二进制部署k8s（1.18版本）+高可用版本测试
部署说明
部署说明
部署规划
| 主机 | ip | 作用 | 部署的软件 | 备注 |
|---|---|---|---|---|
| centos7-node4 | 172.17.17.85 | master | kube-apiserver,kube-controller-manager,kube-scheduler,docker,etcd | 后期介绍master扩容 |
| centos7-node5 | 172.17.17.86 | node | kubelet,kube-proxy,docker,etcd | 后期介绍master扩容 |
| centos7-node6 | 172.17.17.87 | node | kubelet,kube-proxy,docker,etcd | 后期介绍master扩容 |
系统初始化（所有节点执行）
-
软件安装路径默认路径为
/data
# 更新yum源
yum -y install wget && wget -O /etc/yum.repos.d/CentOS-Base.repo https://mirrors.aliyun.com/repo/Centos-7.repo && yum -y install epel-release
# 关闭selinux，firewalld，swap
sed -i 's/enforcing/disabled/' /etc/selinux/config
systemctl disable firewalld && systemctl stop firewalld
sed -ri 's/.*swap.*/#&/' /etc/fstab && swapoff -a
# 设置好主机名与主机名解析
cat >> /etc/hosts << EOF
172.17.17.85 k8s-master-1
172.17.17.89 k8s-master-2
172.17.17.86 k8s-node5
172.17.17.87 k8s-node6
EOF
# 将桥接的IPv4流量传递到iptables的链
modprobe br_netfilter
cat > /etc/sysctl.d/k8s.conf << EOF
net.bridge.bridge-nf-call-ip6tables = 1
net.bridge.bridge-nf-call-iptables = 1
net.ipv4.ip_forward = 1
EOF
sysctl -p /etc/sysctl.d/k8s.conf #配置生效
#时间同步
yum install chrony -y && systemctl enable chronyd && systemctl start chronyd
timedatectl set-timezone Asia/Shanghai && timedatectl set-ntp yes
生成etcd证书配置
准备cfssl证书管理工具，使用json文件生成证书，相比openssl更方便使用
# 软件安装
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
wget https://pkg.cfssl.org/R1.2/cfssl-certinfo_linux-amd64 -O /usr/local/bin/cfssl-certinfo
chmod +x /usr/local/bin/cfssl*
准备ca与证书配置
mkdir -p ~/TLS/{etcd,k8s} && cd ~/TLS/etcd
# 自签CA配置文件
cat > ca-config.json << EOF
{
"signing": {
"default": {
"expiry": "87600h"
},
"profiles": {
"www": {
"expiry": "87600h",
"usages": [
"signing",
"key encipherment",
"server auth",
"client auth"
]
}
}
}
}
EOF
# 自签csr配置文件
cat > ca-csr.json << EOF
{
"CN": "etcd CA",
"key": {
"algo": "rsa",
"size": 2048
},
"ca": {
"expiry": "87600h"
},
"names": [
{
"C": "CN",
"L": "BJ",
"ST": "BeiJing"
}
]
}
EOF
# 生成CA证书
[root@k8s-master-1 etcd]# cfssl gencert -initca ca-csr.json | cfssljson -bare ca -
[root@k8s-master-1 etcd]# ls *pem
# 签发ETCD https证书
[root@k8s-master-1 etcd]# cat > server-csr.json << EOF
{
"CN": "etcd",
"hosts": [
"172.17.17.85",
"172.17.17.86",
"172.17.17.87",
"172.17.17.84",
],
"key": {
"algo": "rsa",
"size": 2048
},
"names": [
{
"C": "CN",
"L": "BeiJing",
"ST": "BeiJing"
}
]
}
EOF
注:上述文件hosts字段中IP为所有etcd节点的集群内部通信IP，一个都不能少!为了方便后期扩 容可以多写几个预留的IP。
签发证书
[root@k8s-master-1 etcd]# cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=www server-csr.json | cfssljson -bare server
[root@k8s-master-1 etcd]# ls server*pem #签发证书文件
部署ETCD集群
单个节点配置
# 安装路径准备
mkdir /data/etcd/{bin,cfg,ssl,data} -p
# 二进制文件准备
wget https://github.com/etcd-io/etcd/releases/download/v3.4.9/etcd-v3.4.9-linux-amd64.tar.gz && tar xf etcd-v3.4.9-linux-amd64.tar.gz
mv etcd-v3.4.9-linux-amd64/etcd* /data/etcd/bin/
# 当前节点172.17.17.85配置文件
cat > /data/etcd/cfg/etcd.conf <<EOF
#[Member]
ETCD_NAME="etcd-1"
ETCD_DATA_DIR="/data/etcd/data/default.etcd"
ETCD_LISTEN_PEER_URLS="https://172.17.17.85:2380"
ETCD_LISTEN_CLIENT_URLS="https://172.17.17.85:2379"
#[Clustering]
ETCD_INITIAL_ADVERTISE_PEER_URLS="https://172.17.17.85:2380"
ETCD_ADVERTISE_CLIENT_URLS="https://172.17.17.85:2379"
ETCD_INITIAL_CLUSTER="etcd-1=https://172.17.17.85:2380,etcd-2=https://172.17.17.86:2380,etcd-3=https://172.17.17.87:2380"
ETCD_INITIAL_CLUSTER_TOKEN="etcd-cluster"
ETCD_INITIAL_CLUSTER_STATE="new"
EOF
# systemctl 启动管理文件配置(所有节点配置是一致的)
cat > /usr/lib/systemd/system/etcd.service <<EOF
[Unit]
Description=Etcd Server
After=network.target
After=network-online.target
Wants=network-online.target
[Service]
Type=notify
EnvironmentFile=/data/etcd/cfg/etcd.conf
ExecStart=/data/etcd/bin/etcd \
--cert-file=/data/etcd/ssl/server.pem \
--key-file=/data/etcd/ssl/server-key.pem \
--peer-cert-file=/data/etcd/ssl/server.pem \
--peer-key-file=/data/etcd/ssl/server-key.pem \
--trusted-ca-file=/data/etcd/ssl/ca.pem \
--peer-trusted-ca-file=/data/etcd/ssl/ca.pem \
--logger=zap
Restart=on-failure
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
EOF
# 拷贝证书文件
mv ~/TLS/etcd/*pem /data/etcd/ssl
# 启动当前节点
systemctl daemon-reload && systemctl enable etcd && systemctl start etcd
配置文件字段介绍
