前言
准备好 【k8s-1.20.x安装】前置工作 章节中的6台机器
1. 基本组件安装
所有节点安装Docker-ce 19.03
yum install -y docker-ce-19.03.14-3.el7 docker-ce-cli-19.03.14-3.el7
所有节点设置开机自启动Docker
mkdir /etc/docker
cat > /etc/docker/daemon.json <<EOF
{
"exec-opts" : ["native.cgroupdriver=systemd"]
}
EOF
systemctl daemon-reload && systemctl enable --now docker
安装k8s组件
yum list kubeadm.x86_64 --showduplicates | sort -r
所有节点安装最新版本kubeadm
yum install kubeadm -y
默认配置的pause镜像使用gcr.io仓库，国内可能无法访问，所以这里配置Kubelet使用阿里云的pause镜像：
cat >/etc/sysconfig/kubelet<<EOF
KUBELET_EXTRA_ARGS="--pod-infra-container-image=registry.cn-hangzhou.aliyuncs.com/google_containers/pause-amd64:3.2"
EOF
设置Kubelet开机自启动
systemctl daemon-reload
systemctl enable --now kubelet
2. 高可用组件安装
注意：如果不是高可用集群或者在云上安装，haproxy和keepalived无需安装 所有Master节点通过yum安装HAProxy和KeepAlived：
yum install keepalived haproxy -y
所有Master节点配置HAProxy（详细配置参考HAProxy文档，所有Master节点的HAProxy配置相同）：
[root@k8s-master01 etc]# mkdir /etc/haproxy
[root@k8s-master01 etc]# vim /etc/haproxy/haproxy.cfg
global
maxconn 2000
ulimit-n 16384
log 127.0.0.1 local0 err
stats timeout 30s
defaults
log global
mode http
option httplog
timeout connect 5000
timeout client 50000
timeout server 50000
timeout http-request 15s
timeout http-keep-alive 15s
frontend monitor-in
bind *:33305
mode http
option httplog
monitor-uri /monitor
frontend k8s-master
bind 0.0.0.0:16443
bind 127.0.0.1:16443
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 192.168.0.201:6443 check
server k8s-master02 192.168.0.202:6443 check
server k8s-master03 192.168.0.203:6443 check
所有Master节点配置KeepAlived，配置不一样，注意区分 注意每个节点的IP和网卡（interface参数） Master01节点的配置：
[root@k8s-master01 etc]# mkdir /etc/keepalived
[root@k8s-master01 ~]# vim /etc/keepalived/keepalived.conf
! Configuration File for keepalived
global_defs {
router_id LVS_DEVEL
script_user root
enable_script_security
}
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 eth1
mcast_src_ip 192.168.0.201
virtual_router_id 51
priority 101
advert_int 2
authentication {
auth_type PASS
auth_pass K8SHA_KA_AUTH
}
virtual_ipaddress {
192.168.0.206
}
track_script {
chk_apiserver
}
}
Master02节点的配置：
! Configuration File for keepalived
global_defs {
router_id LVS_DEVEL
script_user root
enable_script_security
}
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 eth1
mcast_src_ip 192.168.0.202
virtual_router_id 51
priority 100
advert_int 2
authentication {
auth_type PASS
auth_pass K8SHA_KA_AUTH
}
virtual_ipaddress {
192.168.0.206
}
track_script {
chk_apiserver
}
}
Master03节点的配置：
! Configuration File for keepalived
global_defs {
router_id LVS_DEVEL
script_user root
enable_script_security
}
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 eth1
mcast_src_ip 192.168.0.203
virtual_router_id 51
priority 100
advert_int 2
authentication {
auth_type PASS
auth_pass K8SHA_KA_AUTH
}
virtual_ipaddress {
192.168.0.206
}
track_script {
chk_apiserver
}
}
配置KeepAlived健康检查文件：
[root@k8s-master01 keepalived]# cat /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
启动haproxy和keepalived
[root@k8s-master01 keepalived]# systemctl daemon-reload
[root@k8s-master01 keepalived]# systemctl enable --now haproxy
[root@k8s-master01 keepalived]# systemctl enable --now keepalived
检查haproxy是否成功启动
telnet -ntpl | grep 16443
检查keepalived是否启动成功
[root@k8s-1 ~]# telnet 192.168.0.206 16443
Trying 192.168.0.206...
Connected to 192.168.0.206.
Escape character is '^]'.
Connection closed by foreign host.
