K8S二进制安装
基本环境配置
高可用Kubernetes集群规划
| 主机名 | IP地址 | 说明 |
|---|---|---|
| k8s-master01 ~ 03 | 192.168.8.15 ~ 17 | master节点* 3 |
| k8s-node01 ~ 02 | 192.168.8.18 ~ 19 | worker节点* 2 |
| k8s-master-lb | 192.168.8.20 | keepalived虚拟IP |
| 配置信息 | 备注 |
|---|---|
| 系统版本 | ubuntu |
| Docker版本 | 20.10.x |
| Pod网段 | 172.16.0.0/16 |
| Service网段 | 10.96.0.0/16 |
所有节点更改主机名
hostnamectl set-hostname k8s-master01
hostnamectl set-hostname k8s-master02
hostnamectl set-hostname k8s-master03
hostnamectl set-hostname k8s-node01
hostnamectl set-hostname k8s-node02
所有节点配置hosts文件
cat << EOF >> /etc/hosts
192.168.8.15 k8s-master01
192.168.8.16 k8s-master02
192.168.8.17 k8s-master03
192.168.8.18 k8s-node01
192.168.8.19 k8s-node02
192.168.8.20 k8s-master-lb
EOF
所有节点apt源
deb https://mirrors.aliyun.com/ubuntu/ jammy main restricted universe multiverse
deb-src https://mirrors.aliyun.com/ubuntu/ jammy main restricted universe multiverse
deb https://mirrors.aliyun.com/ubuntu/ jammy-security main restricted universe multiverse
deb-src https://mirrors.aliyun.com/ubuntu/ jammy-security main restricted universe multiverse
deb https://mirrors.aliyun.com/ubuntu/ jammy-updates main restricted universe multiverse
deb-src https://mirrors.aliyun.com/ubuntu/ jammy-updates main restricted universe multiverse
# deb https://mirrors.aliyun.com/ubuntu/ jammy-proposed main restricted universe multiverse
# deb-src https://mirrors.aliyun.com/ubuntu/ jammy-proposed main restricted universe multiverse
deb https://mirrors.aliyun.com/ubuntu/ jammy-backports main restricted universe multiverse
deb-src https://mirrors.aliyun.com/ubuntu/ jammy-backports main restricted universe multiverse
所有节点安装必备软件包
apt install wget jq psmisc vim net-tools telnet lvm2 git -y
所有节点关闭swap分区，fstab注释swap
swapoff -a && sysctl -w vm.swappiness=0
sed -ri '/^[^#]*swap/s@^@#@' /etc/fstab
cat /etc/fstab
所有节点同步时间，安装ntpdate
apt install ntpdate -y
所有节点同步时间。时间同步配置如下
ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime
echo 'Asia/Shanghai' >/etc/timezone
ntpdate time2.aliyun.com
# 加入到crontab
*/5 * * * * /usr/sbin/ntpdate time2.aliyun.com
所有节点配置limit
ulimit -SHn 65535
vim /etc/security/limits.conf
# 末尾添加如下内容
* soft nofile 65536
* hard nofile 131072
* soft nproc 65535
* hard nproc 655350
* soft memlock unlimited
* hard memlock unlimited
Master01节点免密钥登录其他节点，安装过程中生成配置文件和证书均在Master01上操作，集群管理也在Master01上操作
ssh-keygen -t rsa
Master01配置免密码登录其他节点
for i in k8s-master01 k8s-master02 k8s-master03 k8s-node01 k8s-node02;do ssh-copy-id -i .ssh/id_rsa.pub $i;done
Master01下载安装文件
cd /root/ ; git clone https://gitee.com/dukuan/k8s-ha-install.git
所有节点安装ipvsadm
sudo apt install ipvsadm ipset sysstat conntrack libseccomp2 -y
所有节点配置ipvs模块
modprobe -- ip_vs
modprobe -- ip_vs_rr
modprobe -- ip_vs_wrr
modprobe -- ip_vs_sh
modprobe -- nf_conntrack
vim /etc/modules-load.d/ipvs.conf
# 加入以下内容
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
ip_vs_sh
nf_conntrack
ip_tables
ip_set
xt_set
ipt_set
ipt_rpfilter
ipt_REJECT
ipip
然后执行systemctl enable --now systemd-modules-load.service即可
所有节点检查是否加载
lsmod | grep -e ip_vs -e nf_conntrack
nf_conntrack_ipv4 16384 23
nf_defrag_ipv4 16384 1 nf_conntrack_ipv4
nf_conntrack 135168 10 xt_conntrack,nf_conntrack_ipv6,nf_conntrack_ipv4,nf_nat,nf_nat_ipv6,ipt_MASQUERADE,nf_nat_ipv4,xt_nat,nf_conntrack_netlink,ip_vs
所有节点开启一些k8s集群中必须的内核参数，所有节点配置k8s内核
cat <<EOF > /etc/sysctl.d/k8s.conf
net.ipv4.ip_forward = 1
net.bridge.bridge-nf-call-iptables = 1
net.bridge.bridge-nf-call-ip6tables = 1
fs.may_detach_mounts = 1
vm.overcommit_memory=1
net.ipv4.conf.all.route_localnet = 1
vm.panic_on_oom=0
fs.inotify.max_user_watches=89100
fs.file-max=52706963
fs.nr_open=52706963
net.netfilter.nf_conntrack_max=2310720
net.ipv4.tcp_keepalive_time = 600
net.ipv4.tcp_keepalive_probes = 3
net.ipv4.tcp_keepalive_intvl =15
net.ipv4.tcp_max_tw_buckets = 36000
net.ipv4.tcp_tw_reuse = 1
net.ipv4.tcp_max_orphans = 327680
net.ipv4.tcp_orphan_retries = 3
net.ipv4.tcp_syncookies = 1
net.ipv4.tcp_max_syn_backlog = 16384
net.ipv4.ip_conntrack_max = 65536
net.ipv4.tcp_max_syn_backlog = 16384
net.ipv4.tcp_timestamps = 0
net.core.somaxconn = 16384
EOF
sysctl --system
所有节点配置完内核后，重启服务器
reboot
lsmod | grep --color=auto -e ip_vs -e nf_conntrack
所有节点开启一些k8s集群中必须的内核参数，所有节点配置k8s内核
cat <<EOF > /etc/sysctl.d/k8s.conf
net.ipv4.ip_forward = 1
net.bridge.bridge-nf-call-iptables = 1
net.bridge.bridge-nf-call-ip6tables = 1
fs.may_detach_mounts = 1
vm.overcommit_memory=1
net.ipv4.conf.all.route_localnet = 1
vm.panic_on_oom=0
fs.inotify.max_user_watches=89100
fs.file-max=52706963
fs.nr_open=52706963
net.netfilter.nf_conntrack_max=2310720
net.ipv4.tcp_keepalive_time = 600
net.ipv4.tcp_keepalive_probes = 3
net.ipv4.tcp_keepalive_intvl =15
net.ipv4.tcp_max_tw_buckets = 36000
net.ipv4.tcp_tw_reuse = 1
net.ipv4.tcp_max_orphans = 327680
net.ipv4.tcp_orphan_retries = 3
net.ipv4.tcp_syncookies = 1
net.ipv4.tcp_max_syn_backlog = 16384
net.ipv4.ip_conntrack_max = 65536
net.ipv4.tcp_max_syn_backlog = 16384
net.ipv4.tcp_timestamps = 0
net.core.somaxconn = 16384
EOF
sysctl --system
所有节点配置完内核后，重启服务器，保证重启后内核依旧加载
reboot
lsmod | grep --color=auto -e ip_vs -e nf_conntrack
安装containerd
所有节点
# step 1: 安装必要的一些系统工具
sudo apt-get update
sudo apt-get install ca-certificates curl gnupg -y
# step 2: 信任 Docker 的 GPG 公钥
sudo install -m 0755 -d /etc/apt/keyrings
curl -fsSL https://mirrors.aliyun.com/docker-ce/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg
sudo chmod a+r /etc/apt/keyrings/docker.gpg
# Step 3: 写入软件源信息
echo \
"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://mirrors.aliyun.com/docker-ce/linux/ubuntu \
"$(. /etc/os-release && echo "$VERSION_CODENAME")" stable" | \
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
# Step 4: 安装Docker
sudo apt-get update
sudo apt-get install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin -y
所有节点首先配置Containerd所需的模块（所有节点）
