角色

主机准备:
1.安装必要软件以及升级所有软件

yum -y install vim-enhanced wget curl net-tools conntrack-tools bind-utils socat ipvsadm ipset
yum -y update

2.关闭selinux

sed -i 's#SELINUX=enforcing#SELINUX=disabled#g'  /etc/sysconfig/selinux
sed -i 's#SELINUX=enforcing#SELINUX=disabled#g'  /etc/selinux/config 

3.关闭不必要服务

systemctl disable auditd
systemctl disable postfix
systemctl disable irqbalance
systemctl disable remote-fs
systemctl disable tuned
systemctl disable rhel-configure
systemctl disable firewalld

4.安装kernel-lt(kernel 4.4.178)

rpm --import https://www.elrepo.org/RPM-GPG-KEY-elrepo.org
yum -y install https://www.elrepo.org/elrepo-release-7.0-3.el7.elrepo.noarch.rpm
yum --enablerepo=elrepo-kernel install kernel-lt -y

grub2-set-default 0
grub2-mkconfig -o /etc/grub2.cfg

5.优化内核

cat >>/etc/sysctl.conf <<EOF
net.ipv4.ip_forward = 1
vm.swappiness = 0
net.bridge.bridge-nf-call-ip6tables = 1
net.bridge.bridge-nf-call-iptables = 1
net.ipv4.tcp_max_syn_backlog = 65536
net.core.netdev_max_backlog =  32768
net.core.somaxconn = 32768
net.core.wmem_default = 8388608
net.core.rmem_default = 8388608
net.core.rmem_max = 16777216
net.core.wmem_max = 16777216
net.ipv4.tcp_timestamps = 0
net.ipv4.tcp_synack_retries = 2
net.ipv4.tcp_syn_retries = 2
net.ipv4.tcp_tw_recycle = 1
net.ipv4.tcp_tw_reuse = 1
net.ipv4.tcp_mem = 94500000 915000000 927000000
net.ipv4.tcp_max_orphans = 3276800
net.ipv4.ip_local_port_range = 1024  65535
EOF

sysctl -p

6.修改文件打开数

cat >>/etc/security/limits.conf <<EOF
* soft memlock unlimited
* hard memlock unlimited
* soft nofile 65535
* hard nofile 65535
* soft nproc 65535
* hard nproc 65535
EOF

7.系统关闭使用交换内存

echo "swapoff -a">>/etc/rc.local
chmod +x /etc/rc.local
swapoff -a

8.安装docker

yum -y install docker
curl -sSL https://get.daocloud.io/daotools/set_mirror.sh | sh -s http://e2a6d434.m.daocloud.io
sed -i 's#,##g' /etc/docker/daemon.json
service docker start 
chkconfig docker on

9.内核加载ipvs_rr、ipvs_wrr、ipvs_sh模块

cat <<EOF>/etc/sysconfig/modules/ipvs.modules 
#!/bin/bash
ipvs_modules="ip_vs ip_vs_lc ip_vs_wlc ip_vs_rr ip_vs_wrr ip_vs_lblc ip_vs_lblcr ip_vs_dh ip_vs_sh ip_vs_fo ip_vs_nq ip_vs_sed ip_vs_ftp nf_conntrack_ipv4"
for kernel_module in \${ipvs_modules}; do
 /sbin/modinfo -F filename \${kernel_module} > /dev/null 2>&1
 if [ $? -eq 0 ]; then
 /sbin/modprobe \${kernel_module}
 fi
done
EOF

chmod +x /etc/sysconfig/modules/ipvs.modules
sh /etc/sysconfig/modules/ipvs.modules