# 看到有 '^]' 就是成功了
3. 集群初始化
Master01节点创建new.yaml配置文件如下：
apiVersion: kubeadm.k8s.io/v1beta2
bootstrapTokens:
- groups:
- system:bootstrappers:kubeadm:default-node-token
token: 7t2weq.bjbawausm0jaxury
ttl: 24h0m0s
usages:
- signing
- authentication
kind: InitConfiguration
localAPIEndpoint:
advertiseAddress: 192.168.0.201
bindPort: 6443
nodeRegistration:
criSocket: /var/run/dockershim.sock
name: k8s-master01
taints:
- effect: NoSchedule
key: node-role.kubernetes.io/master
---
apiServer:
certSANs:
- 192.168.0.206
timeoutForControlPlane: 4m0s
apiVersion: kubeadm.k8s.io/v1beta2
certificatesDir: /etc/kubernetes/pki
clusterName: kubernetes
controlPlaneEndpoint: 192.168.0.206:16443
controllerManager: {}
dns:
type: CoreDNS
etcd:
local:
dataDir: /var/lib/etcd
imageRepository: registry.cn-hangzhou.aliyuncs.com/google_containers
kind: ClusterConfiguration
kubernetesVersion: v1.20.1
networking:
dnsDomain: cluster.local
podSubnet: 172.168.0.0/16
serviceSubnet: 10.96.0.0/12
scheduler: {}
注意：如果不是高可用集群，192.168.0.206:16443改为master01的地址，16443改为apiserver的端口，默认是6443，注意更改v1.20.1为自己服务器kubeadm的版本：kubeadm version 将new.yaml文件复制到其他master节点，之后所有Master节点提前下载镜像，可以节省初始化时间：
三个master节点执行：
kubeadm config images pull --config /root/new.yaml
所有节点设置开机自启动kubelet
systemctl enable --now kubelet（如果启动失败无需管理，初始化成功以后即可启动）
Master01节点初始化，初始化以后会在/etc/kubernetes目录下生成对应的证书和配置文件，之后其他Master节点加入Master01即可：
kubeadm init --config /root/new.yaml --upload-certs
初始化成功以后，会产生Token值，用于其他节点加入时使用，因此要记录下初始化成功生成的token值（令牌值）：
Your Kubernetes control-plane has initialized successfully!
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
Alternatively, if you are the root user, you can run:
export KUBECONFIG=/etc/kubernetes/admin.conf
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 the control-plane node running the following command on each as root:
kubeadm join 192.168.0.206:16443 --token 7t2weq.bjbawausm0jaxury \
--discovery-token-ca-cert-hash sha256:43d6d361aad79ec0df6eed9cf38e732c29f71bd1a0d691064a0667ec51054558 \
--control-plane --certificate-key cf9e188c8dcdfee745c6b7d4eed45a166ea8f3e1908c5ab2364a9fdc657210bc
Please note that the certificate-key gives access to cluster sensitive data, keep it secret!
As a safeguard, uploaded-certs will be deleted in two hours; If necessary, you can use
"kubeadm init phase upload-certs --upload-certs" to reload certs afterward.
Then you can join any number of worker nodes by running the following on each as root:
kubeadm join 192.168.0.206:16443 --token 7t2weq.bjbawausm0jaxury \
--discovery-token-ca-cert-hash sha256:43d6d361aad79ec0df6eed9cf38e732c29f71bd1a0d691064a0667ec51054558
Master01节点配置环境变量，用于访问Kubernetes集群：
cat <<EOF >> /root/.bashrc
export KUBECONFIG=/etc/kubernetes/admin.conf
EOF
source /root/.bashrc
查看节点状态：
[root@k8s-1 ~]# kubectl get nodes
NAME STATUS ROLES AGE VERSION
k8s-master01 NotReady control-plane,master 3m46s v1.20.1
采用初始化安装方式，所有的系统组件均以容器的方式运行并且在kube-system命名空间内，此时可以查看Pod状态：
[root@k8s-1 ~]# kubectl get pods -n kube-system -o wide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
coredns-54d67798b7-ggzfs 0/1 Pending 0 5m18s <none> <none> <none> <none>
coredns-54d67798b7-sfsrd 0/1 Pending 0 5m18s <none> <none> <none> <none>
etcd-k8s-master01 1/1 Running 0 5m12s 192.168.0.201 k8s-master01 <none> <none>
kube-apiserver-k8s-master01 1/1 Running 0 5m12s 192.168.0.201 k8s-master01 <none> <none>
kube-controller-manager-k8s-master01 1/1 Running 0 5m12s 192.168.0.201 k8s-master01 <none> <none>
kube-proxy-rtzs6 1/1 Running 0 5m17s 192.168.0.201 k8s-master01 <none> <none>
