高可用K8S构建3master+3node+keepalived+haproxy

12. 高可用的K8S集群构建

安装准备

系统：

CentOS-7-x86_64-Minimal-1810.iso

虚拟机配置：

网络：

虚拟机网络使用本地网卡共享到VMnet1，虚拟机使用VMnet1。

网卡配置

VMnet1配置：

vmware网络配置：

关闭DHCP，网段改为192.168.66.0

安装过程略过，最小化安装，全部默认，设置root密码。

12.1 系统初始化

#设置系统主机名以及 Host 文件的相互解析，其他机器同理

hostnamectl set-hostname k8s-master01

echo "192.168.66.10 k8s-master01

192.168.66.11 k8s-master02
192.168.66.12 k8s-master03
192.168.66.20 k8s-node01
192.168.66.21 k8s-node02
192.168.66.22 k8s-node03
192.168.66.100 k8s-harbor" >> /etc/hosts

vi /etc/selinux/config
SELINUX=disabled

#安装依赖包

yum -y install yum-utils

yum-config-manager --add-repo http://mirrors.aliyun.com/repo/Centos-7.repo

yum install -y conntrack ntpdate ntp ipvsadm ipset jq iptables curl sysstat libseccomp wget vim net-tools git

#设置防火墙为 Iptables 并设置空规则

systemctl stop firewalld && systemctl disable firewalld

yum -y install iptables-services && systemctl start iptables && systemctl enable iptables && iptables -F && service iptables save

#关闭 SELINUX

swapoff -a && sed -i '/ swap / s/^\(.*\)$/#\1/g' /etc/fstab
setenforce 0 && sed -i 's/^SELINUX=.*/SELINUX=disabled/' /etc/selinux/config

#调整内核参数,对于 K8S

cat > kubernetes.conf <<EOF
net.bridge.bridge-nf-call-iptables=1
net.bridge.bridge-nf-call-ip6tables=1
net.ipv4.ip_forward=1
net.ipv4.tcp_tw_recycle=0
vm.swappiness=0 # 禁止使用 swap 空间,只有当系统 OOM 时才允许使用它
vm.overcommit_memory=1 # 不检查物理内存是否够用
vm.panic_on_oom=0 # 开启 OOM
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.netfilter.nf_conntrack_max=2310720
EOF

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

# 调整系统时区

# 设置系统时区为 中国/上海
timedatectl set-timezone Asia/Shanghai

# 将当前的 UTC 时间写入硬件时钟
timedatectl set-local-rtc 0

# 重启依赖于系统时间的服务
systemctl restart rsyslog
systemctl restart crond

#关闭系统不需要服务
systemctl stop postfix && systemctl disable postfix

#设置 rsyslogd 和 systemd journald
mkdir /var/log/journal # 持久化保存日志的目录
mkdir /etc/systemd/journald.conf.d


cat > /etc/systemd/journald.conf.d/99-prophet.conf <<EOF
[Journal]
# 持久化保存到磁盘
Storage=persistent
# 压缩历史日志
Compress=yes
SyncIntervalSec=5m
RateLimitInterval=30s
RateLimitBurst=1000
# 最大占用空间 10G
SystemMaxUse=10G
# 单日志文件最大 200M
SystemMaxFileSize=200M
# 日志保存时间 2 周
MaxRetentionSec=2week
# 不将日志转发到 syslog
ForwardToSyslog=no
EOF



systemctl restart systemd-journald

#升级系统内核为 4.44
#CentOS 7.x 系统自带的 3.10.x 内核存在一些 Bugs,导致运行的 Docker、Kubernetes 不稳定,例如:

rpm -Uvh http://www.elrepo.org/elrepo-release-7.0-3.el7.elrepo.noarch.rpm

# 安装完成后检查 /boot/grub2/grub.cfg 中对应内核 menuentry 中是否包含 initrd16 配置,如果没有,再安装
一次!

yum --enablerepo=elrepo-kernel install -y kernel-lt

# 设置开机从新内核启动

grub2-set-default "CentOS Linux (4.4.248-1.el7.elrepo.x86_64) 7 (Core)"

# CentOS Linux (4.4.248-1.el7.elrepo.x86_64) 7 (Core)

# 重启后安装内核源文件

yum --enablerepo=elrepo-kernel install kernel-lt-devel-$(uname -r) kernel-lt-headers-$(uname -r)

# 关闭 NUMA

cp /etc/default/grub{,.bak}
vim /etc/default/grub # 在 GRUB_CMDLINE_LINUX 一行添加 `numa=off`

# 参数,如下所示:
# diff /etc/default/grub.bak /etc/default/grub
#< GRUB_CMDLINE_LINUX="crashkernel=auto rd.lvm.lv=centos/root rhgb quiet"

cp /boot/grub2/grub.cfg{,.bak}
grub2-mkconfig -o /boot/grub2/grub.cfg

------------------------------

12.2 Kubeadm 部署安装

#所有节点

# kube-proxy开启ipvs的前置条件

modprobe br_netfilter
cat > /etc/sysconfig/modules/ipvs.modules <<EOF
#!/bin/bash
modprobe -- ip_vs
modprobe -- ip_vs_rr
modprobe -- ip_vs_wrr
modprobe -- ip_vs_sh
modprobe -- nf_conntrack_ipv4
EOF
 

chmod 755 /etc/sysconfig/modules/ipvs.modules && bash /etc/sysconfig/modules/ipvs.modules && lsmod | grep -e ip_vs -e nf_conntrack_ipv4