10.安装kubeadm、kubelet、kubectl

mkdir /etc/yum.repos.d/bak && cp -rf /etc/yum.repos.d/*.repo /etc/yum.repos.d/bak
wget -O /etc/yum.repos.d/CentOS-Base.repo http://mirrors.cloud.tencent.com/repo/centos7_base.repo
wget -O /etc/yum.repos.d/epel.repo http://mirrors.cloud.tencent.com/repo/epel-7.repo
 yum clean all && yum makecache
cat <<EOF > /etc/yum.repos.d/kubernetes.repo
 [kubernetes]
name=Kubernetes
baseurl=https://mirrors.aliyun.com/kubernetes/yum/repos/kubernetes-el7-x86_64/
enabled=1
gpgcheck=1
repo_gpgcheck=1
gpgkey=https://mirrors.aliyun.com/kubernetes/yum/doc/yum-key.gpg https://mirrors.aliyun.com/kubernetes/yum/doc/rpm-package-key.gpg
EOF
yum install -y kubelet kubeadm kubectl
systemctl enable kubelet

11.安装以及配置haproxy

yum -y install haproxy
cat <<EOF >/etc/haproxy/haproxy.cfg 
global
    #   /etc/sysconfig/syslog
    #
    #    local2.*                       /var/log/haproxy.log
    #
    log         127.0.0.1 local2

    chroot      /var/lib/haproxy
    pidfile     /var/run/haproxy.pid
    maxconn     4000
    user        haproxy
    group       haproxy
    daemon

defaults
    mode                    tcp
    log                     global
    retries                 3
    timeout connect         10s
    timeout client          1m
    timeout server          1m

frontend  kubernetes
        bind *:8443
        mode tcp
        default_backend kubernetes_master

backend kubernetes_master
    balance     roundrobin
    server 210 192.168.10.210:6443 check maxconn 2000
    server 211 192.168.10.211:6443 check maxconn 2000
    server 212 192.168.10.212:6443 check maxconn 2000
EOF

systemctl start haproxy
systemctl enable haproxy

12.安装及配置keepalived

yum -y install keepalived
cat <<EOF >/etc/keepalived/keepalived.conf
global_defs {
   router_id LVS_DEVEL
   vrrp_skip_check_adv_addr
   // vrrp_strict  加了这个参数VIP无法PING通
   vrrp_garp_interval 0
   vrrp_gna_interval 0
}

vrrp_instance VI_1 {
    state MASTER   #角色需要修改
    interface ens32  #此处需要修改为网卡的名称,有的是eth0
    virtual_router_id 51
    priority 100     #每台机器此处不同
    advert_int 1
    authentication {
        auth_type PASS
        auth_pass 1111
    }
    virtual_ipaddress {
        192.168.10.200
    }
}
EOF

service keepalived start
systemctl enable keepalived 

注意:
1.如果是其他机器的话，state应当修改为BACKUP,同时priority的值应当低于MASTER
2.interface需要修改为网卡的名称
3.一开始配置keepalived的时候VIP已经在某台机器了，但是随后发现无法ping通，端口也无法访问，最后发现是vrrp_strict 这个参数需要注释

13.配置kubeadm配置文件

cat << EOF > /root/init.yaml
apiVersion: kubeadm.k8s.io/v1beta2
kind: InitConfiguration
bootstrapTokens:
- groups:
  - system:bootstrappers:kubeadm:default-node-token
  token: abcdef.0123456789abcdef
  ttl: 24h0m0s
  usages:
  - signing
  - authentication
localAPIEndpoint:
  advertiseAddress: 192.168.10.210
  bindPort: 6443
nodeRegistration:
  criSocket: /var/run/dockershim.sock
  name: node210
  taints:
  - effect: NoSchedule
    key: node-role.kubernetes.io/master
---
apiVersion: kubeadm.k8s.io/v1beta2
kind: ClusterConfiguration
clusterName: kubernetes
kubernetesVersion: v1.15.1
certificatesDir: /etc/kubernetes/pki
controllerManager: {}
controlPlaneEndpoint: "192.168.10.200:8443"
imageRepository: registry.aliyuncs.com/google_containers
apiServer:
  timeoutForControlPlane: 4m0s
  certSANs:
  - "node210"
  - "node211"
  - "node212"
  - "192.168.10.210"
  - "192.168.10.211"
  - "192.168.10.212"
  - "192.168.10.212"
  - "192.168.10.200"
  - "127.0.0.1"
dns:
  type: CoreDNS
etcd:
  local:
    dataDir: /var/lib/etcd
networking:
  dnsDomain: cluster.local
  serviceSubnet: 10.253.0.0/16
  podSubnet: 172.60.0.0/16
scheduler: {}
---
apiVersion: kubeproxy.config.k8s.io/v1alpha1
kind: KubeProxyConfiguration
mode: "ipvs"
EOF