cat <<EOF | sudo tee /etc/modules-load.d/containerd.conf
overlay
br_netfilter
EOF
所有节点加载模块
modprobe -- overlay
modprobe -- br_netfilter
所有节点，配置Containerd所需的内核
cat <<EOF | sudo tee /etc/sysctl.d/99-kubernetes-cri.conf
net.bridge.bridge-nf-call-iptables = 1
net.ipv4.ip_forward = 1
net.bridge.bridge-nf-call-ip6tables = 1
EOF
所有节点加载内核
sysctl --system
所有节点配置Containerd的配置文件
mkdir -p /etc/containerd
containerd config default | tee /etc/containerd/config.toml
将Containerd的Cgroup改为Systemd：
vim /etc/containerd/config.toml
找到containerd.runtimes.runc.options，添加SystemdCgroup = true
所有节点将sandbox_image的Pause镜像改成符合自己版本的地址registry.cn-hangzhou.aliyuncs.com/google_containers/pause:3.9
所有节点启动Containerd，并配置开机自启动
systemctl daemon-reload
systemctl enable --now containerd
systemctl status containerd
所有节点配置crictl客户端连接的运行时位置
cat > /etc/crictl.yaml <<EOF
runtime-endpoint: unix:///run/containerd/containerd.sock
image-endpoint: unix:///run/containerd/containerd.sock
timeout: 10
debug: false
EOF
etcd安装
Master01下载kubernetes安装包（1.28.15需要更改为你看到的最新版本）
https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.28.md#server-binaries
wget https://dl.k8s.io/v1.28.15/kubernetes-server-linux-amd64.tar.gz
master01下载etcd的安装包
wget https://github.com/etcd-io/etcd/releases/download/v3.5.7/etcd-v3.5.7-linux-amd64.tar.gz
解压kubernetes安装文件
tar -xf kubernetes-server-linux-amd64.tar.gz --strip-components=3 -C /usr/local/bin kubernetes/server/bin/kube{let,ctl,-apiserver,-controller-manager,-scheduler,-proxy}
解压etcd安装文件
tar -zxvf etcd-v3.5.7-linux-amd64.tar.gz --strip-components=1 -C /usr/local/bin etcd-v3.5.7-linux-amd64/etcd{,ctl}
版本查看
kubelet --version
Kubernetes v1.28.15
etcdctl version
etcdctl version: 3.5.7
API version: 3.5
将组件发送到其他节点
MasterNodes='k8s-master02 k8s-master03'
WorkNodes='k8s-node01 k8s-node02'
for NODE in $MasterNodes; do echo $NODE; scp /usr/local/bin/kube{let,ctl,-apiserver,-controller-manager,-scheduler,-proxy} $NODE:/usr/local/bin/; scp /usr/local/bin/etcd* $NODE:/usr/local/bin/; done
for NODE in $WorkNodes; do scp /usr/local/bin/kube{let,-proxy} $NODE:/usr/local/bin/ ; done
Master01节点切换到1.28.x分支
cd /root/k8s-ha-install && git checkout manual-installation-v1.28.x
生成证书工具
二进制安装最关键步骤
master01下载生成证书工具
下面的可能无法下载 https://github.com/cloudflare/cfssl/releases
wget "https://pkg.cfssl.org/R1.2/cfssl_linux-amd64" -O /usr/local/bin/cfssl
wget "https://pkg.cfssl.org/R1.2/cfssljson_linux-amd64" -O /usr/local/bin/cfssljson
chmod +x /usr/local/bin/cfssl /usr/local/bin/cfssljson
etcd证书
所有Master节点创建etcd证书目录
mkdir /etc/etcd/ssl -p
所有节点创建kubernetes相关目录
mkdir -p /etc/kubernetes/pki
Master01节点生成etcd证书
生成证书的CSR文件：证书签名请求文件，配置了一些域名、公司、单位
cd /root/k8s-ha-install/pki
# 生成etcd CA证书和CA证书的key
cfssl gencert -initca etcd-ca-csr.json | cfssljson -bare /etc/etcd/ssl/etcd-ca
cfssl gencert \
-ca=/etc/etcd/ssl/etcd-ca.pem \
-ca-key=/etc/etcd/ssl/etcd-ca-key.pem \
-config=ca-config.json \
-hostname=127.0.0.1,k8s-master01,k8s-master02,k8s-master03,192.168.8.15,192.168.8.16,192.168.8.17 \
-profile=kubernetes \
etcd-csr.json | cfssljson -bare /etc/etcd/ssl/etcd
将证书复制到其他节点
MasterNodes='k8s-master02 k8s-master03'
WorkNodes='k8s-node01 k8s-node02'
for NODE in $MasterNodes; do
ssh $NODE "mkdir -p /etc/etcd/ssl"
for FILE in etcd-ca-key.pem etcd-ca.pem etcd-key.pem etcd.pem; do
scp /etc/etcd/ssl/${FILE} $NODE:/etc/etcd/ssl/${FILE}
done
done
k8s证书
Master01生成kubernetes证书
cd /root/k8s-ha-install/pki
cfssl gencert -initca ca-csr.json | cfssljson -bare /etc/kubernetes/pki/ca
10.96.0.是k8s service的网段，如果说需要更改k8s service网段，那就需要更改10.96.0.1
如果不是高可用，就不要用二进制了
cfssl gencert -ca=/etc/kubernetes/pki/ca.pem -ca-key=/etc/kubernetes/pki/ca-key.pem -config=ca-config.json -hostname=10.96.0.1,192.168.8.20,127.0.0.1,kubernetes,kubernetes.default,kubernetes.default.svc,kubernetes.default.svc.cluster,kubernetes.default.svc.cluster.local,192.168.8.15,192.168.8.16,192.168.8.17 -profile=kubernetes apiserver-csr.json | cfssljson -bare /etc/kubernetes/pki/apiserver
生成apiserver的聚合证书。Requestheader-client-xxx requestheader-allowwd-xxx:aggerator
cfssl gencert -initca front-proxy-ca-csr.json | cfssljson -bare /etc/kubernetes/pki/front-proxy-ca
cfssl gencert -ca=/etc/kubernetes/pki/front-proxy-ca.pem -ca-key=/etc/kubernetes/pki/front-proxy-ca-key.pem -config=ca-config.json -profile=kubernetes front-proxy-client-csr.json | cfssljson -bare /etc/kubernetes/pki/front-proxy-client
成controller-manage的证书
cfssl gencert \
-ca=/etc/kubernetes/pki/ca.pem \
-ca-key=/etc/kubernetes/pki/ca-key.pem \
-config=ca-config.json \
-profile=kubernetes \
manager-csr.json | cfssljson -bare /etc/kubernetes/pki/controller-manager
# 注意，如果不是高可用集群，192.168.8.20:8443改为master01的地址，8443改为apiserver的端口，默认是6443
# set-cluster：设置一个集群项，
kubectl config set-cluster kubernetes \
--certificate-authority=/etc/kubernetes/pki/ca.pem \
--embed-certs=true \
--server=https://192.168.8.20:8443 \
--kubeconfig=/etc/kubernetes/controller-manager.kubeconfig
# 设置一个环境项，一个上下文
kubectl config set-context system:kube-controller-manager@kubernetes \
--cluster=kubernetes \
--user=system:kube-controller-manager \
--kubeconfig=/etc/kubernetes/controller-manager.kubeconfig
# set-credentials 设置一个用户项
kubectl config set-credentials system:kube-controller-manager \
--client-certificate=/etc/kubernetes/pki/controller-manager.pem \
--client-key=/etc/kubernetes/pki/controller-manager-key.pem \
--embed-certs=true \
--kubeconfig=/etc/kubernetes/controller-manager.kubeconfig
# 使用某个环境当做默认环境
kubectl config use-context system:kube-controller-manager@kubernetes \
--kubeconfig=/etc/kubernetes/controller-manager.kubeconfig
cfssl gencert \
-ca=/etc/kubernetes/pki/ca.pem \
-ca-key=/etc/kubernetes/pki/ca-key.pem \
-config=ca-config.json \
-profile=kubernetes \
scheduler-csr.json | cfssljson -bare /etc/kubernetes/pki/scheduler
# 注意，如果不是高可用集群，192.168.8.20:8443改为master01的地址，8443改为apiserver的端口，默认是6443
kubectl config set-cluster kubernetes \