ETCD_NAME:节点名称，集群中唯一 ETCD_DATA_DIR:数据目录 ETCD_LISTEN_PEER_URLS:集群通信监听地址 ETCD_LISTEN_CLIENT_URLS:客户端访问监听地址 ETCD_INITIAL_ADVERTISE_PEER_URLS:集群通告地址 ETCD_ADVERTISE_CLIENT_URLS:客户端通告地址 ETCD_INITIAL_CLUSTER:集群节点地址 ETCD_INITIAL_CLUSTER_TOKEN:集群Token ETCD_INITIAL_CLUSTER_STATE:加入集群的当前状态，new是新集群，existing表示加入已有集 群
其余两个节点配置
-
数据分发（从172.17.17.85分发到86，87两个节点）
scp -r /data/etcd/ root@172.17.17.86:/data/ scp -r /data/etcd/ root@172.17.17.87:/data/
scp /usr/lib/systemd/system/etcd.service root@172.17.17.86:/usr/lib/systemd/system/
scp /usr/lib/systemd/system/etcd.service root@172.17.17.87:/usr/lib/systemd/system/
然后在节点2和节点3分别修改etcd.conf配置文件中的节点名称和当前服务器IP：
vi /data/etcd/cfg/etcd.conf
#[Member]
ETCD_NAME="etcd-1"# 修改此处，节点2改为etcd-2，节点3改为etcd-3
ETCD_DATA_DIR="/var/lib/etcd/default.etcd"
ETCD_LISTEN_PEER_URLS="https://172.17.17.86:2380"# 修改此处为当前服务器
IPETCD_LISTEN_CLIENT_URLS="https://172.17.17.86:2379"# 修改此处为当前服务器IP
#[Clustering]
ETCD_INITIAL_ADVERTISE_PEER_URLS="https://172.17.17.86:2380"# 修改此处为当前服务器
IPETCD_ADVERTISE_CLIENT_URLS="https://172.17.17.86:2379"# 修改此处为当前服务器
IPETCD_INITIAL_CLUSTER="etcd-1=https://172.17.17.85:2380,etcd-2=https://172.17.17.86:2380,etcd-3=https://172.17.17.87:2380"
ETCD_INITIAL_CLUSTER_TOKEN="etcd-cluster"
ETCD_INITIAL_CLUSTER_STATE="new"
最后启动etcd并设置开机启动，同上。
systemctl daemon-reload && systemctl enable etcd && systemctl start etcd
验证Etcd部署状态是否成功
[root@k8s-master-1 default.etcd]# ETCDCTL_API=3 /data/etcd/bin/etcdctl --cacert=/data/etcd/ssl/ca.pem --cert=/data/etcd/ssl/server.pem --key=/data/etcd/ssl/server-key.pem --endpoints="https://172.17.17.85:2379,https://172.17.17.86:2379,https://172.17.17.87:2379" endpoint health
正常返回结果
https://172.17.17.87:2379 is healthy: successfully committed proposal: took = 32.593008ms https://172.17.17.85:2379 is healthy: successfully committed proposal: took = 39.390838ms https://172.17.17.86:2379 is healthy: successfully committed proposal: took = 38.243128ms
集群异常排查
1. 查看/var/log/message日志或者journalctl -xe -f -uetcd
2. 一般配置文件没问题的话就ok,最大的问题还有一点就是网络通信和防火墙，注意响应的策略放开即可
3.如果集群ID重复错误 删除这个目录/data/etcd/data/default.etcd
所有节点安装docker
# 下载和解压docker二进制文件
wget https://download.docker.com/linux/static/stable/x86_64/docker-19.03.9.tgz && tar xf docker-19.03.9.tgz
# 转移可执行文件
mv docker/* /usr/bin/
# 配置systemd管理docker (其余的两个节点也需要安装)
cat > /usr/lib/systemd/system/docker.service << EOF
[Unit]
Description=Docker Application Container Engine
Documentation=https://docs.docker.com
After=network-online.target firewalld.service
Wants=network-online.target
[Service]
Type=notify
ExecStart=/usr/bin/dockerd
ExecReload=/bin/kill -s HUP $MAINPID
LimitNOFILE=infinity
LimitNPROC=infinity
LimitCORE=infinity
TimeoutStartSec=0
Delegate=yes
KillMode=process
Restart=on-failure
StartLimitBurst=3
StartLimitInterval=60s
[Install]
WantedBy=multi-user.target
EOF
docker配置与启动
# 配置docker阿里云镜像加速和存储路径（graph）
mkdir /etc/docker
cat > /etc/docker/daemon.json << EOF
{
"graph": "/data/docker",
"registry-mirrors": ["https://b9pmyelo.mirror.aliyuncs.com"]
}
EOF
# 服务启动
systemctl daemon-reload && systemctl restart docker && systemctl enable docker
k8s master节点的安装与部署
当前部署master节点 ip: 172.17.17.85
生成k8s证书配置 自签证书颁发机构（CA）
cd ~/TLS/k8s
cat > ca-config.json <<EOF
{
"signing":{
"default":{
"expiry":"87600h"
},
"profiles":{
"kubernetes":{
"expiry":"87600h",
"usages":[
"signing",
"key encipherment",
"server auth",
"client auth"
]
}
}
}
}
EOF
cat > ca-csr.json <<EOF
{
"CN":"kubernetes",
"key":{
"algo":"rsa",
"size":2048
},
"names":[
{
"C":"CN",
"L":"Beijing",
"ST":"Beijing",
"O":"k8s",
"OU":"System"
}
]
}
EOF
# 生成CA证书
cfssl gencert -initca ca-csr.json | cfssljson -bare ca -
使用自签CA签发kube-apiserver HTTPS证书
cd ~/TLS/k8s
cat > server-csr.json << EOF
{
"CN":"kubernetes",
"hosts":[
"10.0.0.1",
"172.0.0.1",
"127.0.0.1",
"172.17.17.85",
"172.17.17.86",
"172.17.17.87",
"172.17.17.89",
"172.17.17.84",
"172.17.17.83",
"kubernetes",
"kubernetes.default",
"kubernetes.default.svc",
"kubernetes.default.svc.cluster",
"kubernetes.default.svc.cluster.local"
],
"key":{
"algo":"rsa",
"size":2048
},
"names":[
{
"C":"CN",
"L":"BeiJing",
"ST":"BeiJing",
"O":"k8s",
"OU":"System"
}
]
}
EOF
注:上述文件hosts字段中IP为所有Master/LB/VIP IP，一个都不能少!为了方便后期扩容可以多 写几个预留的IP。
生成apiserver证书
cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=kubernetes server-csr.json | cfssljson -bare server
