二进制部署kubernetes集群-v1.15.2

实验环境说明

实验架构图

实验主机说明

主机名 IP地址 角色 硬件配置
zzgw7-200.host.com 10.4.7.200 k8s运维节点 2c2g
zzgw7-11.host.com 10.4.7.11 k8s代理节点 2c2g
zzgw7-12.host.com 10.4.7.12 k8s代理节点 2c2g
zzgw7-21.host.com 10.4.7.21 k8s计算节点 2c2g
zzgw7-22.host.com 10.4.7.22 k8s计算节点 2c2g

调整系统

#配置YUM源
curl -o /etc/yum.repos.d/CentOS-Base.repo http://mirrors.aliyun.com/repo/Centos-7.repo
curl -o /etc/yum.repos.d/epel.repo http://mirrors.aliyun.com/repo/epel-7.repo

#关闭SElinux
sed -i 's/SELINUX=enforcing/SELINUX=disabled/' /etc/selinux/config
setenforce 0

#关闭firewalld
systemctl disable firewalld.service  
systemctl stop firewalld.service

#安装必要工具
 yum install -y wget net-tools telnet tree nmap sysstat lrzsz dos2unix bind-utils 

统一时间

ntpdate -u ntp.api.bz

前期环境准备

部署 DNS服务

部署节点:zzgw7-11

安装bind9服务

[root@zzgw7-11 ~]# yum install -y bind

修改配置文件

[root@zzgw7-11 ~]# vim /etc/named.conf
12 options {
 13         listen-on port 53 { 10.4.7.11; };	# 监听地址
 14         //listen-on-v6 port 53 { ::1; };	# 不监听IV6
 21         allow-query     { any; };			# 允许谁来访问,所有
 22         forwarders      { 10.4.7.254; };	# 上级DNS,添加
 33         recursion yes;
 35         dnssec-enable no;

检查配置文件

[root@zzgw7-11 ~]# named-checkconf 	
# 没有任何输出,说明配置文件无误

修改区域配置文件

添加主机域名host.com,业务域onelpc.com

[root@zzgw7-11 ~]# vim /etc/named.rfc1912.zones
# 文件结尾添加以下内容
zone " host.com" IN {
        type master;
        file "host.com.zone";
        allow-update { 10.4.7.11; };
};
zone " onelpc.com" IN {
        type master;
        file "onelpc.com.zone";
        allow-update { 10.4.7.11; };
};

添加区域数据文件

主机域配置文件

[root@zzgw7-11 ~]# vim /var/named/host.com.zone
$ORIGIN host.com.
$TTL 600  ; 10minutes
@    IN   SOA   dns.host.com.  dnsadmin.host.com. (
                2019122301    ; serial
                10800         ; refresh (3 hours)
                900           ; retry (15 minutes)
                604800        ; expire (1 week)
                86400         ; minimum (1 day)
                )
                NS   dns.host.com.
$TTL 60 ; 1 minute
dns         A     10.4.7.11
zzgw7-11    A     10.4.7.11
zzgw7-12    A     10.4.7.12
zzgw7-21    A     10.4.7.21
zzgw7-22    A     10.4.7.22
zzgw7-200   A     10.4.7.200

业务域配置文件

[root@zzgw7-11 ~]# cat /var/named/od.com.zome
$ORIGIN od.com.
$TTL 600  ; 10minutes
@    IN   SOA   dns.od.com.  dnsadmin.od.com. (
                2019122301    ; serial
                10800         ; refresh (3 hours)
                900           ; retry (15 minutes)
                604800        ; expire (1 week)
                86400         ; minimum (1 day)
                )
                NS   dns.od.com.
$TTL 60 ; 1 minute
dns         A     10.4.7.11

启动 bind9服务

[root@zzgw7-11 ~]# systemctl start named
[root@zzgw7-11 ~]# systemctl enable named
[root@zzgw7-11 ~]# netstat -lntup|grep -w 53
tcp        0      0 10.4.7.11:53            0.0.0.0:*               LISTEN      2510/named          
tcp6       0      0 :::53                   :::*                    LISTEN      2510/named          
udp        0      0 10.4.7.11:53            0.0.0.0:*                           2510/named          
udp6       0      0 :::53                   :::*                                2510/named  

检查DNS可用性

[root@zzgw7-11 ~]# yum install -y bind-utils
[root@zzgw7-11 ~]# dig -t A zzgw7-21.host.com @10.4.7.11 +short
10.4.7.21
[root@zzgw7-11 ~]# dig -t A zzgw7-200.host.com @10.4.7.11 +short
10.4.7.200

配置DNS客户端

所有主机都需要修改

[root@zzgw-200 ~]# vim /etc/sysconfig/network-scripts/ifcfg-eth0 
DNS1="10.4.7.11"	#修改DNS1地址

[root@zzgw7-200 ~]# systemctl restart network

[root@zzgw7-200 ~]# cat /etc/resolv.conf
# Generated by NetworkManager
search host.com
nameserver 10.4.7.11

测试访问外网

[root@zzgw7-11 ~]# ping -w1 baidu.com
PING baidu.com (220.181.38.148) 56(84) bytes of data.