--certificate-authority=/etc/kubernetes/pki/ca.pem \
--embed-certs=true \
--server=https://192.168.8.20:8443 \
--kubeconfig=/etc/kubernetes/scheduler.kubeconfig
kubectl config set-credentials system:kube-scheduler \
--client-certificate=/etc/kubernetes/pki/scheduler.pem \
--client-key=/etc/kubernetes/pki/scheduler-key.pem \
--embed-certs=true \
--kubeconfig=/etc/kubernetes/scheduler.kubeconfig
kubectl config set-context system:kube-scheduler@kubernetes \
--cluster=kubernetes \
--user=system:kube-scheduler \
--kubeconfig=/etc/kubernetes/scheduler.kubeconfig
kubectl config use-context system:kube-scheduler@kubernetes \
--kubeconfig=/etc/kubernetes/scheduler.kubeconfig
cfssl gencert \
-ca=/etc/kubernetes/pki/ca.pem \
-ca-key=/etc/kubernetes/pki/ca-key.pem \
-config=ca-config.json \
-profile=kubernetes \
admin-csr.json | cfssljson -bare /etc/kubernetes/pki/admin
# 注意，如果不是高可用集群，192.168.8.20:8443改为master01的地址，8443改为apiserver的端口，默认是6443
kubectl config set-cluster kubernetes --certificate-authority=/etc/kubernetes/pki/ca.pem --embed-certs=true --server=https://192.168.8.20:8443 --kubeconfig=/etc/kubernetes/admin.kubeconfig
kubectl config set-credentials kubernetes-admin --client-certificate=/etc/kubernetes/pki/admin.pem --client-key=/etc/kubernetes/pki/admin-key.pem --embed-certs=true --kubeconfig=/etc/kubernetes/admin.kubeconfig
kubectl config set-context kubernetes-admin@kubernetes --cluster=kubernetes --user=kubernetes-admin --kubeconfig=/etc/kubernetes/admin.kubeconfig
kubectl config use-context kubernetes-admin@kubernetes --kubeconfig=/etc/kubernetes/admin.kubeconfig
创建ServiceAccount Key à secret
openssl genrsa -out /etc/kubernetes/pki/sa.key 2048
返回结果
Generating RSA private key, 2048 bit long modulus (2 primes)
...................................................................................+++++
...............+++++
e is 65537 (0x010001)
openssl rsa -in /etc/kubernetes/pki/sa.key -pubout -out /etc/kubernetes/pki/sa.pub
发送证书至其他节点
for NODE in k8s-master02 k8s-master03; do
ssh $NODE "mkdir -p /etc/kubernetes/pki/"
for FILE in $(ls /etc/kubernetes/pki | grep -v etcd); do
scp /etc/kubernetes/pki/${FILE} $NODE:/etc/kubernetes/pki/${FILE};
done;
for FILE in admin.kubeconfig controller-manager.kubeconfig scheduler.kubeconfig; do
scp /etc/kubernetes/${FILE} $NODE:/etc/kubernetes/${FILE};
done;
done
查看证书文件
ls /etc/kubernetes/pki/
admin.csr apiserver.csr ca.csr controller-manager.csr front-proxy-ca.csr front-proxy-client.csr sa.key scheduler-key.pem
admin-key.pem apiserver-key.pem ca-key.pem controller-manager-key.pem front-proxy-ca-key.pem front-proxy-client-key.pem sa.pub scheduler.pem
admin.pem apiserver.pem ca.pem controller-manager.pem front-proxy-ca.pem front-proxy-client.pem scheduler.csr
ls /etc/kubernetes/pki/ |wc -l
23
高可用配置
高可用配置（注意：如果不是高可用集群，haproxy和keepalived无需安装）
如果在云上安装也无需执行此章节的步骤，可以直接使用云上的lb，比如阿里云slb，腾讯云elb等
公有云要用公有云自带的负载均衡，比如阿里云的SLB，腾讯云的ELB，用来替代haproxy和keepalived，因为公有云大部分都是不支持keepalived的，另外如果用阿里云的话，kubectl控制端不能放在master节点，推荐使用腾讯云，因为阿里云的slb有回环的问题，也就是slb代理的服务器不能反向访问SLB，但是腾讯云修复了这个问题
Slb -> haproxy -> apiserver
所有Master节点安装keepalived和haproxy
apt install keepalived haproxy -y
所有Master配置HAProxy，配置一样
vim /etc/haproxy/haproxy.cfg
# 在配置文件中添加如下内容
frontend k8s-master
bind 0.0.0.0:8443
bind 127.0.0.1:8443
mode tcp
option tcplog
tcp-request inspect-delay 5s
default_backend k8s-master
backend k8s-master
mode tcp
option tcplog
option tcp-check
balance roundrobin
default-server inter 10s downinter 5s rise 2 fall 2 slowstart 60s maxconn 250 maxqueue 256 weight 100
server k8s-master01 192.168.8.15:6443 check
server k8s-master02 192.168.8.16:6443 check
server k8s-master03 192.168.8.17:6443 check
master01-keepalived
所有Master节点配置KeepAlived，配置不一样，注意区分
vim /etc/keepalived/keepalived.conf
! Configuration File for keepalived
global_defs {
router_id LVS_DEVEL
}
vrrp_script chk_apiserver {
script "/etc/keepalived/check_apiserver.sh"
interval 5
weight -5
fall 2
rise 1
}
vrrp_instance VI_1 {
state MASTER
interface ens33
mcast_src_ip 192.168.8.15
virtual_router_id 51
priority 101
nopreempt
advert_int 2
authentication {
auth_type PASS
auth_pass K8SHA_KA_AUTH
}
virtual_ipaddress {
192.168.8.20
}
track_script {
chk_apiserver
} }
master02-keepalived
vim /etc/keepalived/keepalived.conf
! Configuration File for keepalived
global_defs {
router_id LVS_DEVEL
}
vrrp_script chk_apiserver {
script "/etc/keepalived/check_apiserver.sh"
interval 5
weight -5
fall 2
rise 1
}
vrrp_instance VI_1 {
state BACKUP
interface ens33
mcast_src_ip 192.168.8.16
virtual_router_id 51
priority 100
nopreempt
advert_int 2
authentication {
auth_type PASS
auth_pass K8SHA_KA_AUTH
}
virtual_ipaddress {
192.168.8.20
}
track_script {
chk_apiserver
} }
master03-keepalived
vim /etc/keepalived/keepalived.conf
! Configuration File for keepalived
global_defs {
router_id LVS_DEVEL
}
vrrp_script chk_apiserver {
script "/etc/keepalived/check_apiserver.sh"
interval 5
weight -5
fall 2
rise 1
}
vrrp_instance VI_1 {
state BACKUP
interface ens33
mcast_src_ip 192.168.8.17
virtual_router_id 51
priority 100
nopreempt
advert_int 2
authentication {
auth_type PASS
auth_pass K8SHA_KA_AUTH
}
virtual_ipaddress {
192.168.8.20
}
track_script {
chk_apiserver
} }
健康检查
所有节点
vim /etc/keepalived/check_apiserver.sh
#!/bin/bash
err=0
for k in $(seq 1 3)
do
check_code=$(pgrep haproxy)
if [[ $check_code == "" ]]; then
err=$(expr $err + 1)
sleep 1
continue
else
err=0
break
fi
done
if [[ $err != "0" ]]; then
echo "systemctl stop keepalived"
/usr/bin/systemctl stop keepalived
exit 1
else
exit 0
fi
chmod +x /etc/keepalived/check_apiserver.sh
有master节点启动haproxy和keepalived
systemctl daemon-reload
systemctl enable --now haproxy
systemctl enable --now keepalived
systemctl status haproxy && systemctl status keepalived
测试vip
ping 192.168.8.20
PING 192.168.8.20 (192.168.8.20) 56(84) bytes of data.