ls *pem
从Github下载二进制文件
# 创建软件目录
mkdir -p /data/kubernetes/{cfg,bin,ssl,logs}
# 文件下载与拷贝
wget https://dl.k8s.io/v1.18.4/kubernetes-server-linux-amd64.tar.gz && tar xf kubernetes-server-linux-amd64.tar.gz
cp kubernetes/server/bin/kube-apiserver /data/kubernetes/bin/
cp kubernetes/server/bin/kube-controller-manager /data/kubernetes/bin/
cp kubernetes/server/bin/kube-scheduler /data/kubernetes/bin/
cp kubernetes/server/bin/kubectl /usr/bin/
部署kube-apiserver
# 创建配置文件
cat > /data/kubernetes/cfg/kube-apiserver.conf << EOF
KUBE_APISERVER_OPTS="--logtostderr=false \
--v=2 \
--log-dir=/data/kubernetes/logs \
--etcd-servers=https://172.17.17.85:2379,https://172.17.17.86:2379,https://172.17.17.87:2379 \
--bind-address=172.17.17.85 \
--secure-port=6443 \
--advertise-address=172.17.17.85 \
--allow-privileged=true \
--service-cluster-ip-range=10.0.0.0/24 \
--enable-admission-plugins=NamespaceLifecycle,LimitRanger,ServiceAccount,ResourceQuota,NodeRestriction \
--authorization-mode=RBAC,Node \
--enable-bootstrap-token-auth=true \
--token-auth-file=/data/kubernetes/cfg/token.csv \
--service-node-port-range=30000-32767 \
--kubelet-client-certificate=/data/kubernetes/ssl/server.pem \
--kubelet-client-key=/data/kubernetes/ssl/server-key.pem \
--tls-cert-file=/data/kubernetes/ssl/server.pem \
--tls-private-key-file=/data/kubernetes/ssl/server-key.pem \
--client-ca-file=/data/kubernetes/ssl/ca.pem \
--service-account-key-file=/data/kubernetes/ssl/ca-key.pem \
--etcd-cafile=/data/etcd/ssl/ca.pem \
--etcd-certfile=/data/etcd/ssl/server.pem \
--etcd-keyfile=/data/etcd/ssl/server-key.pem \
--audit-log-maxage=30 \
--audit-log-maxbackup=3 \
--audit-log-maxsize=100 \
--audit-log-path=/data/kubernetes/logs/k8s-audit.log"
EOF
# 拷贝证书
mv ~/TLS/k8s/*pem /data/kubernetes/ssl/
注意事项：
--logtostderr:启用日志 ---v:日志等级 --log-dir:日志目录 --etcd-servers:etcd集群地址 --bind-address:监听地址 --secure-port:https安全端口 --advertise-address:集群通告地址 --allow-privileged:启用授权 --service-cluster-ip-range:Service虚拟IP地址段
--enable-admission-plugins:准入控制模块
--authorization-mode:认证授权，启用RBAC授权和节点自管理
--enable-bootstrap-token-auth:启用TLS bootstrap机制
--token-auth-file:bootstrap token文件
--service-node-port-range:Service nodeport类型默认分配端口范围
--kubelet-client-xxx:apiserver访问kubelet客户端证书
--tls-xxx-file:apiserver https证书
--etcd-xxxfile:连接Etcd集群证书 --audit-log-xxx:审计日志
启用TLS Bootstrap机制
TLS Bootstraping：Master apiserver启用TLS认证后，Node节点kubelet和kube-proxy要与kube-apiserver进行通信，必须使用CA签发的有效证书才可以，当Node节点很多时，这种客户端证书颁发需要大量工作，同样也会增加集群扩展复杂度。为了简化流程，Kubernetes引入了TLS bootstraping机制来自动颁发客户端证书，kubelet会以一个低权限用户自动向apiserver申请证书，kubelet的证书由apiserver动态签署。所以强烈建议在Node上使用这种方式，目前主要用于kubelet，kube-proxy还是由我们统一颁发一个证书。TLS bootstraping 工作流程：
-
根据上述配置token文件
cat > /data/kubernetes/cfg/token.csv << EOF
2b4b65d2e33e24dc0beafddda6dd4b23,kubelet-bootstrap,10001,"system:node-bootstrapper"
EOF
格式:token，用户名，UID，用户组 token也可自行生成替换:
head -c 16 /dev/urandom | od -An -t x | tr -d ' '
使用systemctl管理apiserver
生成配置文件
cat > /usr/lib/systemd/system/kube-apiserver.service << EOF
[Unit]
Description=Kubernetes API Server
Documentation=https://github.com/kubernetes/kubernetes
[Service]
EnvironmentFile=/data/kubernetes/cfg/kube-apiserver.conf
ExecStart=/data/kubernetes/bin/kube-apiserver $KUBE_APISERVER_OPTS
Restart=on-failure
[Install]
WantedBy=multi-user.target
EOF
启动并设置开机自启动
systemctl daemon-reload && systemctl start kube-apiserver && systemctl enable kube-apiserver
-
授权kubelet-bootstrap用户允许请求证书
- kubectl create clusterrolebinding kubelet-bootstrap --clusterrole=system:node-bootstrapper --user=kubelet-bootstrap
部署kube-controller-manager
创建配置文件
cat > /data/kubernetes/cfg/kube-controller-manager.conf << EOF KUBE_CONTROLLER_MANAGER_OPTS="--logtostderr=false \ --v=2 \ --log-dir=/data/kubernetes/logs \ --leader-elect=true \ --master=127.0.0.1:8080 \ --bind-address=127.0.0.1 \ --allocate-node-cidrs=true \ --cluster-cidr=10.244.0.0/16 \ --service-cluster-ip-range=10.0.0.0/24 \ --cluster-signing-cert-file=/data/kubernetes/ssl/ca.pem \ --cluster-signing-key-file=/data/kubernetes/ssl/ca-key.pem \ --root-ca-file=/data/kubernetes/ssl/ca.pem \ --service-account-private-key-file=/data/kubernetes/ssl/ca-key.pem \ --experimental-cluster-signing-duration=87600h0m0s" EOF
--master:通过本地非安全本地端口8080连接apiserver。