# 安装 Docker 软件

yum-config-manager \
--add-repo http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo


yum install -y yum-utils device-mapper-persistent-data lvm2


yum update -y && yum install -y docker-ce

 

reboot

grub2-set-default "CentOS Linux (4.4.248-1.el7.elrepo.x86_64) 7 (Core)"

reboot

# 创建 /etc/docker 目录

mkdir /etc/docker

# 配置 daemon.

cat > /etc/docker/daemon.json <<EOF
{
"exec-opts": ["native.cgroupdriver=systemd"],
"log-driver": "json-file",
"log-opts": {
"max-size": "100m"
}
}
EOF

mkdir -p /etc/systemd/system/docker.service.d

# 重启docker服务

systemctl daemon-reload && systemctl restart docker && systemctl enable docker

# master1:
# 在主节点启动 Haproxy 与 Keepalived 容器
# 导入脚本 > 运行 > 查看可用节点

mkdir -p /usr/local/kubernetes/install
cd !$

yum install lrzsz -y

# 导入

haproxy.tar
keepalived.tar
kubeadm-basic.images.tar.gz
load-images.sh
start.keep.tar.gz
 

tar zxvf kubeadm-basic.images.tar.gz
cat load-images.sh 

#!/bin/bash
cd /usr/local/kubernetes/install/kubeadm-basic.images
ls /usr/local/kubernetes/install/kubeadm-basic.images | grep -v load-images.sh > /tmp/k8s-images.txt
for i in $( cat /tmp/k8s-images.txt )
do
docker load -i $i
done
rm -rf /tmp/k8s-images.txt

 
chmod a+x load-images.sh 

./load-images.sh

docker load -i haproxy.tar

docker load -i keepalived.tar

tar zxvf start.keep.tar.gz

# 修改haproxy配置文件

vim data/lb/etc/haproxy.cfg

# 确保先负载到第一个上，就先填写一个IP ，之后再加全

vim data/lb/start-haproxy.sh

vim data/lb/start-keepalived.sh

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 -y install kubeadm-1.15.1 kubectl-1.15.1 kubelet-1.15.1

systemctl enable kubelet.service

# 初始化主节点

mkdir images
mv * images/
cd images

kubeadm config print init-defaults > kubeadm-config.yaml

vim kubeadm-config.yaml

# 在master02 03创建目录

mkdir -p /usr/local/kubernetes/install/images

# 然后master01:

scp -r * root@k8s-master02:/usr/local/kubernetes/install/images

scp -r * root@k8s-master03:/usr/local/kubernetes/install/images

# master01:

mv data/ /
cd /data/lb
ls

./start-haproxy.sh

netstat -antlup | grep 6444

./start-keepalived.sh

ip addr show
 

kubeadm init --config=kubeadm-config.yaml --experimental-upload-certs | tee kubeadm-init.log

mkdir -p $HOME/.kube

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

cat ~/.kube/config

# 可以这这里看到IP信息

kubectl get node

# master02 03

 

# 初始化主节点

cd /usr/local/kubernetes/install/images

vim kubeadm-config.yaml




#加入节点


kubeadm join 192.168.66.100:6444 --token abcdef.0123456789abcdef \
--discovery-token-ca-cert-hash sha256:824dd354a9785a0ca2c624ffcee1cea77b4931dbf82a123d4a5d32bffd6f4cf4 \
--control-plane --certificate-key 9d6240640a9164e5161cededde0527e94ecdc8044c0c45b5565bf2662ac7120a

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 node

# master03加入后：

kubectl get pod -n kube-system

# 状态都还是notready 修改haproxy

vim /data/lb/etc/haproxy.cfg

docker ps

docker rm -f HAProxy-K8S && bash /data/lb/start-haproxy.sh

scp etc/haproxy.cfg root@k8s-master02:/data/lb/etc/

master02 03:

docker rm -f HAProxy-K8S && bash /data/lb/start-haproxy.sh

部署flannel网络

#master 01

cd /usr/local/kubernetes/install/images

echo "199.232.68.133 raw.githubusercontent.com" >> /etc/hosts

wget https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml

kubectl get node

# 把master01关机

shutdown -h now

master02\03:


# 多次尝试

kubectl get node

修改地址

vim ~/.kube/config

修改成自己的IP

kubectl get node

# 启动master01

----------------

查看集群状态:

kubectl get endpoints kube-controller-manager --namespace=kube-system -o yaml

controller-manager的工作节点是master02，其他两个阻塞状态

kubectl get endpoints kube-scheduler --namespace=kube-system -o yaml

kube-scheduler是matser03

#Etcd 集群状态查看

kubectl -n kube-system exec etcd-k8s-master01 -- etcdctl \
--endpoints=https://192.168.66.10:2379 \
--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

#指定kube-system名称空间运行 etcd-k8s-master01容器，执行容器内部命令etcdctl指定访问地址66.10:2379端口（etcd客户端连接端口 :2379内部互联端口(监听节点间通信) :2380）,指定CA证书和SERVER的证书、秘钥，检查集群健康。

# 加入Node节点

# node :

# 需要node提前装完docker，然后装K8s

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 -y install kubeadm-1.15.1 kubectl-1.15.1 kubelet-1.15.1
systemctl enable kubelet.service

mkdir -p /usr/local/kubernetes/install/images/

master01 : scp -r kubeadm-basic.images load-images.sh root@192.168.66.20:/usr/local/kubernetes/install/images/

cd /usr/local/kubernetes/install/images/

vim load-images.sh

#!/bin/bash

cd /usr/local/kubernetes/install/images/kubeadm-basic.images
ls /usr/local/kubernetes/install/images/kubeadm-basic.images | grep -v load-images.sh > /tmp/k8s-images.txt

for i in $( cat /tmp/k8s-images.txt )
do
docker load -i $i
done

rm -rf /tmp/k8s-images.txt

./load-images.sh

master01:cat /usr/local/kubernetes/install/images/kubeadm-init.log