64 bytes from 192.168.8.20: icmp_seq=1 ttl=64 time=1.39 ms
64 bytes from 192.168.8.20: icmp_seq=2 ttl=64 time=2.46 ms
64 bytes from 192.168.8.20: icmp_seq=3 ttl=64 time=1.68 ms
64 bytes from 192.168.8.20: icmp_seq=4 ttl=64 time=1.08 ms
注意
如果ping不通且telnet没有出现 ]，则认为VIP不可以，不可在继续往下执行，需要排查keepalived的问题，比如防火墙和selinux，haproxy和keepalived的状态，监听端口等
所有节点查看防火墙状态必须为disable和inactive：systemctl status firewalld
所有节点查看selinux状态，必须为disable：getenforce
master节点查看haproxy和keepalived状态：systemctl status keepalived haproxy
master节点查看监听端口：netstat -lntp
etcd配置
etcd配置大致相同，注意修改每个Master节点的etcd配置的主机名和IP地址
master01
vim /etc/etcd/etcd.config.yml
name: 'k8s-master01' #主机名
data-dir: /var/lib/etcd #数据存储目录
wal-dir: /var/lib/etcd/wal
snapshot-count: 5000
heartbeat-interval: 100
election-timeout: 1000
quota-backend-bytes: 0
listen-peer-urls: 'https://192.168.8.15:2380'
listen-client-urls: 'https://192.168.8.15:2379,http://127.0.0.1:2379'
max-snapshots: 3
max-wals: 5
cors:
initial-advertise-peer-urls: 'https://192.168.8.15:2380'
advertise-client-urls: 'https://192.168.8.15:2379'
discovery:
discovery-fallback: 'proxy'
discovery-proxy:
discovery-srv:
initial-cluster: 'k8s-master01=https://192.168.8.15:2380,k8s-master02=https://192.168.8.16:2380,k8s-master03=https://192.168.8.17:2380'
initial-cluster-token: 'etcd-k8s-cluster'
initial-cluster-state: 'new'
strict-reconfig-check: false
enable-v2: true
enable-pprof: true
proxy: 'off'
proxy-failure-wait: 5000
proxy-refresh-interval: 30000
proxy-dial-timeout: 1000
proxy-write-timeout: 5000
proxy-read-timeout: 0
client-transport-security:
cert-file: '/etc/kubernetes/pki/etcd/etcd.pem'
key-file: '/etc/kubernetes/pki/etcd/etcd-key.pem'
client-cert-auth: true
trusted-ca-file: '/etc/kubernetes/pki/etcd/etcd-ca.pem'
auto-tls: true
peer-transport-security:
cert-file: '/etc/kubernetes/pki/etcd/etcd.pem'
key-file: '/etc/kubernetes/pki/etcd/etcd-key.pem'
peer-client-cert-auth: true
trusted-ca-file: '/etc/kubernetes/pki/etcd/etcd-ca.pem'
auto-tls: true
debug: false
log-package-levels:
log-outputs: [default]
force-new-cluster: false
master02
vim /etc/etcd/etcd.config.yml
name: 'k8s-master02'
data-dir: /var/lib/etcd
wal-dir: /var/lib/etcd/wal
snapshot-count: 5000
heartbeat-interval: 100
election-timeout: 1000
quota-backend-bytes: 0
listen-peer-urls: 'https://192.168.8.16:2380'
listen-client-urls: 'https://192.168.8.16:2379,http://127.0.0.1:2379'
max-snapshots: 3
max-wals: 5
cors:
initial-advertise-peer-urls: 'https://192.168.8.16:2380'
advertise-client-urls: 'https://192.168.8.16:2379'
discovery:
discovery-fallback: 'proxy'
discovery-proxy:
discovery-srv:
initial-cluster: 'k8s-master01=https://192.168.8.15:2380,k8s-master02=https://192.168.8.16:2380,k8s-master03=https://192.168.8.17:2380'
initial-cluster-token: 'etcd-k8s-cluster'
initial-cluster-state: 'new'
strict-reconfig-check: false
enable-v2: true
enable-pprof: true
proxy: 'off'
proxy-failure-wait: 5000
proxy-refresh-interval: 30000
proxy-dial-timeout: 1000
proxy-write-timeout: 5000
proxy-read-timeout: 0
client-transport-security:
cert-file: '/etc/kubernetes/pki/etcd/etcd.pem'
key-file: '/etc/kubernetes/pki/etcd/etcd-key.pem'
client-cert-auth: true
trusted-ca-file: '/etc/kubernetes/pki/etcd/etcd-ca.pem'
auto-tls: true
peer-transport-security:
cert-file: '/etc/kubernetes/pki/etcd/etcd.pem'
key-file: '/etc/kubernetes/pki/etcd/etcd-key.pem'
peer-client-cert-auth: true
trusted-ca-file: '/etc/kubernetes/pki/etcd/etcd-ca.pem'
auto-tls: true
debug: false
log-package-levels:
log-outputs: [default]
force-new-cluster: false
master03
vim /etc/etcd/etcd.config.yml
name: 'k8s-master03'
data-dir: /var/lib/etcd
wal-dir: /var/lib/etcd/wal
snapshot-count: 5000
heartbeat-interval: 100
election-timeout: 1000
quota-backend-bytes: 0
listen-peer-urls: 'https://192.168.8.17:2380'
listen-client-urls: 'https://192.168.8.17:2379,http://127.0.0.1:2379'
max-snapshots: 3
max-wals: 5
cors:
initial-advertise-peer-urls: 'https://192.168.8.17:2380'
advertise-client-urls: 'https://192.168.8.17:2379'
discovery:
discovery-fallback: 'proxy'
discovery-proxy:
discovery-srv:
initial-cluster: 'k8s-master01=https://192.168.8.15:2380,k8s-master02=https://192.168.8.16:2380,k8s-master03=https://192.168.8.17:2380'
initial-cluster-token: 'etcd-k8s-cluster'
initial-cluster-state: 'new'
strict-reconfig-check: false
enable-v2: true
enable-pprof: true
proxy: 'off'
proxy-failure-wait: 5000
proxy-refresh-interval: 30000
proxy-dial-timeout: 1000
proxy-write-timeout: 5000
proxy-read-timeout: 0
client-transport-security:
cert-file: '/etc/kubernetes/pki/etcd/etcd.pem'
key-file: '/etc/kubernetes/pki/etcd/etcd-key.pem'
client-cert-auth: true
trusted-ca-file: '/etc/kubernetes/pki/etcd/etcd-ca.pem'
auto-tls: true
peer-transport-security:
cert-file: '/etc/kubernetes/pki/etcd/etcd.pem'
key-file: '/etc/kubernetes/pki/etcd/etcd-key.pem'
peer-client-cert-auth: true
trusted-ca-file: '/etc/kubernetes/pki/etcd/etcd-ca.pem'
auto-tls: true
debug: false
log-package-levels:
log-outputs: [default]
force-new-cluster: false
创建service
所有Master节点创建etcd service并启动
vim /usr/lib/systemd/system/etcd.service
[Unit]
Description=Etcd Service
Documentation=https://coreos.com/etcd/docs/latest/
After=network.target
[Service]
Type=notify
ExecStart=/usr/local/bin/etcd --config-file=/etc/etcd/etcd.config.yml
Restart=on-failure
RestartSec=10
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
Alias=etcd3.service
所有Master节点创建etcd的证书目录
mkdir /etc/kubernetes/pki/etcd
ln -s /etc/etcd/ssl/* /etc/kubernetes/pki/etcd/
systemctl daemon-reload
systemctl enable --now etcd
查看etcd状态
export ETCDCTL_API=3