--leader-elect:当该组件启动多个时，自动选举(HA)
--cluster-signing-cert-file/--cluster-signing-key-file：自动为kubelet颁发证书的CA，与apiserver保持一致
systemctl管理controller-manager
vim /data/kubernetes/cfg/kube-controller-manager.conf
KUBE_CONTROLLER_MANAGER_OPTS="--logtostderr=false \ --v=2 \
--log-dir=/data/kubernetes/logs \ --leader-elect=true \
--master=127.0.0.1:8080 \ --bind-address=127.0.0.1 \
--allocate-node-cidrs=true \ --cluster-cidr=10.244.0.0/16 \ --service-cluster-ip-range=10.0.0.0/24 \ --cluster-signing-cert-file=/data/kubernetes/ssl/ca.pem \ --cluster-signing-key-file=/data/kubernetes/ssl/ca-key.pem \ --root-ca-file=/data/kubernetes/ssl/ca.pem \ --service-account-private-key-file=/data/kubernetes/ssl/ca-key.pem \ --experimental-cluster-signing-duration=87600h0m0s"
vim /usr/lib/systemd/system/kube-controller-manager.service
[Unit] Description=Kubernetes Controller Manager Documentation=https://github.com/kubernetes/kubernetes [Service] EnvironmentFile=/data/kubernetes/cfg/kube-controller-manager.conf ExecStart=/data/kubernetes/bin/kube-controller-manager $KUBE_CONTROLLER_MANAGER_OPTS Restart=on-failure [Install] WantedBy=multi-user.target
启动&开机自启
systemctl daemon-reload && systemctl start kube-controller-manager && systemctl enable kube-controller-manager
部署kube-scheduler
创建配置文件
cat > /data/kubernetes/cfg/kube-scheduler.conf << EOF
KUBE_SCHEDULER_OPTS="--logtostderr=false \\
--v=2 \\
--log-dir=/data/kubernetes/logs \\
--leader-elect \\
--master=127.0.0.1:8080 \\
--bind-address=127.0.0.1"
EOF
--master：通过本地非安全本地端口8080连接apiserver。
--leader-elect：当该组件启动多个时，自动选举（HA）
systemctl管理kube-scheduler
cat > /usr/lib/systemd/system/kube-scheduler.service << EOF
[Unit]
Description=Kubernetes Scheduler
Documentation=https://github.com/kubernetes/kubernetes
[Service]
EnvironmentFile=/data/kubernetes/cfg/kube-scheduler.conf
ExecStart=/data/kubernetes/bin/kube-scheduler $KUBE_SCHEDULER_OPTS
Restart=on-failure
[Install]
WantedBy=multi-user.target EOF
-
启动&开机自启
systemctl daemon-reload && systemctl start kube-scheduler && systemctl enable kube-scheduler
至此master部署完成，集群状态查看
kubectl get cs
返回如下结果，证明mater部署ok
NAME STATUS MESSAGE ERROR
controller-manager Healthy ok
scheduler Healthy ok
etcd-2 Healthy {"health":"true"}
etcd-0 Healthy {"health":"true"}
etcd-1 Healthy {"health":"true"}
部署WorkNode
当前操作节点是： 172.17.17.85(将这个master也作为node)
-
需要的软件：
-
kubelet
-
kube-proxy
-
基础软件包准备
# 创建软件目录
mkdir -p /data/kubernetes/{cfg,bin,ssl,logs}
# 文件下载与拷贝
wget https://dl.k8s.io/v1.18.4/kubernetes-server-linux-amd64.tar.gz && tar xf kubernetes-server-linux-amd64.tar.gz
cp kubernetes/server/bin/kube-proxy /data/kubernetes/bin/
cp kubernetes/server/bin/kubelet /data/kubernetes/bin/
部署kubelet
创建kubelet配置文件
cat > /data/kubernetes/cfg/kubelet.conf << EOF
KUBELET_OPTS="--logtostderr=false \\ --v=2 \\ --log-dir=/data/kubernetes/logs \\ --hostname-override=k8s-master \\ --network-plugin=cni \\ --kubeconfig=/data/kubernetes/cfg/kubelet.kubeconfig \\ --bootstrap-kubeconfig=/data/kubernetes/cfg/bootstrap.kubeconfig \\ --config=/data/kubernetes/cfg/kubelet-config.yml \\ --cert-dir=/data/kubernetes/ssl \\ --pod-infra-container-image=lizhenliang/pause-amd64:3.0"
--hostname-override:显示名称，集群中唯一
--network-plugin:启用CNI
--kubeconfig:空路径，会自动生成，后面用于连接apiserver
--bootstrap-kubeconfig:首次启动向apiserver申请证书
--config:配置参数文件
--cert-dir:kubelet证书生成目录
--pod-infra-container-image:管理Pod网络容器的镜像
创建参数配置文件
cat > /data/kubernetes/cfg/kubelet-config.yml << EOF
kind: KubeletConfiguration
apiVersion: kubelet.config.k8s.io/v1beta1
address: 0.0.0.0
port: 10250
readOnlyPort: 10255
cgroupDriver: cgroupfs
clusterDNS:
- 10.0.0.2
clusterDomain: cluster.local
failSwapOn: false
authentication:
anonymous:
enabled: false
webhook:
cacheTTL: 2m0s
enabled: true
x509:
clientCAFile: /data/kubernetes/ssl/ca.pem
authorization:
mode: Webhook
webhook:
cacheAuthorizedTTL: 5m0s
cacheUnauthorizedTTL: 30s
evictionHard:
imagefs.available: 15%
memory.available: 100M
nodefs.available: 10%
nodefs.inodesFree: 5%
maxOpenFiles: 1000000
maxPods: 110
生成bootstrap.kubeconfig文件
[root@k8s-master-1 ~]# KUBE_APISERVER="https://172.17.17.85:6443"
[root@k8s-master-1 ~]# TOKEN="2b4b65d2e33e24dc0beafddda6dd4b23"
