Kubernetes高可用集群二进制部署（六）Kubernetes集群节点添加

Kubernetes概述
使用kubeadm快速部署一个k8s集群
Kubernetes高可用集群二进制部署（一）主机准备和负载均衡器安装
Kubernetes高可用集群二进制部署（二）ETCD集群部署
Kubernetes高可用集群二进制部署（三）部署api-server
Kubernetes高可用集群二进制部署（四）部署kubectl和kube-controller-manager、kube-scheduler
Kubernetes高可用集群二进制部署（五）kubelet、kube-proxy、Calico、CoreDNS
Kubernetes高可用集群二进制部署（六）Kubernetes集群节点添加

主要介绍worker集群添加节点

1. 主机准备

1.1 主机名设置

hostnamectl set-hostname k8s-worker2

hostname

1.2 主机与IP地址解析

集群中已有节点也需要添加新节点的解析。

cat >> /etc/hosts << EOF
192.168.10.101 ha1
192.168.10.102 ha2
192.168.10.103 k8s-master1
192.168.10.104 k8s-master2
192.168.10.105 k8s-master3
192.168.10.106 k8s-worker1
192.168.10.107 k8s-worker2

EOF

1.3 主机安全设置

1.3.1 关闭防火墙

systemctl stop firewalld
systemctl disable firewalld
firewall-cmd --state

1.3.2 关闭selinux

setenforce 0
sed -ri 's/SELINUX=enforcing/SELINUX=disabled/' /etc/selinux/config
sestatus

1.4 交换分区设置

swapoff -a
sed -ri 's/.*swap.*/#&/' /etc/fstab
echo "vm.swappiness=0" >> /etc/sysctl.conf
sysctl -p

1.5 主机系统时间同步

安装软件
yum -y install ntpdate

制定时间同步计划任务
crontab -e
0 */1 * * * ntpdate time1.aliyun.com

1.6 主机系统优化

limit优化

ulimit -SHn 65535

cat <<EOF >> /etc/security/limits.conf
* soft nofile 655360
* hard nofile 131072
* soft nproc 655350
* hard nproc 655350
* soft memlock unlimited
* hard memlock unlimited
EOF

1.7 ipvs管理工具安装及模块加载

为集群节点安装，负载均衡节点不用安装

yum -y install ipvsadm ipset sysstat conntrack libseccomp

所有节点配置ipvs模块，在内核4.19+版本nf_conntrack_ipv4已经改为nf_conntrack， 4.18以下使用nf_conntrack_ipv4即可： 
 
modprobe -- ip_vs 
modprobe -- ip_vs_rr 
modprobe -- ip_vs_wrr 
modprobe -- ip_vs_sh 
modprobe -- nf_conntrack

创建 /etc/modules-load.d/ipvs.conf 并加入以下内容： 
cat >/etc/modules-load.d/ipvs.conf <<EOF 
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 
EOF

设置为开机启动
systemctl enable --now systemd-modules-load.service

如果执行开机启动失败了，提示如下信息：

Job for systemd-modules-load.service failed because the control process exited with error code. See "systemctl status systemd-modules-load.service" and "journalctl -xe" for details.

Failed to find module 'ip_vs_fo'

具体原因是内核版本问题，不过也可以将文件中的ip_vs_fo 去掉，然后继续执行

1.8 Linux内核升级

在所有节点中安装,需要重新操作系统更换内核。

[root@localhost ~]# yum -y install perl

[root@localhost ~]# rpm --import https://www.elrepo.org/RPM-GPG-KEY-elrepo.org

[root@localhost ~]# yum -y install https://www.elrepo.org/elrepo-release-7.0-4.el7.elrepo.noarch.rpm

[root@localhost ~]# yum  --enablerepo="elrepo-kernel"  -y install kernel-ml.x86_64

[root@localhost ~]# grub2-set-default 0

[root@localhost ~]# grub2-mkconfig -o /boot/grub2/grub.cfg

1.9 Linux内核优化

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
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 = 131072
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 -h now

重启后查看结果：
lsmod | grep --color=auto -e ip_vs -e nf_conntrack

1.10 其它工具安装(选装)

yum install wget jq psmisc vim net-tools telnet yum-utils device-mapper-persistent-data lvm2 git lrzsz -y

2. 配置免密登录

在k8s-master1节点操作

ssh-copy-id root@k8s-worker2

3. Kubernetes软件包获取

3.1 软件包获取

[root@k8s-master1 bin]# pwd
/data/k8s-work/kubernetes/server/bin

scp kubelet kube-proxy k8s-worker2:/usr/local/bin

[root@k8s-worker2 ~]# ls /usr/local/bin/kube*
/usr/local/bin/kubelet
/usr/local/bin/kube-proxy

3.2 docker-ce安装及配置

wget -O /etc/yum.repos.d/docker-ce.repo https://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo

yum -y install docker-ce

systemctl enable docker
systemctl start docker

cat <<EOF | sudo tee /etc/docker/daemon.json
{
  "exec-opts": ["native.cgroupdriver=systemd"],
  "registry-mirrors": ["https://8i185852.mirror.aliyuncs.com"]
}
EOF

必须配置native.cgroupdriver，不配置这个步骤会导致kubelet启动失败

systemctl restart docker

3.3 部署kubelet

[root@k8s-worker2 ~]# mkdir -p /etc/kubernetes
[root@k8s-worker2 ~]# mkdir -p /etc/kubernetes/ssl
[root@k8s-worker2 ~]# mkdir -p /var/lib/kubelet
[root@k8s-worker2 ~]# mkdir -p /var/log/kubernetes