etcdctl --endpoints="192.168.8.17:2379,192.168.8.16:2379,192.168.8.15:2379" --cacert=/etc/kubernetes/pki/etcd/etcd-ca.pem --cert=/etc/kubernetes/pki/etcd/etcd.pem --key=/etc/kubernetes/pki/etcd/etcd-key.pem endpoint status --write-out=table
注意，，，3个节点，只能挂掉一个etcd节点， etc必须是基数，不能是偶数
apiserver
master01
注意本文档使用的k8s service网段为10.96.0.0/16，该网段不能和宿主机的网段、Pod网段的重复，请按需修改
vim /usr/lib/systemd/system/kube-apiserver.service
[Unit]
Description=Kubernetes API Server
Documentation=https://github.com/kubernetes/kubernetes
After=network.target
[Service]
ExecStart=/usr/local/bin/kube-apiserver \
--v=2 \
--allow-privileged=true \
--bind-address=0.0.0.0 \
--secure-port=6443 \
--advertise-address=192.168.8.15 \
--service-cluster-ip-range=10.96.0.0/16 \
--service-node-port-range=30000-32767 \
--etcd-servers=https://192.168.8.15:2379,https://192.168.8.16:2379,https://192.168.8.17:2379 \
--etcd-cafile=/etc/etcd/ssl/etcd-ca.pem \
--etcd-certfile=/etc/etcd/ssl/etcd.pem \
--etcd-keyfile=/etc/etcd/ssl/etcd-key.pem \
--client-ca-file=/etc/kubernetes/pki/ca.pem \
--tls-cert-file=/etc/kubernetes/pki/apiserver.pem \
--tls-private-key-file=/etc/kubernetes/pki/apiserver-key.pem \
--kubelet-client-certificate=/etc/kubernetes/pki/apiserver.pem \
--kubelet-client-key=/etc/kubernetes/pki/apiserver-key.pem \
--service-account-key-file=/etc/kubernetes/pki/sa.pub \
--service-account-signing-key-file=/etc/kubernetes/pki/sa.key \
--service-account-issuer=https://kubernetes.default.svc.cluster.local \
--kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname \
--enable-admission-plugins=NamespaceLifecycle,LimitRanger,ServiceAccount,DefaultStorageClass,DefaultTolerationSeconds,NodeRestriction,ResourceQuota \
--authorization-mode=Node,RBAC \
--enable-bootstrap-token-auth=true \
--requestheader-client-ca-file=/etc/kubernetes/pki/front-proxy-ca.pem \
--proxy-client-cert-file=/etc/kubernetes/pki/front-proxy-client.pem \
--proxy-client-key-file=/etc/kubernetes/pki/front-proxy-client-key.pem \
--requestheader-allowed-names=aggregator \
--requestheader-group-headers=X-Remote-Group \
--requestheader-extra-headers-prefix=X-Remote-Extra- \
--requestheader-username-headers=X-Remote-User
# --token-auth-file=/etc/kubernetes/token.csv
Restart=on-failure
RestartSec=10s
LimitNOFILE=65535
[Install]
WantedBy=multi-user.target
master02
vim /usr/lib/systemd/system/kube-apiserver.service
[Unit]
Description=Kubernetes API Server
Documentation=https://github.com/kubernetes/kubernetes
After=network.target
[Service]
ExecStart=/usr/local/bin/kube-apiserver \
--v=2 \
--allow-privileged=true \
--bind-address=0.0.0.0 \
--secure-port=6443 \
--advertise-address=192.168.8.16 \
--service-cluster-ip-range=10.96.0.0/16 \
--service-node-port-range=30000-32767 \
--etcd-servers=https://192.168.8.15:2379,https://192.168.8.16:2379,https://192.168.8.17:2379 \
--etcd-cafile=/etc/etcd/ssl/etcd-ca.pem \
--etcd-certfile=/etc/etcd/ssl/etcd.pem \
--etcd-keyfile=/etc/etcd/ssl/etcd-key.pem \
--client-ca-file=/etc/kubernetes/pki/ca.pem \
--tls-cert-file=/etc/kubernetes/pki/apiserver.pem \
--tls-private-key-file=/etc/kubernetes/pki/apiserver-key.pem \
--kubelet-client-certificate=/etc/kubernetes/pki/apiserver.pem \
--kubelet-client-key=/etc/kubernetes/pki/apiserver-key.pem \
--service-account-key-file=/etc/kubernetes/pki/sa.pub \
--service-account-signing-key-file=/etc/kubernetes/pki/sa.key \
--service-account-issuer=https://kubernetes.default.svc.cluster.local \
--kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname \
--enable-admission-plugins=NamespaceLifecycle,LimitRanger,ServiceAccount,DefaultStorageClass,DefaultTolerationSeconds,NodeRestriction,ResourceQuota \
--authorization-mode=Node,RBAC \
--enable-bootstrap-token-auth=true \
--requestheader-client-ca-file=/etc/kubernetes/pki/front-proxy-ca.pem \
--proxy-client-cert-file=/etc/kubernetes/pki/front-proxy-client.pem \
--proxy-client-key-file=/etc/kubernetes/pki/front-proxy-client-key.pem \
--requestheader-allowed-names=aggregator \
--requestheader-group-headers=X-Remote-Group \
--requestheader-extra-headers-prefix=X-Remote-Extra- \
--requestheader-username-headers=X-Remote-User
Restart=on-failure
RestartSec=10s
LimitNOFILE=65535
[Install]
WantedBy=multi-user.target
master03
vim /usr/lib/systemd/system/kube-apiserver.service
[Unit]
Description=Kubernetes API Server
Documentation=https://github.com/kubernetes/kubernetes
After=network.target
[Service]
ExecStart=/usr/local/bin/kube-apiserver \
--v=2 \
--allow-privileged=true \
--bind-address=0.0.0.0 \
--secure-port=6443 \
--advertise-address=192.168.8.17 \
--service-cluster-ip-range=10.96.0.0/16 \
--service-node-port-range=30000-32767 \
--etcd-servers=https://192.168.8.15:2379,https://192.168.8.16:2379,https://192.168.8.17:2379 \
--etcd-cafile=/etc/etcd/ssl/etcd-ca.pem \
--etcd-certfile=/etc/etcd/ssl/etcd.pem \
--etcd-keyfile=/etc/etcd/ssl/etcd-key.pem \
--client-ca-file=/etc/kubernetes/pki/ca.pem \
--tls-cert-file=/etc/kubernetes/pki/apiserver.pem \
--tls-private-key-file=/etc/kubernetes/pki/apiserver-key.pem \
--kubelet-client-certificate=/etc/kubernetes/pki/apiserver.pem \
--kubelet-client-key=/etc/kubernetes/pki/apiserver-key.pem \
--service-account-key-file=/etc/kubernetes/pki/sa.pub \
--service-account-signing-key-file=/etc/kubernetes/pki/sa.key \
--service-account-issuer=https://kubernetes.default.svc.cluster.local \
--kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname \
--enable-admission-plugins=NamespaceLifecycle,LimitRanger,ServiceAccount,DefaultStorageClass,DefaultTolerationSeconds,NodeRestriction,ResourceQuota \
--authorization-mode=Node,RBAC \
--enable-bootstrap-token-auth=true \