[root@k8s-master-1 ~]# kubectl config set-cluster kubernetes --certificate-authority=/data/kubernetes/ssl/ca.pem --embed-certs=true --server=${KUBE_APISERVER} --kubeconfig=bootstrap.kubeconfig
[root@k8s-master-1 ~]# kubectl config set-credentials "kubelet-bootstrap" --token=${TOKEN} --kubeconfig=bootstrap.kubeconfig
[root@k8s-master-1 ~]# kubectl config set-context default --cluster=kubernetes --user="kubelet-bootstrap" --kubeconfig=bootstrap.kubeconfig
[root@k8s-master-1 ~]# kubectl config use-context default --kubeconfig=bootstrap.kubeconfig
拷贝到配置文件路径：
[root@k8s-master-1 ~]# cp bootstrap.kubeconfig /data/kubernetes/cfg
systemctl管理kubelet
-
创建启动文件
[root@k8s-master-1 ~]# cat > /usr/lib/systemd/system/kubelet.service << EOF
[Unit]
Description=Kubernetes Kubelet
After=docker.service
[Service]
EnvironmentFile=/data/kubernetes/cfg/kubelet.conf
ExecStart=/data/kubernetes/bin/kubelet \$KUBELET_OPTS
Restart=on-failure
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target EOF
-
启动kubelet&开机自启动
systemctl daemon-reload && systemctl start kubelet && systemctl enable kubelet如有异常，及时查看日志解决，大多数问题会出现在/data/kubernetes/cfg/kubelet-config.yml格式上
批准kubelet证书申请并加入集群
查看kubelet证书请求
[root@k8s-master-1 ~]# kubectl get csr NAME AGE SIGNERNAME REQUESTOR CONDITION node-csr-cUACWJSaXTJHpc1XIscmgbvarl1aZ3Hk79d7qjkII_A 68s kubernetes.io/kube-apiserver-client-kubelet kubelet-bootstrap Pending
批准kubelet证书申请，并加入集群
[root@k8s-master-1 ~]# kubectl certificate approve node-csr-cUACWJSaXTJHpc1XIscmgbvarl1aZ3Hk79d7qjkII_A
查看节点 [root@k8s-master-1 ~]# kubectl get node NAME STATUS ROLES AGE VERSION k8s-master-1 NotReady <none> 4s v1.18.4
注：由于网络插件还没有部署，节点会没有准备就绪 NotReady
部署kube-proxy
创建配置文件
[root@k8s-master-1 ~]# cat > /data/kubernetes/cfg/kube-proxy.conf << EOF KUBE_PROXY_OPTS="--logtostderr=false \ --v=2 \ --log-dir=/data/kubernetes/logs \ --config=/data/kubernetes/cfg/kube-proxy-config.yml" EOF
配置参数文件
[root@k8s-master-1 ~]# cat > /data/kubernetes/cfg/kube-proxy-config.yml << EOF kind: KubeProxyConfiguration apiVersion: kubeproxy.config.k8s.io/v1alpha1 bindAddress: 0.0.0.0 metricsBindAddress: 0.0.0.0:10249 clientConnection: kubeconfig: /data/kubernetes/cfg/kube-proxy.kubeconfig hostnameOverride: k8s-master-1 clusterCIDR: 10.0.0.0/24 EOF
生成kube-proxy.kubeconfig文件
生成kube-proxy证书
cd ~/TLS/k8s/
cat > kube-proxy-csr.json << EOF
{
"CN":"system:kube-proxy",
"hosts":[
],
"key":{
"algo":"rsa",
"size":2048
},
"names":[
{
"C":"CN",
"L":"BeiJing",
"ST":"BeiJing",
"O":"k8s",
"OU":"System"
}
]
}
# 生成证书
cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=kubernetes kube-proxy-csr.json | cfssljson -bare kube-proxy
ls kube-proxy*pem
kube-proxy-key.pem kube-proxy.pem
生成kubeconfig配置文件
KUBE_APISERVER="https://172.17.17.85:6443"
kubectl config set-cluster kubernetes --certificate-authority=/data/kubernetes/ssl/ca.pem --embed-certs=true --server=${KUBE_APISERVER} --kubeconfig=kube-proxy.kubeconfig
kubectl config set-credentials kube-proxy --client-certificate=./kube-proxy.pem --client-key=./kube-proxy-key.pem --embed-certs=true --kubeconfig=kube-proxy.kubeconfig
kubectl config set-context default --cluster=kubernetes --user=kube-proxy --kubeconfig=kube-proxy.kubeconfig
kubectl config use-context default --kubeconfig=kube-proxy.kubeconfig
# 拷贝配置到cfg下
cp kube-proxy.kubeconfig /data/kubernetes/cfg/
systemctl管理kube-proxy
-
创建启动文件
cat > /usr/lib/systemd/system/kube-proxy.service << EOF [Unit] Description=Kubernetes Proxy After=network.target [Service] EnvironmentFile=/data/kubernetes/cfg/kube-proxy.conf ExecStart=/data/kubernetes/bin/kube-proxy $KUBE_PROXY_OPTS Restart=on-failure LimitNOFILE=65536
[Install] WantedBy=multi-user.target EOF
-
设置开机自启动
systemctl daemon-reload && systemctl start kube-proxy && systemctl enable kube-proxy
部署CNI网络
先准备好CNI二进制文件：下载地址：https://github.com/containernetworking/plugins/releases/download/v0.8.6/cni-plugins-linux-amd64-v0.8.6.tgz
wget https://github.com/containernetworking/plugins/releases/download/v0.8.6/cni-plugins-linux-amd64-v0.8.6.tgz && mkdir /opt/cni/bin -p
tar zxvf cni-plugins-linux-amd64-v0.8.6.tgz -C /opt/cni/bin/
-
部署flannel
wget https://raw.githubusercontent.com/coreos/flannel/master/Documentation/kube-flannel.yml
sed -i -r "s#quay.io/coreos/flannel:.*-amd64#lizhenliang/flannel:v0.12.0-amd64#g" kube-flannel.yml
kubectl apply -f kube-flannel.yml
查看部署状态
kubectl get nodes