[root@k8s-master1 k8s-work]# pwd
/data/k8s-work

scp kubelet-bootstrap.kubeconfig kubelet.json k8s-worker2:/etc/kubernetes/

scp ca.pem k8s-worker2:/etc/kubernetes/ssl/

scp kubelet.service k8s-worker2:/usr/lib/systemd/system/

在新加节点k8s-work2上修改kubelet.json文件
[root@k8s-worker2 ~]# vim /etc/kubernetes/kubelet.json
{
  "kind": "KubeletConfiguration",
  "apiVersion": "kubelet.config.k8s.io/v1beta1",
  "authentication": {
    "x509": {
      "clientCAFile": "/etc/kubernetes/ssl/ca.pem"
    },
    "webhook": {
      "enabled": true,
      "cacheTTL": "2m0s"
    },
    "anonymous": {
      "enabled": false
    }
  },
  "authorization": {
    "mode": "Webhook",
    "webhook": {
      "cacheAuthorizedTTL": "5m0s",
      "cacheUnauthorizedTTL": "30s"
    }
  },
  "address": "192.168.10.107", #当前主机的地址
  "port": 10250,
  "readOnlyPort": 10255,
  "cgroupDriver": "systemd", #要和docker中的一致，否则启动不了
  "hairpinMode": "promiscuous-bridge",
  "serializeImagePulls": false,
  "clusterDomain": "cluster.local.",
  "clusterDNS": ["10.96.0.2"]
}

[root@k8s-worker2 ~]# systemctl daemon-reload
[root@k8s-worker2 ~]# systemctl enable --now kubelet

[root@k8s-worker2 ~]# systemctl status kubelet

# kubectl get nodes
NAME          STATUS   ROLES    AGE   VERSION
k8s-master1   Ready    <none>   41h   v1.21.10
k8s-master2   Ready    <none>   41h   v1.21.10
k8s-master3   Ready    <none>   41h   v1.21.10
k8s-worker1   Ready    <none>   41h   v1.21.10
k8s-worker2   NotReady    <none>   55s   v1.21.10

如果启动失败，查看日志

kubectl get pods -n kube-system -o wide
#或者
less /var/log/messages

在这里插入图片描述

镜像拉取错误，多试几次或者尝试将镜像下载到本地上传到服务器，用docker load -i xxxx加载镜像

在这里插入图片描述

3.4 部署kube-proxy

[root@k8s-master1 k8s-work]# scp kube-proxy.kubeconfig kube-proxy.yaml k8s-worker2:/etc/kubernetes/
[root@k8s-master1 k8s-work]# scp  kube-proxy.service k8s-worker2:/usr/lib/systemd/system/

[root@k8s-worker2 ~]# vim /etc/kubernetes/kube-proxy.yaml
apiVersion: kubeproxy.config.k8s.io/v1alpha1
bindAddress: 192.168.10.107 #当前地址
clientConnection:
  kubeconfig: /etc/kubernetes/kube-proxy.kubeconfig
clusterCIDR: 10.244.0.0/16
healthzBindAddress: 192.168.10.107:10256 #当前地址
kind: KubeProxyConfiguration
metricsBindAddress: 192.168.10.107:10249 #当前地址
mode: "ipvs"

[root@k8s-worker2 ~]# mkdir -p /var/lib/kube-proxy

[root@k8s-worker2 ~]# systemctl daemon-reload
[root@k8s-worker2 ~]# systemctl enable --now kube-proxy

[root@k8s-worker2 ~]# systemctl status kube-proxy

4. 验证

[root@k8s-master1 k8s-work]# kubectl get pods -n kube-system -o wide
NAME                                       READY   STATUS    RESTARTS   AGE     IP               NODE          NOMINATED NODE   READINESS GATES
calico-kube-controllers-7cc8dd57d9-pd44j   1/1     Running   4          2d      10.244.224.4     k8s-master2   <none>           <none>
calico-node-bpqfr                          1/1     Running   3          2d      192.168.10.103   k8s-master1   <none>           <none>
calico-node-f8c6t                          1/1     Running   3          2d      192.168.10.104   k8s-master2   <none>           <none>
calico-node-gndtg                          1/1     Running   4          2d      192.168.10.106   k8s-worker1   <none>           <none>
calico-node-pptqm                          1/1     Running   3          2d      192.168.10.105   k8s-master3   <none>           <none>
calico-node-sjvjc                          1/1     Running   0          7m18s   192.168.10.107   k8s-worker2   <none>           <none>
coredns-675db8b7cc-xlwsp                   1/1     Running   2          24h     10.244.159.132   k8s-master1   <none>           <none>

kubectl get nodes --show-labels
kubectl label nodes k8s-worker2 deploy.type=nginxapp

cat > nginx2.yaml << EOF
---
apiVersion: v1
kind: ReplicationController
metadata:
  name: nginx-web
spec:
  replicas: 1
  selector:
    name: nginx
  template:
    metadata:
      labels:
        name: nginx
    spec:
      nodeSelector:
        deploy.type: nginxapp #根据标签部署
      containers:
        - name: nginx
          image: nginx:1.19.6
          ports:
            - containerPort: 80
---
apiVersion: v1
kind: Service
metadata:
  name: nginx-service-nodeport
spec:
  ports:
    - port: 80
      targetPort: 80
      nodePort: 30001
      protocol: TCP
  type: NodePort
  selector:
    name: nginx
EOF

kubectl apply -f nginx-work2.yaml
#查看所有名字空间的 Pod
kubectl get pods -A
#查看pod的描述信息
kubectl describe pod <podname> -n <namespace> 
#删除Pod
kubectl delete pod <podname> -n <namespace>