#在210上执行初始化集群
kubeadm init --config=init.yaml

执行完之后保存一下提示的信息:

To start using your cluster, you need to run the following as a regular user:

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

You should now deploy a pod network to the cluster.
Run "kubectl apply -f [podnetwork].yaml" with one of the options listed at:
  https://kubernetes.io/docs/concepts/cluster-administration/addons/

You can now join any number of control-plane nodes by copying certificate authorities
and service account keys on each node and then running the following as root:

  kubeadm join 192.168.10.200:8443 --token abcdef.0123456789abcdef \
    --discovery-token-ca-cert-hash sha256:4f542d1d54cbbf2961bed56fac7fe8a195ffef5f33f2ae699908ab0379d7f568 \
    --control-plane

Then you can join any number of worker nodes by running the following on each as root:

kubeadm join 192.168.10.200:8443 --token abcdef.0123456789abcdef \
    --discovery-token-ca-cert-hash sha256:4f542d1d54cbbf2961bed56fac7fe8a195ffef5f33f2ae699908ab0379d7f568

在210机器执行:

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

14.在210上执行将相关证书文件复制到211、212

ssh 192.168.10.211 "mkdir -p /etc/kubernetes/pki/etcd"
ssh 192.168.10.212 "mkdir -p /etc/kubernetes/pki/etcd"
scp -r /etc/kubernetes/admin.conf 192.168.10.211:/etc/kubernetes/admin.conf
scp -r /etc/kubernetes/admin.conf 192.168.10.212:/etc/kubernetes/admin.conf
scp -r /etc/kubernetes/pki/{ca.*,sa.*,front*}  192.168.10.211:/etc/kubernetes/pki/
scp -r /etc/kubernetes/pki/{ca.*,sa.*,front*}  192.168.10.212:/etc/kubernetes/pki/
scp -r /etc/kubernetes/pki/etcd/ca.*  192.168.10.211:/etc/kubernetes/pki/etcd/ 
scp -r /etc/kubernetes/pki/etcd/ca.*  192.168.10.212:/etc/kubernetes/pki/etcd/ 

15.在211、212机器上执行,下面这段就是在初始化集群时生成的提示，211，212完成master部署

 kubeadm join 192.168.10.200:8443 --token abcdef.0123456789abcdef \
    --discovery-token-ca-cert-hash sha256:4f542d1d54cbbf2961bed56fac7fe8a195ffef5f33f2ae699908ab0379d7f568 \
    --control-plane
mkdir -p $HOME/.kube
sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
sudo chown $(id -u):$(id -g) $HOME/.kube/config

16.在213机器上执行，以加入节点

kubeadm join 192.168.10.200:8443 --token abcdef.0123456789abcdef \
    --discovery-token-ca-cert-hash sha256:4f542d1d54cbbf2961bed56fac7fe8a195ffef5f33f2ae699908ab0379d7f568

17.安装网络，我们这里使用calico，注意这里的网段需要对应初始网络配置文件中的podSubnet

curl -s https://docs.projectcalico.org/v3.7/manifests/calico.yaml -O
sed 's#192.168.0.0/16#172.60.0.0/16#g' calico.yaml |kubectl apply -f -