NAME STATUS ROLES AGE VERSION
k8s-master-1 Ready <none> 79m v1.18.4
部署好网络插件，Node准备就绪
授权apiserver访问kubelet
[root@k8s-master-1 k8s]# cat > apiserver-to-kubelet-rbac.yaml << EOF
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
annotations:
rbac.authorization.kubernetes.io/autoupdate: "true"
labels:
kubernetes.io/bootstrapping: rbac-defaults
name: system:kube-apiserver-to-kubelet
rules:
- apiGroups:
- ""
resources:
- nodes/proxy
- nodes/stats
- nodes/log
- nodes/spec
- nodes/metrics
- pods/log
verbs:
- "*"
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata: kubernetesuthorization.k8s.iot
name: system:kube-apiserver
namespace: ""
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:kube-apiserver-to-kubelet
subjects:
- apiGroup: rbac.authorization.k8s.io
kind: User
name: kubernetes
EOF
## 创建授权
kubectl apply -f apiserver-to-kubelet-rbac.yaml
新增workNode
同步文件和配置
-
将172.17.17.85上的node相关的配置拷贝到172.17.17.86，172.17.17.87上
mkdir -p /data/kubernetes/{cfg,bin,ssl,logs} #在86 87上先创建目录
# kubelet,kube-proxy拷贝
scp /data/kubernetes/bin/kubelet 172.17.17.86:/data/kubernetes/bin/
scp /data/kubernetes/bin/kubelet 172.17.17.87:/data/kubernetes/bin/
scp /data/kubernetes/bin/kube-proxy root@172.17.17.86:/data/kubernetes/bin/
scp /data/kubernetes/bin/kube-proxy root@172.17.17.87:/data/kubernetes/bin/
# cni插件拷贝
scp -rp /opt/cni/ root@172.17.17.86:/opt
scp -rp /opt/cni/ root@172.17.17.87:/opt
# 证书拷贝
scp /data/kubernetes/ssl/ca.pem 172.17.17.86:/data/kubernetes/ssl/
scp /data/kubernetes/ssl/ca.pem 172.17.17.87:/data/kubernetes/ssl/
# 配置文件拷贝
scp /data/kubernetes/cfg/kube-proxy* 172.17.17.86:/data/kubernetes/cfg/
scp /data/kubernetes/cfg/kube-proxy* 172.17.17.87:/data/kubernetes/cfg/
scp /data/kubernetes/cfg/kubelet* 172.17.17.86:/data/kubernetes/cfg/
scp /data/kubernetes/cfg/kubelet* 172.17.17.87:/data/kubernetes/cfg/
scp /data/kubernetes/cfg/bootstrap.kubeconfig 172.17.17.86:/data/kubernetes/cfg/
scp /data/kubernetes/cfg/bootstrap.kubeconfig 172.17.17.87:/data/kubernetes/cfg/
# 启动文件拷贝
scp /usr/lib/systemd/system/kubelet.service 172.17.17.86:/usr/lib/systemd/system/
scp /usr/lib/systemd/system/kubelet.service 172.17.17.87:/usr/lib/systemd/system/
scp /usr/lib/systemd/system/kube-proxy.service 172.17.17.86:/usr/lib/systemd/system/
scp /usr/lib/systemd/system/kube-proxy.service 172.17.17.87:/usr/lib/systemd/system/
删除证书和配置文件 86 87 上操作
rm -rf /data/kubernetes/cfg/kubelet.kubeconfig
rm -f /data/kubernetes/ssl/kubelet*
注：这几个文件是证书申请审批后自动生成的，每个
配置新的Node节点 86 87 上操作
-
修改kubelet和kube-proxy配置文件
vi /data/kubernetes/cfg/kubelet.conf
--hostname-override=k8s-node5
vim /data/kubernetes/cfg/kube-proxy-config.yml
hostnameOverride: k8s-node5
vi /data/kubernetes/cfg/kubelet.conf
--hostname-override=k8s-node6
vi /data/kubernetes/cfg/kube-proxy-config.yml
hostnameOverride: k8s-node6
-
配置kubectl和kube-proxy开机启动
-
systemctl daemon-reload && systemctl start kubelet && systemctl start kube-proxy
systemctl enable kubelet && systemctl enable kube-proxy
在master节点上准许node加入
-
获取准入的node信息
[root@k8s-master-1 k8s]# kubectl get csr NAME AGE SIGNERNAME REQUESTOR CONDITION node-csr-BKIF1VFOrkRKlbKeJc8CbEe22JLgsMwMU6aJ4KCjeMg 2m42s kubernetes.io/kube-apiserver-client-kubelet kubelet-bootstrap Pending node-csr-MAr2KDH13mbed2dLM4QEmZGuikl1ooXW5ksLlkCVtOA 2m45s kubernetes.io/kube-apiserver-client-kubelet kubelet-bootstrap Pending
-
准入node
kubectl certificate approve node-csr-BKIF1VFOrkRKlbKeJc8CbEe22JLgsMwMU6aJ4KCjeMg kubectl certificate approve node-csr-MAr2KDH13mbed2dLM4QEmZGuikl1ooXW5ksLlkCVtOA
查看状态
[root@k8s-master-1 k8s]# kubectl get node NAME STATUS ROLES AGE VERSION k8s-master-1 Ready <none> 72m v1.18.4 k8s-node5 Ready <none> 60s v1.18.4 k8s-node6 Ready <none> 50s v1.18.4
部署Dashboard和CoreDNS
部署Dashboard
wget https://raw.githubusercontent.com/kubernetes/dashboard/v2.0.0-beta8/aio/deploy/recommended.yaml
默认Dashboard只能集群内部访问，修改Service为NodePort类型，暴露到外部
vim recommended.yaml
kind: Service
apiVersion: v1
metadata:
labels:
k8s-app: kubernetes-dashboard
name: kubernetes-dashboard
namespace: kubernetes-dashboard
spec:
ports:
- port: 443
targetPort: 8443
nodePort: 30001
type: NodePort
selector:
k8s-app: kubernetes-dashboard
# 部署dashboard
kubectl apply -f recommended.yml
# 查看状态
[root@k8s-master-1 k8s]# kubectl get pods,svc -n kubernetes-dashboard
