k8s-01. k8s 集群安装

k8s-01. k8s集群安装

个人学习安装笔记
内容来自视频教程尚硅谷k8s教程

1. 安装环境准备（所有节点）

准备了三台测试服务器，centos7（适用于ubuntu，差异点已另外说明）
1.1 修改服务器主机名

vi /etc/hostname
# 三台改名为node153, node154, node155

1.2 配置hosts

vi /etc/hosts

xx.xx.xx.154 node154
xx.xx.xx.155 node155
xx.xx.xx.156 node156

1.3 安装依赖包

yum install -y ntpdate wget
# ubuntu 使用 apt-get 
apt-get -y ntpdate wget


ntpdate time.windows.com

1.4 关闭防火墙

systemctl stop firewalld
systemctl disable firewalld

1.4.1 ubuntu 关闭防火墙

ufw disable

1.5 关闭swap分区和selinux

swapoff -a && sed -ri 's/.*swap.*/#&/' /etc/fstab
setenforce 0 && set -i 's/^SELINUX=*./SELINUX=disabled/' /etc/selinux/config

1.6 调整内核参数,对于K8S

cat >> kubernetes.conf <<EOF
net.ipv4.ip_forward=1
vm.swappiness=0
vm.overcommit_memory=1
vm.panic_on_oom=0
fs.inotify.max_user_instances=8192
fs.inotify.max_user_watches=1048576
fs.file-max=52706963
fs.nr_open=52706963
net.ipv6.conf.all.disable_ipv6=1
net.bridge.bridge-nf-call-ip6tables=1
net.bridge.bridge-nf-call-iptables=1
net.netfilter.nf_conntrack_max=2310720
net.ipv4.neigh.default.gc_thresh1=4096
net.ipv4.neigh.default.gc_thresh2=6144
net.ipv4.neigh.default.gc_thresh3=8192
EOF

cp kubernetes.conf /etc/sysctl.d/kubernetes.conf
sysctl -p /etc/sysctl.d/kubernetes.conf


# 如果出现 sysctl: cannot stat /proc/sys/net/bridge/bridge-nf-call-ip6tables: No such file or directory
sysctl: cannot stat /proc/sys/net/bridge/bridge-nf-call-iptables: No such file or directory
#执行 modprobe br_netfilter 命令 

# 如果出现sysctl: cannot stat /proc/sys/net/netfilter/nf_conntrack_max: No such file or directory
#执行 modprobe ip_conntrack 命令 
#再重试

2. 安装docker/kubeadm/kubelet

2.1 安装docker

wget https://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo -O /etc/yum.repos.d/docker-ce.repo
yum -y install docker-ce-18.06.1.ce-3.el7
systemctl enable docker && systemctl start docker
docker --version

cat > /etc/docker/daemon.json << EOF
{
  "registry-mirrors": ["https://b9pmyelo.mirror.aliyuncs.com"]
}
EOF

2.1.1 ubuntua安装docker

curl -fsSL https://get.docker.com | bash -s docker --mirror Aliyun

2.2 添加阿里云yum软件源

cat > /etc/yum.repos.d/kubernetes.repo << EOF
[kubernetes]
name=Kubernetes
baseurl=https://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64
enabled=1
gpgcheck=0
repo_gpgcheck=0
gpgkey=https://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg https://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpg
EOF

2.3 安装kubeadm，kubelet和kubectl

yum install -y kubelet-1.18.0 kubeadm-1.18.0 kubectl-1.18.0
systemctl enable kubelet

2.3.3 ubuntu安装 kubeadm，kubelet和kubectl

apt-get update && apt-get install -y apt-transport-https curl
apt-get install -y kubelet kubeadm kubectl --allow-unauthenticated


# 如果出现No apt package "kubeadm"  Unable to locate package kubelet 错误,执行下列命令再重试
echo "deb https://mirrors.aliyun.com/kubernetes/apt kubernetes-xenial main" >> /etc/apt/sources.list
curl https://mirrors.aliyun.com/kubernetes/apt/doc/apt-key.gpg | sudo apt-key add
apt-get update

2.4 部署master（master节点操作）

# apiserver-advertise-address master主机的IP地址
# service-cidr 不与master和pod network 地址冲突即可
# pod-network-cidr 不与master和service-cidr 地址冲突即可

kubeadm init \
  --apiserver-advertise-address=xx.xx.xx.154 \
  --image-repository registry.aliyuncs.com/google_containers \
  --kubernetes-version v1.18.0 \
  --service-cidr=10.96.0.0/12 \
  --pod-network-cidr=10.244.0.0/16


#注意 kubeadm init后会生成一个token用来其他node加入


#可能出现的错误
[kubelet-check] It seems like the kubelet isn't running or healthy.
journalctl -xeu kubelet 查看日志 提示：
failed to run Kubelet: misconfiguration: kubelet cgroup driver: \"systemd\" is different from docker cgroup driver: \"cgroupfs\"

vi /etc/docker/daemon.json
# 添加属性值
"exec-opts": ["native.cgroupdriver=systemd"]
# 如果是空的daemon.json文件，则应该为
{"exec-opts": ["native.cgroupdriver=systemd"]}
systemctl daemon-reload

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

2.5 加入Kubernetes Node(在node节点执行)

