12.高可用的k8s集群构建
方案一
方案二
BRZEE 瑞云的k8s 实现了高可用
初始化系统(所有节点)
设置系统主机名以及Host文件的相互解析
hostnamectl set-hostname k8s-master01
hostnamectl set-hostname k8s-master02
hostnamectl set-hostname k8s-master03
192.168.66.110 k8s-master01
192.168.66.111 k8s-master02
192.168.66.112 k8s-master03
安装依赖包
yum install -y conntrack ntpdate ntp ipvsadm ipset jq iptables curl sysstat libseccomp wgetvimnet-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
查看系统可用内核
yum --disablerepo="*" --enablerepo="elrepo-kernel" list available
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
# 查看可用内核
awk -F \' '$1=="menuentry " {print i++ " : " $2}' /etc/grub2.cfg
# 设置开机从新内核启动
grub2-set-default "CentOS Linux (4.4.248-1.el7.elrepo.x86_64) 7 (Core)"
# 重启后安装内核源文件
yum --enablerepo=elrepo-kernel install kernel-lt-devel-$(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
6c6
< GRUB_CMDLINE_LINUX="crashkernel=auto rd.lvm.lv=centos/root rhgb quiet"
---
> GRUB_CMDLINE_LINUX="crashkernel=auto rd.lvm.lv=centos/root rhgb quiet numa=off"
cp /boot/grub2/grub.cfg{,.bak}
grub2-mkconfig -o /boot/grub2/grub.cfg
kubeadm部署安装
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
sudo yum install -y yum-utils device-mapper-persistent-data lvm2
sudo yum-config-manager \
--add-repo https://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo
查看docker版本
yum list docker-ce --showduplicates | sort -r
安装指定版本
yum install -y docker-ce-18.09.9-3.el7
yum update -y && yum install -y docker-ce
## 创建 /etc/docker 目录
mkdir /etc/docker
# 配置 daemon.
cat > /etc/docker/daemon.json <<EOF
{
"registry-mirrors": ["https://f4573wwn.mirror.aliyuncs.com"],
"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
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/kubeadm-basic.images
docker load -i haproxy.tar
docker load -i keepalived.tar
tar -zxvf kubeadm-basic.images.tar.gz
更改 vim haproxy.cfg 脚本 ，更改为集群的ip地址
log global
balance roundrobin
server rancher01 192.168.6.110:6443 #第一个节点初始化时，需要删除下面两个
server rancher02 192.168.6.111:6443
server rancher03 192.168.6.112:6443
更改start-haproxy.sh 为集群地址
#!/bin/bash
MasterIP1=192.168.66.110
MasterIP2=192.168.66.111
MasterIP3=192.168.66.112
MasterPort=6443
docker run -d --restart=always --name HAProxy-K8S -p 6444:6444 \
-e MasterIP1=$MasterIP1 \
-e MasterIP2=$MasterIP2 \
-e MasterIP3=$MasterIP3 \
-e MasterPort=$MasterPort \
-v /data/lb/etc/haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg \
wise2c/haproxy-k8s
更改vim start-keepalived.sh VIP地址和网卡名称
#!/bin/bash
VIRTUAL_IP=192.168.6.120
INTERFACE=ens33
NETMASK_BIT=24
CHECK_PORT=6444
RID=10
VRID=160
MCAST_GROUP=224.0.0.18
docker run -itd --restart=always --name=Keepalived-K8S \
--net=host --cap-add=NET_ADMIN \
-e VIRTUAL_IP=$VIRTUAL_IP \
-e INTERFACE=$INTERFACE \
-e CHECK_PORT=$CHECK_PORT \
-e RID=$RID \
-e VRID=$VRID \
-e NETMASK_BIT=$NETMASK_BIT \
-e MCAST_GROUP=$MCAST_GROUP \
wise2c/keepalived-k8s
安装kubeadm（主从配置）
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
systemctl start kubelet.service
初始化主节点
kubeadm config print init-defaults > kubeadm-config.yaml
更改节点配置文件
apiVersion: kubeadm.k8s.io/v1beta2
bootstrapTokens:
- groups:
- system:bootstrappers:kubeadm:default-node-token
token: abcdef.0123456789abcdef
ttl: 24h0m0s
usages:
- signing
- authentication
kind: InitConfiguration
localAPIEndpoint:
advertiseAddress: 192.168.66.110
bindPort: 6443
nodeRegistration:
criSocket: /var/run/dockershim.sock
name: k8s-master01
taints:
- effect: NoSchedule
key: node-role.kubernetes.io/master
---
apiServer:
timeoutForControlPlane: 4m0s
apiVersion: kubeadm.k8s.io/v1beta2
certificatesDir: /etc/kubernetes/pki
clusterName: kubernetes
controlPlaneEndpoint: "192.168.66.120:6444"
controllerManager: {}
dns:
type: CoreDNS
etcd:
local:
dataDir: /var/lib/etcd
imageRepository: k8s.gcr.io
kind: ClusterConfiguration
kubernetesVersion: v1.15.1
networking:
dnsDomain: cluster.local
podSubnet: "10.244.0.0/16"
serviceSubnet: 10.96.0.0/12
scheduler: {}
---
apiVersion: kubeproxy.config.k8s.io/v1alpha1
kind: KubeProxyConfiguration
featureGates:
SupportIPVSProxyMode: true
mode: ipvs
初始化集群
kubeadm init --config=kubeadm-config.yaml --experimental-upload-certs \
| tee kubeadm-init.log
加入集群状态
kubeadm join 192.168.66.120:6444 --token abcdef.0123456789abcdef \
--discovery-token-ca-cert-hash sha256:407d8af1d1dbd6dc870513e9410827af90652bb6f54b1676d97ae811bc07f51c \
--control-plane --certificate-key 7730556e99bb54bd038321497e674ee7745e999eee425f6849c181b8c5d8873f
vim /root/.kube/config
将VIP地址改为本机地址
加入主节点以及其余工作节点
执行安装日志中的加入命令即可
ETCD集群状态查看
kubectl -n kube-system exec etcd-k8s-master01 -- etcdctl \
--endpoints=https://192.168.66.110:2379 \
--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
kubectl get endpoints kube-controller-manager --namespace=kube-system -o yaml
kubectl get endpoints kube-scheduler --namespace=kube-system -o yaml
部署网络
kubectl apply -f kube-flannel.yml
将master也作为node使用
1.让 Master 也当作 Node 使用
kubectl taint node --all node-role.kubernetes.io/master-
有提示可以忽略
2.将 Master 恢复成 Master Only 状态
kubectl taint node --all node-role.kubernetes.io/master="":NoSchedule