如果需要使用flannel,则

curl -s https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml -O
sed 's#0.244.0.0/16#172.60.0.0/16#g' kube-flannel.yml|kubectl apply -f -

18.查看节点

[root@node210 ~]# kubectl get nodes
NAME      STATUS   ROLES    AGE    VERSION
node210   Ready    master   3h7m   v1.15.1
node211   Ready    master   175m   v1.15.1
node212   Ready    master   176m   v1.15.1
node213   Ready    <none>   129m   v1.15.1

19.测试服务

kubectl create deployment nginx --image=nginx
kubectl expose deployment nginx --port=80 --type=NodePort
[root@node210 ~]# kubectl get svc
NAME          TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)    AGE
nginx       ClusterIP   10.253.103.72    <none>        80:30230/TCP   151m
kubernetes    ClusterIP   10.253.0.1       <none>        443/TCP    3h9m

curl 192.168.10.210:90230如果正常即可

20.安装kubernetes-dashboard

wget https://raw.githubusercontent.com/kubernetes/dashboard/v1.10.1/src/deploy/recommended/kubernetes-dashboard.yaml
sed  's#k8s.gcr.io#gcrxio#g' kubernetes-dashboard.yaml  |kubectl apply -f -
cat <<EOF > dashboard-admin.yaml
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1beta1
metadata:
  name: admin
  annotations:
    rbac.authorization.kubernetes.io/autoupdate: "true"
roleRef:
  kind: ClusterRole
  name: cluster-admin
  apiGroup: rbac.authorization.k8s.io
subjects:
- kind: ServiceAccount
  name: admin
  namespace: kube-system
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: admin
  namespace: kube-system
  labels:
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
EOF
kubectl apply -f dashboard-admin.yaml

#在210上执行添加NAT

echo "iptables -t nat -A POSTROUTING  -d 10.253.0.0/16 -j MASQUERADE">>/etc/rc.local
chmod +x /etc/rc.local
iptables -t nat -A POSTROUTING  -d 10.253.0.0/16 -j MASQUERADE

#查看SVC IP

[root@node210 ~]# kubectl get svc -nkube-system
NAME                   TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)                  AGE
kube-dns               ClusterIP   10.253.0.10      <none>        53/UDP,53/TCP,9153/TCP   3h23m
kubernetes-dashboard   ClusterIP   10.253.165.188   <none>        443/TCP                  29s

#查看secret

kubectl describe secret/$(kubectl get secret -nkube-system|grep admin-token|awk '{print $1}') -nkube-system

#在本地机器添加静态路由

route add 10.253.0.0 mask 255.255.0.0 192.168.10.210 -p

#查看secret

kubectl describe secret/$(kubectl get secret -nkube-system|grep admin-token|awk '{print $1}') -nkube-system

21.检查ETCD服务

docker exec -it $(docker ps |grep etcd_etcd|awk '{print $1}') sh
etcdctl --endpoints=https://192.168.10.212:2379 --ca-file=/etc/kubernetes/pki/etcd/ca.crt --cert-file=/etc/kubernetes/pki/etcd/server.crt --key-file=/etc/kubernetes/pki/etcd/server.key member list
etcdctl --endpoints=https://192.168.10.212:2379 --ca-file=/etc/kubernetes/pki/etcd/ca.crt --cert-file=/etc/kubernetes/pki/etcd/server.crt --key-file=/etc/kubernetes/pki/etcd/server.key cluster-health

22.如果配置出错如何重置集群呢?

kubeadm reset
ipvsadm --clear
rm -rf /etc/kubernetes/
service kubelet stop
docker stop $(docker ps -a |awk '{print $1}')
docker rm $(docker ps -a -q)

23.其他问题
集群跑起来后，发现210、211、212上无法跑容器，那是因为在初始集群参数的时候设置了污点，如果要去除污点

#以下是将211、212取消污点
kubectl taint nodes node211 node-role.kubernetes.io/master-
kubectl taint nodes node212 node-role.kubernetes.io/master-