NAME READY STATUS RESTARTS AGE
pod/dashboard-metrics-scraper-694557449d-82n2p 0/1 ContainerCreating 0 2m2s
pod/kubernetes-dashboard-9774cc786-2fcvk 0/1 ContainerCreating 0 2m2s
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
service/dashboard-metrics-scraper ClusterIP 10.0.0.107 <none> 8000/TCP 2m2s
service/kubernetes-dashboard NodePort 10.0.0.64 <none> 443:31614/TCP 2m3s
此时可以直接访问https://NodeIP:30001 NodeIP也就是宿主机的IP
-
创建dashboard访问token
-
kubectl create serviceaccount dashboard-admin -n kube-system
kubectl create clusterrolebinding dashboard-admin --clusterrole=cluster-admin --serviceaccount=kube-system:dashboard-admin
kubectl describe secrets -n kube-system $(kubectl -n kube-system get secret | awk '/dashboard-admin/{print $1}') #获取token
部署coreDNS
上传vim coredns.yaml
用于集群内部Service名称解析
kubectl apply -f coredns.yaml
[root@k8s-master-1 k8s]# kubectl get pods -n kube-system
NAME READY STATUS RESTARTS AGE
coredns-5675d5b4d-njxc4 1/1 Running 0 30m
kube-flannel-ds-69w4v 1/1 Running 0 84m
kube-flannel-ds-6twp8 1/1 Running 5 84m
kube-flannel-ds-t6sqv 1/1 Running 0 84m
如果创建不成功报错 failed to set bridge addr: \"cni0\" already has an IP address different from 10.244.3.1/24"
ifconfig cni0 down
ip link delete cni0
网卡删除会自动重建
DNS解析测试：
[root@k8s-master-1 k8s]# kubectl run -it --rm dns-test --image=busybox:1.28.4 sh If you don't see a command prompt, try pressing enter. / # nslookup kubernetes Server: 10.0.0.2 Address 1: 10.0.0.2 kube-dns.kube-system.svc.cluster.local
Name: kubernetes Address 1: 10.0.0.1 kubernetes.default.svc.cluster.local
高可用架构（扩容多Master架构）
Kubernetes作为容器集群系统，通过健康检查+重启策略实现了Pod故障自我修复能力，通过调度算法实现将Pod分布式部署，并保持预期副本数，根据Node失效状态自动在其他Node拉起Pod，实现了应用层的高可用性。
针对Kubernetes集群，高可用性还应包含以下两个层面的考虑：Etcd数据库的高可用性和KubernetesMaster组件的高可用性。而Etcd我们已经采用3个节点组建集群实现高可用，本节将对Master节点高可用进行说明和实施。
Master节点扮演着总控中心的角色，通过不断与工作节点上的Kubelet和kube-proxy进行通信来维护整个集群的健康工作状态。如果Master节点故障，将无法使用kubectl工具或者API做任何集群管理。
Master节点主要有三个服务kube-apiserver、kube-controller-manager和kube-scheduler，其中kube-controller-manager和kube-scheduler组件自身通过选择机制已经实现了高可用，所以Master高可用主要针对kube-apiserver组件，而该组件是以HTTP API提供服务，因此对他高可用与Web服务器类似，增加负载均衡器对其负载均衡即可，并且可水平扩容。
多Master架构图：
扩容流程
新增主机：centos7-node, 角色k8s-master2
-
系统初始化
-
安装docker
-
wget https://download.docker.com/linux/static/stable/x86_64/docker-19.03.9.tgz
tar xf docker-19.03.9.tgz
mv docker/* /usr/bin/
mkdir /data/docker
mkdir /etc/docker
创建ETCD证书目录（mkdir /data/etcd/ssl -p）
拷贝文件，从master-1拷贝到新机器
scp -rp /opt/cni/ 172.17.17.84:/opt/
scp -r /data/kubernetes root@172.17.17.84:/data
scp -r /data/etcd/ssl root@172.17.17.84:/data/etcd
scp /usr/lib/systemd/system/kube* root@172.17.17.84:/usr/lib/systemd/system
scp /usr/bin/kubectl root@172.17.17.84:/usr/bin
scp /usr/lib/systemd/system/docker.service root@172.17.17.84:/usr/lib/systemd/system
删除证书文件
删除kubelet证书和kubeconfig文件
rm -f /data/kubernetes/cfg/kubelet.kubeconfig
rm-f /data/kubernetes/ssl/kubelet*
修改配置文件IP和主机名
$ vim /data/kubernetes/cfg/kube-apiserver.conf
--bind-address=172.17.17.84 \
--advertise-address=172.17.17.84 \
$ vim /data/kubernetes/cfg/kubelet.conf
--hostname-override=k8s-master-2
$ vim /data/kubernetes/cfg/kube-proxy-config.yml
hostnameOverride: k8s-master-2
启动服务
systemctl daemon-reload && systemctl start docker && systemctl start kube-apiserver && systemctl start kube-controller-manager && systemctl start kube-scheduler && systemctl start kubelet && systemctl start kube-proxy
systemctl enable kube-apiserver && systemctl enable docker && systemctl enable kube-controller-manager && systemctl enable kube-scheduler && systemctl enable kubelet && systemctl enable kube-proxy
查看集群状态
[root@k8s-master-1 data]# kubectl get cs
NAME STATUS MESSAGE ERROR
scheduler Healthy ok
controller-manager Healthy ok
etcd-1 Healthy {"health":"true"}
etcd-2 Healthy {"health":"true"}
etcd-0 Healthy {"health":"true"}
k8s-mater1 准入新master节点
[root@k8s-master-1 data]# kubectl get csr
NAME AGE SIGNERNAME REQUESTOR CONDITION node-csr-KUYz4cMykgJVDNgnXt0okzZsJ22YjAuJ8qWnvJrnyXo 19m kubernetes.io/kube-apiserver-client-kubelet kubelet-bootstrap Approved,Issued
[root@k8s-master-1 data]# kubectl certificate approve node-csr-KUYz4cMykgJVDNgnXt0okzZsJ22YjAuJ8qWnvJrnyXo^C
[root@k8s-master-1 data]# kubectl get node
NAME STATUS ROLES AGE VERSION