--requestheader-client-ca-file=/etc/kubernetes/pki/front-proxy-ca.pem \
--proxy-client-cert-file=/etc/kubernetes/pki/front-proxy-client.pem \
--proxy-client-key-file=/etc/kubernetes/pki/front-proxy-client-key.pem \
--requestheader-allowed-names=aggregator \
--requestheader-group-headers=X-Remote-Group \
--requestheader-extra-headers-prefix=X-Remote-Extra- \
--requestheader-username-headers=X-Remote-User
# --token-auth-file=/etc/kubernetes/token.csv
Restart=on-failure
RestartSec=10s
LimitNOFILE=65535
[Install]
WantedBy=multi-user.target
注意：
如果etcd没有和master部署在一起
--etcd-servers=https://192.168.8.15:2379,https://192.168.8.16:2379,https://192.168.8.17:2379 \
这段改成 etcd的ip地址
启动apiserver
所有Master节点开启kube-apiserver
systemctl daemon-reload && systemctl enable --now kube-apiserver
systemctl status kube-apiserver
controller manager
所有Master节点配置kube-controller-manager service（所有master节点配置一样）
注意本文档使用的k8s Pod网段为172.16.0.0/16，该网段不能和宿主机的网段、k8s Service网段的重复，请按需修改
vim /usr/lib/systemd/system/kube-controller-manager.service
[Unit]
Description=Kubernetes Controller Manager
Documentation=https://github.com/kubernetes/kubernetes
After=network.target
[Service]
ExecStart=/usr/local/bin/kube-controller-manager \
--v=2 \
--root-ca-file=/etc/kubernetes/pki/ca.pem \
--cluster-signing-cert-file=/etc/kubernetes/pki/ca.pem \
--cluster-signing-key-file=/etc/kubernetes/pki/ca-key.pem \
--service-account-private-key-file=/etc/kubernetes/pki/sa.key \
--kubeconfig=/etc/kubernetes/controller-manager.kubeconfig \
--authentication-kubeconfig=/etc/kubernetes/controller-manager.kubeconfig \
--authorization-kubeconfig=/etc/kubernetes/controller-manager.kubeconfig \
--leader-elect=true \
--use-service-account-credentials=true \
--node-monitor-grace-period=40s \
--node-monitor-period=5s \
--controllers=*,bootstrapsigner,tokencleaner \
--allocate-node-cidrs=true \
--cluster-cidr=172.16.0.0/16 \
--requestheader-client-ca-file=/etc/kubernetes/pki/front-proxy-ca.pem \
--node-cidr-mask-size=24
Restart=always
RestartSec=10s
[Install]
WantedBy=multi-user.target
所有Master节点启动kube-controller-manager
systemctl daemon-reload
systemctl enable --now kube-controller-manager
查看状态
systemctl status kube-controller-manager
scheduler
所有Master节点配置kube-scheduler service（所有master节点配置一样）
vim /usr/lib/systemd/system/kube-scheduler.service
[Unit]
Description=Kubernetes Scheduler
Documentation=https://github.com/kubernetes/kubernetes
After=network.target
[Service]
ExecStart=/usr/local/bin/kube-scheduler \
--v=2 \
--leader-elect=true \
--authentication-kubeconfig=/etc/kubernetes/scheduler.kubeconfig \
--authorization-kubeconfig=/etc/kubernetes/scheduler.kubeconfig \
--kubeconfig=/etc/kubernetes/scheduler.kubeconfig
Restart=always
RestartSec=10s
[Install]
WantedBy=multi-user.target
启动
systemctl daemon-reload
systemctl enable --now kube-scheduler
systemctl status kube-scheduler
TLS Bootstrapping配置
给node节点自动颁发证书
只需要在Master01创建bootstrap
cd /root/k8s-ha-install/bootstrap
kubectl config set-cluster kubernetes --certificate-authority=/etc/kubernetes/pki/ca.pem --embed-certs=true --server=https://192.168.8.20:8443 --kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig
kubectl config set-credentials tls-bootstrap-token-user --token=c8ad9c.2e4d610cf3e7426e --kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig
kubectl config set-context tls-bootstrap-token-user@kubernetes --cluster=kubernetes --user=tls-bootstrap-token-user --kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig
kubectl config use-context tls-bootstrap-token-user@kubernetes --kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig
管理文件,如果其他master节点也需要，也拷贝一下即可
mkdir -p /root/.kube ; cp /etc/kubernetes/admin.kubeconfig /root/.kube/config
可以正常查询集群状态，才可以继续往下，否则不行，需要排查k8s组件是否有故障
kubectl get cs
Warning: v1 ComponentStatus is deprecated in v1.19+
NAME STATUS MESSAGE ERROR
controller-manager Healthy ok
etcd-0 Healthy ok
scheduler Healthy ok
kubectl create -f bootstrap.secret.yaml
node节点配置
Master01节点复制证书至Node节点
cd /etc/kubernetes/
for NODE in k8s-master02 k8s-master03 k8s-node01 k8s-node02; do
ssh $NODE mkdir -p /etc/kubernetes/pki
for FILE in pki/ca.pem pki/ca-key.pem pki/front-proxy-ca.pem bootstrap-kubelet.kubeconfig; do
scp /etc/kubernetes/$FILE $NODE:/etc/kubernetes/${FILE}
done
done
kubelet配置
所有节点创建相关目录
mkdir -p /var/lib/kubelet /var/log/kubernetes /etc/systemd/system/kubelet.service.d /etc/kubernetes/manifests/
所有节点配置kubelet service
vim /usr/lib/systemd/system/kubelet.service
[Unit]
Description=Kubernetes Kubelet
Documentation=https://github.com/kubernetes/kubernetes
[Service]
ExecStart=/usr/local/bin/kubelet
Restart=always
StartLimitInterval=0
RestartSec=10
[Install]
WantedBy=multi-user.target
所有节点配置kubelet service的配置文件（也可以写到kubelet.service）
vim /etc/systemd/system/kubelet.service.d/10-kubelet.conf
[Service]
Environment="KUBELET_KUBECONFIG_ARGS=--bootstrap-kubeconfig=/etc/kubernetes/bootstrap-kubelet.kubeconfig --kubeconfig=/etc/kubernetes/kubelet.kubeconfig"
Environment="KUBELET_SYSTEM_ARGS=--container-runtime-endpoint=unix:///run/containerd/containerd.sock"
Environment="KUBELET_CONFIG_ARGS=--config=/etc/kubernetes/kubelet-conf.yml"
Environment="KUBELET_EXTRA_ARGS=--node-labels=node.kubernetes.io/node='' "
ExecStart=
ExecStart=/usr/local/bin/kubelet $KUBELET_KUBECONFIG_ARGS $KUBELET_CONFIG_ARGS $KUBELET_SYSTEM_ARGS $KUBELET_EXTRA_ARGS
创建kubelet的配置文件
注意：如果更改了k8s的service网段，需要更改kubelet-conf.yml 的clusterDNS:配置，改成k8s Service网段的第十个地址，比如10.96.0.10
vim /etc/kubernetes/kubelet-conf.yml
apiVersion: kubelet.config.k8s.io/v1beta1
kind: KubeletConfiguration
address: 0.0.0.0
port: 10250
readOnlyPort: 10255
authentication:
anonymous:
enabled: false
