Etcd 是一个分布式键值存储系统，Kubernetes使用Etcd进行数据存储，所以先准备一个Etcd数据库，为解决Etcd单点故障，应采用集群方式部署，这里使用3台组建集群，可容忍1台机器故障，当然，你也可以使用5台组建集群，可容忍2台机器故障。
主机规划
| 节点名称 | IP |
|---|---|
| etcd-1,k8s-master | 192.168.80.220 |
| etcd-2,k8s-node1 | 192.168.80.221 |
| etcd-3,k8s-node1 | 192.168.80.222 |
操作系统初始化配置
# 关闭防火墙
systemctl stop firewalld
systemctl disable firewalld
# 关闭 selinux
sed -i 's/enforcing/disabled/' /etc/selinux/config # 永久
setenforce 0 # 临时
# 关闭 swap
swapoff -a # 临时
sed -ri 's/.*swap.*/#&/' /etc/fstab # 永久
# 根据规划设置主机名
hostnamectl set-hostname <hostname>
# 在 master 添加 hosts
cat >> /etc/hosts << EOF
192.168.80.220 k8s-master1
192.168.80.221 k8s-node1
192.168.80.222 k8s-node2
EOF
# 将桥接的 IPv4 流量传递到 iptables 的链
cat > /etc/sysctl.d/k8s.conf << EOF
net.bridge.bridge-nf-call-ip6tables = 1
net.bridge.bridge-nf-call-iptables = 1
EOF
sysctl --system # 生效
# 时间同步
yum install ntpdate -y
ntpdate time.windows.com
准备cfssl证书生成工具
cfssl是一个开源的证书管理工具，使用json文件生成证书，相比openssl更方便使用。找任意一台服务器操作，这里用Master节点。
wget https://pkg.cfssl.org/R1.2/cfssl_linux-amd64
wget https://pkg.cfssl.org/R1.2/cfssljson_linux-amd64
wget https://pkg.cfssl.org/R1.2/cfssl-certinfo_linux-amd64
chmod +x cfssl_linux-amd64 cfssljson_linux-amd64 cfssl-certinfo_linux-amd64
mv cfssl_linux-amd64 /usr/local/bin/cfssl
mv cfssljson_linux-amd64 /usr/local/bin/cfssljson
mv cfssl-certinfo_linux-amd64 /usr/bin/cfssl-certinfo
若是下载不了的话可以用我下载好的这个：https://files.cnblogs.com/files/sanduzxcvbnm/etcd集群生成证书的工具.zip
生成Etcd证书
自签证书颁发机构（CA）
# 创建工作目录
mkdir -p ~/TLS/{etcd,k8s}
cd ~/TLS/etcd
# 自签CA
cat > ca-config.json << EOF
{
"signing": {
"default": {
"expiry": "87600h"
},
"profiles": {
"www": {
"expiry": "87600h",
"usages": [
"signing",
"key encipherment",
"server auth",
"client auth"
]
}
}
}
}
EOF
cat > ca-csr.json << EOF
{
"CN": "etcd CA",
"key": {
"algo": "rsa",
"size": 2048
},
"names": [
{
"C": "CN",
"L": "Beijing",
"ST": "Beijing"
}
]
}
EOF
# 生成证书,会生成ca.pem和ca-key.pem文件
cfssl gencert -initca ca-csr.json | cfssljson -bare ca -
使用自签CA签发Etcd HTTPS证书
# 创建证书申请文件
# 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。
cat > server-csr.json << EOF
{
"CN": "etcd",
"hosts": [
"192.168.80.220",
"192.168.80.221",
"192.168.80.222",
"192.168.80.223",
"192.168.80.224",
"192.168.80.225"
],
"key": {
"algo": "rsa",
"size": 2048
},
"names": [
{
"C": "CN",
"L": "BeiJing",
"ST": "BeiJing"
}
]
}
EOF
# 生成证书,会生成server.pem和server-key.pem文件
cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=www server-csr.json | cfssljson -bare server
从Github下载二进制文件
可以使用迅雷下载
https://github.com/etcd-io/etcd/releases/download/v3.5.0/etcd-v3.5.0-linux-amd64.tar.gz
百度云网盘分享地址
链接：https://pan.baidu.com/s/1LvnMZSGgwafkH3Bdce-s8A
提取码：40bc
部署Etcd集群
以下在节点etcd-1上操作，为简化操作，待会将节点1生成的所有文件拷贝到节点2和节点3.