kube-scheduler-k8s-master01 1/1 Running 0 5m12s 192.168.0.201 k8s-master01 <none> <none>
[root@k8s-1 ~]# kubectl get svc
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
kubernetes ClusterIP 10.96.0.1 <none> 443/TCP 8m50s
4. 高可用Master
初始化其他master加入集群
kubeadm join 192.168.0.206:16443 --token 7t2weq.bjbawausm0jaxury \
--discovery-token-ca-cert-hash sha256:43d6d361aad79ec0df6eed9cf38e732c29f71bd1a0d691064a0667ec51054558 \
--control-plane --certificate-key cf9e188c8dcdfee745c6b7d4eed45a166ea8f3e1908c5ab2364a9fdc657210bc
5.添加Node
添加Node节点
kubeadm join 192.168.0.206:16443 --token 7t2weq.bjbawausm0jaxury \
--discovery-token-ca-cert-hash sha256:43d6d361aad79ec0df6eed9cf38e732c29f71bd1a0d691064a0667ec51054558
查看集群状态：
[root@k8s-master01]# kubectl get node
NAME STATUS ROLES AGE VERSION
k8s-master01 NotReady control-plane,master 8m53s v1.20.0
k8s-master02 NotReady control-plane,master 2m25s v1.20.0
k8s-master03 NotReady control-plane,master 31s v1.20.0
k8s-node01 NotReady <none> 32s v1.20.0
k8s-node02 NotReady <none> 88s v1.20.0
6. Callico安装
以下步骤只在master01执行
cd /root/k8s-ha-install && git checkout manual-installation-v1.20.x && cd calico/
修改calico-etcd.yaml的以下位置
sed -i 's#etcd_endpoints: "http://<ETCD_IP>:<ETCD_PORT>"#etcd_endpoints: "https://192.168.0.201:2379,https://192.168.0.202:2379,https://192.168.0.203:2379"#g' calico-etcd.yaml
ETCD_CA=`cat /etc/kubernetes/pki/etcd/ca.crt | base64 | tr -d '\n'`
ETCD_CERT=`cat /etc/kubernetes/pki/etcd/server.crt | base64 | tr -d '\n'`
ETCD_KEY=`cat /etc/kubernetes/pki/etcd/server.key | base64 | tr -d '\n'`
sed -i "s@# etcd-key: null@etcd-key: ${ETCD_KEY}@g; s@# etcd-cert: null@etcd-cert: ${ETCD_CERT}@g; s@# etcd-ca: null@etcd-ca: ${ETCD_CA}@g" calico-etcd.yaml
sed -i 's#etcd_ca: ""#etcd_ca: "/calico-secrets/etcd-ca"#g; s#etcd_cert: ""#etcd_cert: "/calico-secrets/etcd-cert"#g; s#etcd_key: "" #etcd_key: "/calico-secrets/etcd-key" #g' calico-etcd.yaml
POD_SUBNET=`cat /etc/kubernetes/manifests/kube-controller-manager.yaml | grep cluster-cidr= | awk -F= '{print $NF}'`
sed -i 's@# - name: CALICO_IPV4POOL_CIDR@- name: CALICO_IPV4POOL_CIDR@g; s@# value: "192.168.0.0/16"@ value: '"${POD_SUBNET}"'@g' calico-etcd.yaml
创建calico
kubectl apply -f calico-etcd.yaml
7. Metrics Server部署
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。 将Master01节点的front-proxy-ca.crt复制到所有Node节点
scp /etc/kubernetes/pki/front-proxy-ca.crt k8s-node01:/etc/kubernetes/pki/front-proxy-ca.crt
scp /etc/kubernetes/pki/front-proxy-ca.crt k8s-node(其他节点自行拷贝):/etc/kubernetes/pki/front-proxy-ca.crt
安装metrics server
cd /root/k8s-ha-install/metrics-server-0.4.x-kubeadm/
[root@k8s-master01 metrics-server-0.4.x-kubeadm]# kubectl create -f comp.yaml
serviceaccount/metrics-server created
clusterrole.rbac.authorization.k8s.io/system:aggregated-metrics-reader created
clusterrole.rbac.authorization.k8s.io/system:metrics-server created
rolebinding.rbac.authorization.k8s.io/metrics-server-auth-reader created
clusterrolebinding.rbac.authorization.k8s.io/metrics-server:system:auth-delegator created
clusterrolebinding.rbac.authorization.k8s.io/system:metrics-server created
service/metrics-server created
deployment.apps/metrics-server created
apiservice.apiregistration.k8s.io/v1beta1.metrics.k8s.io created
等待kube-system命令空间下的Pod全部启动后，查看状态
[root@k8s-master01 metrics-server-0.4.x-kubeadm]# kubectl top node
NAME CPU(cores) CPU% MEMORY(bytes) MEMORY%
k8s-master01 109m 2% 1296Mi 33%
k8s-master02 99m 2% 1124Mi 29%
k8s-master03 104m 2% 1082Mi 28%
k8s-node01 55m 1% 761Mi 19%
k8s-node02 53m 1% 663Mi 17%