webhook:
cacheTTL: 2m0s
enabled: true
x509:
clientCAFile: /etc/kubernetes/pki/ca.pem
authorization:
mode: Webhook
webhook:
cacheAuthorizedTTL: 5m0s
cacheUnauthorizedTTL: 30s
cgroupDriver: systemd
cgroupsPerQOS: true
clusterDNS:
- 10.96.0.10
clusterDomain: cluster.local
containerLogMaxFiles: 5
containerLogMaxSize: 10Mi
contentType: application/vnd.kubernetes.protobuf
cpuCFSQuota: true
cpuManagerPolicy: none
cpuManagerReconcilePeriod: 10s
enableControllerAttachDetach: true
enableDebuggingHandlers: true
enforceNodeAllocatable:
- pods
eventBurst: 10
eventRecordQPS: 5
evictionHard:
imagefs.available: 15%
memory.available: 100Mi
nodefs.available: 10%
nodefs.inodesFree: 5%
evictionPressureTransitionPeriod: 5m0s
failSwapOn: true
fileCheckFrequency: 20s
hairpinMode: promiscuous-bridge
healthzBindAddress: 127.0.0.1
healthzPort: 10248
httpCheckFrequency: 20s
imageGCHighThresholdPercent: 85
imageGCLowThresholdPercent: 80
imageMinimumGCAge: 2m0s
iptablesDropBit: 15
iptablesMasqueradeBit: 14
kubeAPIBurst: 10
kubeAPIQPS: 5
makeIPTablesUtilChains: true
maxOpenFiles: 1000000
maxPods: 110
nodeStatusUpdateFrequency: 10s
oomScoreAdj: -999
podPidsLimit: -1
registryBurst: 10
registryPullQPS: 5
resolvConf: /etc/resolv.conf
rotateCertificates: true
runtimeRequestTimeout: 2m0s
serializeImagePulls: true
staticPodPath: /etc/kubernetes/manifests
streamingConnectionIdleTimeout: 4h0m0s
syncFrequency: 1m0s
volumeStatsAggPeriod: 1m0s
启动所有节点kubelet
systemctl daemon-reload
systemctl enable --now kubelet
查看集群状态(Ready或NotReady都正常)
kubectl get node
NAME STATUS ROLES AGE VERSION
k8s-master01 NotReady <none> 5m4s v1.28.15
k8s-master02 NotReady <none> 3m6s v1.28.15
k8s-master03 NotReady <none> 3m10s v1.28.15
k8s-node01 NotReady <none> 67s v1.28.15
k8s-node02 NotReady <none> 38s v1.28.15
kube-proxy配置
以下操作只在Master01执行
cd /root/k8s-ha-install/pki
cfssl gencert \
-ca=/etc/kubernetes/pki/ca.pem \
-ca-key=/etc/kubernetes/pki/ca-key.pem \
-config=ca-config.json \
-profile=kubernetes \
kube-proxy-csr.json | cfssljson -bare /etc/kubernetes/pki/kube-proxy
# 注意，如果不是高可用集群，192.168.8.20:8443改为master01的地址，8443改为apiserver的端口，默认是6443
kubectl config set-cluster kubernetes \
--certificate-authority=/etc/kubernetes/pki/ca.pem \
--embed-certs=true \
--server=https://192.168.8.20:8443 \
--kubeconfig=/etc/kubernetes/kube-proxy.kubeconfig
kubectl config set-credentials system:kube-proxy \
--client-certificate=/etc/kubernetes/pki/kube-proxy.pem \
--client-key=/etc/kubernetes/pki/kube-proxy-key.pem \
--embed-certs=true \
--kubeconfig=/etc/kubernetes/kube-proxy.kubeconfig
kubectl config set-context system:kube-proxy@kubernetes \
--cluster=kubernetes \
--user=system:kube-proxy \
--kubeconfig=/etc/kubernetes/kube-proxy.kubeconfig
kubectl config use-context system:kube-proxy@kubernetes \
--kubeconfig=/etc/kubernetes/kube-proxy.kubeconfig
将kubeconfig发送至其他节点
for NODE in k8s-master02 k8s-master03; do
scp /etc/kubernetes/kube-proxy.kubeconfig $NODE:/etc/kubernetes/kube-proxy.kubeconfig
done
for NODE in k8s-node01 k8s-node02; do
scp /etc/kubernetes/kube-proxy.kubeconfig $NODE:/etc/kubernetes/kube-proxy.kubeconfig
done
所有节点添加kube-proxy的配置和service文件
vim /usr/lib/systemd/system/kube-proxy.service
[Unit]
Description=Kubernetes Kube Proxy
Documentation=https://github.com/kubernetes/kubernetes
After=network.target
[Service]
ExecStart=/usr/local/bin/kube-proxy \
--config=/etc/kubernetes/kube-proxy.yaml \
--v=2
Restart=always
RestartSec=10s
[Install]
WantedBy=multi-user.target
如果更改了集群Pod的网段，需要更改kube-proxy.yaml的clusterCIDR为自己的Pod网段：
vim /etc/kubernetes/kube-proxy.yaml
apiVersion: kubeproxy.config.k8s.io/v1alpha1
bindAddress: 0.0.0.0
clientConnection:
acceptContentTypes: ""
burst: 10
contentType: application/vnd.kubernetes.protobuf
kubeconfig: /etc/kubernetes/kube-proxy.kubeconfig
qps: 5
clusterCIDR: 172.16.0.0/16
configSyncPeriod: 15m0s
conntrack:
max: null
maxPerCore: 32768
min: 131072
tcpCloseWaitTimeout: 1h0m0s
tcpEstablishedTimeout: 24h0m0s
enableProfiling: false
healthzBindAddress: 0.0.0.0:10256
hostnameOverride: ""
iptables:
masqueradeAll: false
masqueradeBit: 14
minSyncPeriod: 0s
syncPeriod: 30s
ipvs:
masqueradeAll: true
minSyncPeriod: 5s
scheduler: "rr"
syncPeriod: 30s
kind: KubeProxyConfiguration
metricsBindAddress: 127.0.0.1:10249
mode: "ipvs"
nodePortAddresses: null
oomScoreAdj: -999
portRange: ""
udpIdleTimeout: 250ms
所有节点启动kube-proxy
systemctl daemon-reload
systemctl enable --now kube-proxy
安装Calico
以下步骤只在master01执行
cd /root/k8s-ha-install/calico/
更改calico的网段，主要需要将红色部分的网段，改为自己的Pod网段
sed -i "s#POD_CIDR#172.16.0.0/16#g" calico.yaml
检查网段是自己的Pod网段， grep "IPV4POOL_CIDR" calico.yaml -A 1
grep "IPV4POOL_CIDR" calico.yaml -A 1
kubectl apply -f calico.yaml
查看容器状态
kubectl get po -n kube-system
果容器状态异常可以使用kubectldescribe或者kubectllogs查看容器的日志
1.Kubectl logs -f POD_NAME -n kube-system
2. Kubectl logs -f POD_NAME -c 【upgrade-ipam】 -n kube-system
a) # kube-proxy
安装coreDNS
cd /root/k8s-ha-install/
如果更改了k8s service的网段需要将coredns的serviceIP改成k8s service网段的第十个IP
COREDNS_SERVICE_IP=`kubectl get svc | grep kubernetes | awk '{print $3}'`0
sed -i "s#KUBEDNS_SERVICE_IP#${COREDNS_SERVICE_IP}#g" CoreDNS/coredns.yaml
安装coredns
kubectl create -f CoreDNS/coredns.yaml
serviceaccount/coredns created
clusterrole.rbac.authorization.k8s.io/system:coredns created
clusterrolebinding.rbac.authorization.k8s.io/system:coredns created
configmap/coredns created
deployment.apps/coredns created
service/kube-dns created
如果失败了，提示
[FATAL] plugin/loop: Loop (127.0.0.1:47083 -> :53) detected for zone ".", see https://coredns.io/plugins/loop#troubleshooting. Query: "HINFO 8922049139591519103.6752079822659185910."