# 创建工作目录并解压二进制包
mkdir /opt/etcd/{bin,cfg,ssl} -p
tar zxvf etcd-v3.5.0-linux-amd64.tar.gz
mv etcd-v3.5.0-linux-amd64/{etcd,etcdctl} /opt/etcd/bin/
# 创建etcd配置文件
cat > /opt/etcd/cfg/etcd.conf << EOF
#[Member]
ETCD_NAME="etcd-1"
ETCD_DATA_DIR="/var/lib/etcd/default.etcd"
ETCD_LISTEN_PEER_URLS="https://192.168.80.220:2380"
ETCD_LISTEN_CLIENT_URLS="https://192.168.80.220:2379"
#[Clustering]
ETCD_INITIAL_ADVERTISE_PEER_URLS="https://192.168.80.220:2380"
ETCD_ADVERTISE_CLIENT_URLS="https://192.168.80.220:2379"
ETCD_INITIAL_CLUSTER="etcd-1=https://192.168.80.220:2380,etcd-2=https://192.168.80.221:2380,etcd-3=https://192.168.80.222:2380"
ETCD_INITIAL_CLUSTER_TOKEN="etcd-cluster"
ETCD_INITIAL_CLUSTER_STATE="new"
EOF
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_PEERURLS：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_INITIALCLUSTER_TOKEN：集群Token
ETCD_INITIALCLUSTER_STATE：加入集群的当前状态，new是新集群，existing表示加入已有集群
# systemd管理etcd
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=/opt/etcd/cfg/etcd.conf
ExecStart=/opt/etcd/bin/etcd \
--cert-file=/opt/etcd/ssl/server.pem \
--key-file=/opt/etcd/ssl/server-key.pem \
--peer-cert-file=/opt/etcd/ssl/server.pem \
--peer-key-file=/opt/etcd/ssl/server-key.pem \
--trusted-ca-file=/opt/etcd/ssl/ca.pem \
--peer-trusted-ca-file=/opt/etcd/ssl/ca.pem \
--logger=zap
Restart=on-failure
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
EOF
# 拷贝刚才生成的证书,把刚才生成的证书拷贝到配置文件中的路径
cp ~/TLS/etcd/ca*pem ~/TLS/etcd/server*pem /opt/etcd/ssl/
# 启动并设置开机启动
systemctl daemon-reload
systemctl start etcd # 第一个节点启动比较慢，是连接另外俩节点连接不上超时导致的，等另外俩节点的etcd起来后状态就正常了
systemctl enable etcd
# 将上面节点etcd-1所有生成的文件拷贝到节点etcd-2和节点etcd-3
scp -r /opt/etcd/ root@192.168.80.221:/opt/
scp /usr/lib/systemd/system/etcd.service root@192.168.80.221:/usr/lib/systemd/system/
scp -r /opt/etcd/ root@192.168.80.222:/opt/
scp /usr/lib/systemd/system/etcd.service root@192.168.80.222:/usr/lib/systemd/system/
# 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
vim /opt/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://192.168.80.220:2380" # 修改此处为当前服务器IP
ETCD_LISTEN_CLIENT_URLS="https://192.168.80.220:2379" # 修改此处为当前服务器IP
#[Clustering]
ETCD_INITIAL_ADVERTISE_PEER_URLS="https://192.168.80.220:2380" # 修改此处为当前服务器IP
ETCD_ADVERTISE_CLIENT_URLS="https://192.168.80.220:2379" # 修改此处为当前服务器IP
ETCD_INITIAL_CLUSTER="etcd-1=https://192.168.80.220:2380,etcd-2=https://192.168.80.221:2380,etcd-3=https://192.168.80.222:2380"
ETCD_INITIAL_CLUSTER_TOKEN="etcd-cluster"
ETCD_INITIAL_CLUSTER_STATE="new"
# 最后启动etcd并设置开机启动,操作命令同上
查看集群状态
/opt/etcd/bin/etcdctl --cacert=/opt/etcd/ssl/ca.pem --cert=/opt/etcd/ssl/server.pem --key=/opt/etcd/ssl/server-key.pem --endpoints="https://192.168.80.220:2379,https://192.168.80.221:2379,https://192.168.80.222:2379" endpoint health --write-out=table
+-----------------------------+--------+------------+-------+
| ENDPOINT | HEALTH | TOOK | ERROR |
+-----------------------------+--------+------------+-------+
| https://192.168.80.220:2379 | true | 7.327348ms | |
| https://192.168.80.221:2379 | true | 7.532873ms | |
| https://192.168.80.222:2379 | true | 7.732458ms | |
+-----------------------------+--------+------------+-------+
如果输出上面信息，就说明集群部署成功。
如果有问题第一步先看日志：/var/log/message 或 journalctl -u etcd