# 使用 kubeadm init 后生成的命令
# token默认有效期为24小时，如果过期可重新生成
# kubeadm token create --print-join-command


kubeadm join xx.xx.xx.154:6443 --token 1mb0zg.wqyrfiw1wjvu27lb \
    --discovery-token-ca-cert-hash sha256:5654958cbc3ee6956c91053b7a0f926df9ea5208db2303e4627a99efc5d9ac6a

2.6 部署CNI网络插件

# 下载 或者直接网络apply(网络可能下载失败，下面附文件内容，可以自己创建文件)
wget https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml

kubectl apply -f https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml


kubectl get pods -n kube-system

2.7 附 kube-flannel.yml 内容

cat <<EOF > kube-flannel.yml
---
apiVersion: policy/v1beta1
kind: PodSecurityPolicy
metadata:
  name: psp.flannel.unprivileged
  annotations:
    seccomp.security.alpha.kubernetes.io/allowedProfileNames: docker/default
    seccomp.security.alpha.kubernetes.io/defaultProfileName: docker/default
    apparmor.security.beta.kubernetes.io/allowedProfileNames: runtime/default
    apparmor.security.beta.kubernetes.io/defaultProfileName: runtime/default
spec:
  privileged: false
  volumes:
  - configMap
  - secret
  - emptyDir
  - hostPath
  allowedHostPaths:
  - pathPrefix: "/etc/cni/net.d"
  - pathPrefix: "/etc/kube-flannel"
  - pathPrefix: "/run/flannel"
  readOnlyRootFilesystem: false
  # Users and groups
  runAsUser:
    rule: RunAsAny
  supplementalGroups:
    rule: RunAsAny
  fsGroup:
    rule: RunAsAny
  # Privilege Escalation
  allowPrivilegeEscalation: false
  defaultAllowPrivilegeEscalation: false
  # Capabilities
  allowedCapabilities: ['NET_ADMIN', 'NET_RAW']
  defaultAddCapabilities: []
  requiredDropCapabilities: []
  # Host namespaces
  hostPID: false
  hostIPC: false
  hostNetwork: true
  hostPorts:
  - min: 0
    max: 65535
  # SELinux
  seLinux:
    # SELinux is unused in CaaSP
    rule: 'RunAsAny'
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: flannel
rules:
- apiGroups: ['extensions']
  resources: ['podsecuritypolicies']
  verbs: ['use']
  resourceNames: ['psp.flannel.unprivileged']
- apiGroups:
  - ""
  resources:
  - pods
  verbs:
  - get
- apiGroups:
  - ""
  resources:
  - nodes
  verbs:
  - list
  - watch
- apiGroups:
  - ""
  resources:
  - nodes/status
  verbs:
  - patch
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
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",
      "cniVersion": "0.3.1",
      "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: apps/v1
kind: DaemonSet
metadata:
  name: kube-flannel-ds
  namespace: kube-system
  labels:
    tier: node
    app: flannel
spec:
  selector:
    matchLabels:
      app: flannel
  template:
    metadata:
      labels:
        tier: node
        app: flannel
    spec:
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
            - matchExpressions:
              - key: kubernetes.io/os
                operator: In
                values:
                - linux
      hostNetwork: true
      priorityClassName: system-node-critical
      tolerations:
      - operator: Exists
        effect: NoSchedule
      serviceAccountName: flannel
      initContainers:
      - name: install-cni-plugin
        image: rancher/mirrored-flannelcni-flannel-cni-plugin:v1.0.0
        command:
        - cp
        args:
        - -f
        - /flannel
        - /opt/cni/bin/flannel
        volumeMounts:
        - name: cni-plugin
          mountPath: /opt/cni/bin
      - name: install-cni
        image: rancher/mirrored-flannelcni-flannel:v0.16.1
        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: rancher/mirrored-flannelcni-flannel:v0.16.1
        command:
        - /opt/bin/flanneld
        args:
        - --ip-masq
        - --kube-subnet-mgr
        resources:
          requests:
            cpu: "100m"
            memory: "50Mi"
          limits:
            cpu: "100m"
            memory: "50Mi"
        securityContext:
          privileged: false
          capabilities:
            add: ["NET_ADMIN", "NET_RAW"]
        env:
        - name: POD_NAME
          valueFrom:
            fieldRef:
              fieldPath: metadata.name
        - name: POD_NAMESPACE
          valueFrom:
            fieldRef:
              fieldPath: metadata.namespace
        volumeMounts:
        - name: run
          mountPath: /run/flannel
        - name: flannel-cfg
          mountPath: /etc/kube-flannel/
      volumes:
      - name: run
        hostPath:
          path: /run/flannel
      - name: cni-plugin
        hostPath:
          path: /opt/cni/bin
      - name: cni
        hostPath:
          path: /etc/cni/net.d
      - name: flannel-cfg
        configMap:
          name: kube-flannel-cfg
EOF

测试

# 创建一个Nginx服务,测试是否能正常启动及访问
kubectl create deployment nginx --image=nginx
kubectl expose deployment nginx --port=80 --type=NodePort
kubectl get pod,svc

一段时间后，kubectl get pods可以看到nginx服务已自动部署

kubectl get pod,svc 可以看到映射的端口号

现在 master的 IP:30522 应该可以访问到nginx了