方法一，删除yaml文件里的loop
方法二
添加kubeletyml文件中
vim kubelet-config.yml
resolvConf: "/run/systemd/resolve/resolv.conf"
systemctl restart kubelet
集群规模变大，扩容coredns
kubectl edit deploy coredns -n kube-system
安装metrics server
在新版的Kubernetes中系统资源的采集均使用Metrics-server，可以通过Metrics采集节点和Pod的内存、磁盘、CPU和网络的使用率。
安装metrics server
cd /root/k8s-ha-install/metrics-server
kubectl create -f .
kubectl get pod -A
等待metrics server启动然后查看状态
kubectl top node
NAME CPU(cores) CPU% MEMORY(bytes) MEMORY%
k8s-master01 353m 8% 2108Mi 55%
k8s-master02 297m 7% 1880Mi 49%
k8s-master03 402m 10% 1830Mi 48%
k8s-node01 587m 29% 2157Mi 57%
k8s-node02 589m 29% 1965Mi 52%
如果有如下报错，可以等待10分钟后，再次查看：
Error from server (ServiceUnavailable): the server is currently unable to handle the request (get nodes.metrics.k8s.io)
安装dashboard
Dashboard用于展示集群中的各类资源，同时也可以通过Dashboard实时查看Pod的日志和在容器中执行一些命令等。
安装指定版本
cd /root/k8s-ha-install/dashboard/
kubectl create -f .
kubectl get pod -A
查看ip端口
kubectl get svc kubernetes-dashboard -n kubernetes-dashboard
kubernetes-dashboard NodePort 10.96.14.4 <none> 443:31286/TCP 93s
生成token
kubectl create token admin-user -n kube-system
集群验证
1.查看状态
kubectl get node
NAME STATUS ROLES AGE VERSION
k8s-master01 Ready control-plane 99m v1.28.15
k8s-master02 Ready control-plane 87m v1.28.15
k8s-master03 Ready control-plane 87m v1.28.15
k8s-node01 Ready <none> 85m v1.28.15
k8s-node02 Ready <none> 81m v1.28.15
2.pod是否正常
kubectl get pod -A
全部running
ready 1/1
3.集群网段无任何冲突
kubectl get svc
kubectl get po -A -owide
4.能够正常创建资源
kubectl create deploy cluster-test --image=registry.cn-beijing.aliyuncs.com/dotbalo/debug-tools -- sleep 3600
查看
kubectl get pod
NAME READY STATUS RESTARTS AGE
cluster-test-66bb44bd88-p6tw2 1/1 Running 0 12m
查看部署到那个节点和ip
kubectl get pod -owide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
cluster-test-66bb44bd88-p6tw2 1/1 Running 0 12m 172.16.58.196 k8s-node02 <none> <none>
5.pod必须能够解析service（同namespace和跨namespace）
进入容器
kubectl exec -it cluster-test-66bb44bd88-p6tw2 -- bash
nslookup kubernetes
Server: 10.96.0.10
Address: 10.96.0.10#53
Name: kubernetes.default.svc.cluster.local
Address: 10.96.0.1
================================
nslookup kube-dns.kube-system
Server: 10.96.0.10
Address: 10.96.0.10#53
Name: kube-dns.kube-system.svc.cluster.local
Address: 10.96.0.10
6.每个节点都必须要能访问你kubernetes的kubernetes svc 443和kube-dns的service 53
所有master和node去curl
curl 10.96.0.1:443
Client sent an HTTP request to an HTTPS server.
curl 10.96.0.10:53
curl: (52) Empty reply from server
7.pod和pod之间要能够正常通讯（同namespace和跨namespace）
kubectl get po -owide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
cluster-test-66bb44bd88-p6tw2 1/1 Running 0 32m 172.16.58.196 k8s-node02 <none> <none>
root@k8s-master01:~# ping 172.16.58.196
PING 172.16.58.196 (172.16.58.196) 56(84) bytes of data.
64 bytes from 172.16.58.196: icmp_seq=1 ttl=63 time=13.3 ms
64 bytes from 172.16.58.196: icmp_seq=2 ttl=63 time=1.73 ms
64 bytes from 172.16.58.196: icmp_seq=3 ttl=63 time=1.94 ms
^C
--- 172.16.58.196 ping statistics ---
8.pod和pod之间要正常通讯（同机和跨机器）
kubectl get po -n kube-system -owide 查看一台pod
metrics-server-8df99c47f-7z9ss 1/1 Running 8 (60m ago) 17h 172.16.85.194 k8s-node01 <none> <none>
kube-scheduler-k8s-master03 1/1 Running 1 17h 192.168.8.17 k8s-master03 <none> <none>
进入容器里
kubectl exec -it cluster-test-66bb44bd88-p6tw2 -- bash
(01:59 cluster-test-66bb44bd88-p6tw2:/) ping 172.16.85.194
PING 172.16.85.194 (172.16.85.194) 56(84) bytes of data.
64 bytes from 172.16.85.194: icmp_seq=1 ttl=62 time=14.3 ms
64 bytes from 172.16.85.194: icmp_seq=2 ttl=62 time=2.25 ms
--- 172.16.85.194 ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1002ms
rtt min/avg/max/mdev = 2.255/8.295/14.336/6.041 ms
(02:00 cluster-test-66bb44bd88-p6tw2:/) ping 192.168.8.15
PING 192.168.8.15 (192.168.8.15) 56(84) bytes of data.
64 bytes from 192.168.8.15: icmp_seq=1 ttl=63 time=4.28 ms
--- 192.168.8.15 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 4.282/4.282/4.282/0.000 ms