執行

#獲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 2>/dev/null | openssl dgst -sha256 -hex | sed 's/^.* //'

#獲取加入集群需要使用的token值
kubeadm token list
#如果上述命令沒有token，說明已過期，通過如下命令重新生成

kubeadm token create

#使用kubeadm加入集群 kubeadm join node1.com:6443 --token <token> --discovery-token-ca-cert-hash sha256:<hash>

此時kubectl get nodes如下，因為還沒有配置網絡插件

配置Flannel網路插件

#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/10-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創建kube-flannel ds
kubectl apply -f kube-flannel.yaml
#部署完成查看flannel pod和節點的狀態

 

 部署測試應用

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

#expose deployment，類型為NodePort
kubectl expose  deployment nginx-deployment --type=NodePort

 

設置master參與調度

#取消master節點的taints污點屬性
kubectl taint node node1.com node-role.kubernetes.io/master-

 

安裝過程中遇到的問題

1、kubectl kubelet kubeadm的版本不一致導致安裝失敗

 

#通過一條命令yum install -y kubectl-1.11.1 kubelet-1.11.1 kubeadm-1.11.1 報依賴問題無法安裝
#需要通過逐一使用yum進行安裝
yum install -y kubelet-1.11.1 
yum install -y kubectl-1.11.1 
yum install -y kubeadm-1.11.1

#逐一安裝之后，通過以下命令發現版本不是1.11.1
yum list installed | grep "kubernetes"

#將不是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時會附帶安裝高版本的kubelet 和 kubectl

 

2、flannel pod啟動失敗，CrashLoopBackOff，通過kubectl logs {pod_name}如下

I0815 00:25:37.646559       1 main.go:201] Could not find valid interface matching ens32: error looking up interface ens32: route ip+net: no such network interface
E0815 00:25:37.646628       1 main.go:225] Failed to find interface to use that matches the interfaces and/or regexes provided

需要查看虛擬機的網卡名稱，如下，為eth0，並與flannel pod的yaml文件中--iface=eth0 arg保持一致

 

3、部署nginx后，無法通過公網ip:nodePort訪問

 需要在阿里雲控制台中為對應的實例配置安全組規則：開放30000-32767端口

 

4、docker-storage出現問題時可以通過如下方式重置docker-storage

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

#通過
umount /var/lib/docker/devicemapper
umount /var/lib/docker/containers
#即可刪除/var/lib/docker目錄

docker-storage-setup --reset

#配置docker使用docker-vg作為后端存儲 echo VG=docker-vg > /etc/sysconfig/docker-storage-setup docker-storage-setup