k8s-master-1 Ready <none> 3d4h v1.18.4
k8s-master-2 Ready <none> 9m14s v1.18.4
k8s-node5 Ready <none> 2d23h v1.18.4
k8s-node6 Ready <none>
部署ngixn负载均衡
Nginx是一个主流Web服务和反向代理服务器，这里用四层实现对apiserver实现负载均衡。Keepalived是一个主流高可用软件，基于VIP绑定实现服务器双机热备，在上述拓扑中，Keepalived主要根据Nginx运行状态判断是否需要故障转移（偏移VIP），例如当Nginx主节点挂掉，VIP会自动绑定在Nginx备节点，从而保证VIP一直可用，实现Nginx高可用。
安装软件包（主/备）
172.17.17.81 和172.17.17.84
yum install epel-release -y
yum install nginx keepalived -y
Nginx配置文件（主/备一样）
# nginx配置
$ vim /etc/nginx/nginx.conf
user nginx;
worker_processes auto;
error_log /var/log/nginx/error.log;
pid /run/nginx.pid;
include /usr/share/nginx/modules/*.conf;
events {
worker_connections 1024;
}
# 四层负载均衡，为两台Master apiserver组件提供负载均衡
stream {
log_format main '$remote_addr $upstream_addr - [$time_local] $status $upstream_bytes_sent';
access_log /var/log/nginx/k8s-access.log main;
upstream k8s-apiserver {
server 192.168.56.14:6443;
server 192.168.56.74:6443;
}
server {
listen 6443;
proxy_pass k8s-apiserver;
}
}
http {
log_format main '$remote_addr - $remote_user [$time_local] "$request" '
'$status $body_bytes_sent "$http_referer" ' '"$http_user_agent" "$http_x_forwarded_for"';
access_log /var/log/nginx/access.log main;
sendfile on;
tcp_nopush on;
tcp_nodelay on;
keepalive_timeout 65;
types_hash_max_size 2048;
include /etc/nginx/mime.types;
default_type application/octet-stream;
server {
listen 80;
server_name _;
location / {
}
}
}
keepalived配置文件（Nginx Master)
global_defs {
notification_email {
acassen@firewall.loc
failover@firewall.loc
sysadmin@firewall.loc
}
notification_email_from Alexandre.Cassen@firewall.loc
smtp_server 127.0.0.1
smtp_connect_timeout 30
router_id NGINX_MASTER
}
vrrp_script check_nginx {
script "/etc/keepalived/check_nginx.sh"
}
vrrp_instance VI_1 {
state MASTER
interface enp9s0
virtual_router_id 51
priority 100
advert_int 1
authentication {
auth_type PASS
auth_pass 1111
}
virtual_ipaddress {
172.17.17.79/24
}
track_script {
check_nginx
}
}
vrrp_script：指定检查nginx工作状态脚本（根据nginx状态判断是否故障转移）
virtual_ipaddress：虚拟IP（VIP）
检查nginx状态脚本
vim /etc/keepalived/check_nginx.sh
#!/bin/bash count=$(ps -ef |grep nginx |egrep -cv "grep|$$") if [ "$count" -eq 0 ];then exit 1 else exit 0 fi
chmod+x /etc/keepalived/check_nginx.sh
keepalived配置文件（Nginx Backup)
vim /etc/keepalived/keepalived.conf
global_defs {
notification_email {
acassen@firewall.loc
failover@firewall.loc
sysadmin@firewall.loc
}
notification_email_from Alexandre.Cassen@firewall.loc
smtp_server 127.0.0.1
smtp_connect_timeout 30
router_id NGINX_BACKUP
}
vrrp_script check_nginx {
script "/etc/keepalived/check_nginx.sh"
}
vrrp_instance VI_1 {
state BACKUP
interface enp9s0
virtual_router_id 51
priority 90
advert_int 1
authentication {
auth_type PASS
auth_pass 1111
}
virtual_ipaddress {
172.17.17.79/24
}
track_script {
check_nginx
}
}
启动并设置开机启动
systemctl daemon-reload
systemctl start nginx
systemctl start keepalived
systemctl enable nginx
systemctl enable keepalived
查看keepalived工作状态
ip add
enp9s0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP group default qlen 1000
link/ether 10:c3:7b:49:25:2f brd ff:ff:ff:ff:ff:ff
inet 172.17.17.83/25 brd 172.17.17.127 scope global enp9s0
valid_lft forever preferred_lft forever
inet 172.17.17.79/24 scope global enp9s0
valid_lft forever preferred_lft forever
inet6 fe80::12c3:7bff:fe49:252f/64 scope link
valid_lft forever preferred_lft forever
可以看到，在enp9s0网卡绑定了192.168.31.88 虚拟IP，说明工作正常。
Nginx+Keepalived高可用测试关闭主节点Nginx，
测试VIP是否漂移到备节点服务器。
在Nginx Master执行 pkill nginx在Nginx Backup，
ip addr命令查看已成功绑定VIP。
访问负载均衡器测试
修改k8s-node5 和k8s-node6配置
cd /data/kubernetes/cfg/
[root@k8s-node6 cfg]# sed -i 's/172.17.17.85/172.17.17.79/g' *
[root@k8s-node6 cfg]# systemctl restart kubelet
[root@k8s-node6 cfg]# systemctl restart kube-proxy
https://pkg.cfssl.org/R1.2/cfssl_linux-amd64
cat > /opt/kubernetes/cfg/kubelet.conf << EOF KUBELET_OPTS="--logtostderr=false \\ --v=2 \\ --log-dir=/opt/kubernetes/logs \\ --hostname-override=k8s-master03 \\ --network-plugin=cni \\ --kubeconfig=/opt/kubernetes/cfg/kubelet.kubeconfig \\ --bootstrap-kubeconfig=/opt/kubernetes/cfg/bootstrap.kubeconfig \\ --config=/opt/kubernetes/cfg/kubelet-config.yml \\ --cert-dir=/opt/kubernetes/ssl \\ --pod-infra-container-image=registry.aliyuncs.com/k8sxio/pause:3.2" EOF