测试访问内网

[root@zzgw7-11 ~]# ping -w1 zzgw7-12
PING zzgw7-200.host.com (10.4.7.200) 56(84) bytes of data.
64 bytes from 10.4.7.200 (10.4.7.200): icmp_seq=1 ttl=64 time=0.895 ms

部署签发证书环境

部署主机:ZZGW7-200

安装CFSSL

证书签发工具CFSSL: R1.2

wget https://pkg.cfssl.org/R1.2/cfssl_linux-amd64 -O /usr/bin/cfssl
wget https://pkg.cfssl.org/R1.2/cfssljson_linux-amd64 -O /usr/bin/cfssl-json
wget https://pkg.cfssl.org/R1.2/cfssl-certinfo_linux-amd64  -O  /usr/bin/cfssl-certinfo
chmod +x /usr/bin/cfssl*

创建生成CA证书签名请求(csr)的json配置文件

[root@zzgw7-200 ~]# cat /opt/certs/ca-csr.json
{
    "CN": "kubernetes-ca",
    "hosts": [
    ],
    "key": {
        "algo": "rsa",
        "size": 2048
    },
    "names": [
        {
            "C": "CN",
            "ST": "beijing",
            "L": "beijing",
            "O": "od",
            "OU": "ops"
        }
    ],
    "ca": {
        "expiry": "175200h"		# 证书有效时间
    }
}

CN: Common Name,浏览器使用该字段验证网站是否合法,一般写的是域名。非常重要。浏览器使用该字段验证网站是否合法
C: Country, 国家
ST: State,州,省
L: Locality,地区,城市
O: Organization Name,组织名称,公司名称
OU: Organization Unit Name,组织单位名称,公司部门

生成CA证书和私钥

[root@zzgw7-200 ~]# cd /opt/certs/
[root@zzgw7-200 certs]# cfssl gencert -initca ca-csr.json |cfssl-json -bare ca
[root@zzgw7-200 certs]# ll
total 16
-rw-r--r-- 1 root root 1001 Mar 28 20:39 ca.csr
-rw-r--r-- 1 root root  332 Mar 28 20:36 ca-csr.json	
-rw------- 1 root root 1675 Mar 28 20:39 ca-key.pem		#根证书私钥
-rw-r--r-- 1 root root 1354 Mar 28 20:39 ca.pem			#根证书

部署 docker环境

部署主机:zzgw7-200,zzgw7-21zzgw7-22.

这里以zzgw7-200为例

安装 docker

[root@zzgw7-200 certs]# curl -fsSL https://get.docker.com|bash -s docker --mirror Aliyun

配置 docker

[root@zzgw7-200 certs]# mkdir -p /etc/docker /data/docker
[root@zzgw7-200 certs]# cat /etc/docker/daemon.json
{
  "graph": "/data/docker",
  "storage-driver": "overlay",
  "insecure-registries": ["registry.access.redhat.com","quay.io","harbor.od.com"],
  "bip": "172.7.200.1/24",
  "exec-opts": ["native.cgroupdriver=systemd"],
  "live-restore": true
}

################## 配置说明 ##################
# bip要根据宿主机ip变化。 
#     zzgw7-21.host.com   bip 172.7.21.1/24
#     zzgw7-22.host.com   bip 172.7.22.1/24
#     zzgw7-200.host.com  bip 172.7.200.1/24
###########################################

启动 docker

[root@zzgw7-200 certs]# systemctl enable docker
[root@zzgw7-200 certs]# systemctl start docker
[root@zzgw7-200 certs]# systemctl status docker

部署 docker镜像私有仓库harbor

部署主机:zzgw7-200

下载软件并解压

harbor官网github地址:https://github.com/goharbor/harbor

[root@zzgw7-200 sotf]# tar xf harbor-offline-installer-v1.8.3.tgz -C /opt/
[root@zzgw7-200 sotf]# mv /opt/harbor/ /opt/harbor-v1.8.3
[root@zzgw7-200 sotf]# ln -s /opt/harbor-v1.8.3/ /opt/harbor

修改 harbor配置文件

[root@zzgw7-200 ~]# egrep -nv '^$|#' /opt/harbor/harbor.yml
5:hostname: harbor.od.com				# 配置域名访问
10:  port: 180							# 修改服务端口,防止端口冲突
27:harbor_admin_password: Harbor12345	# harbor登录密码
35:data_volume: /data/harbor			# harbor数据存放路径
82:  location: /data/harbor/logs		# harbor日志存放路径

安装 docker-compose

[root@zzgw7-200 ~]# yum install -y python3-pip
[root@zzgw7-200 ~]# pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple pip -U
[root@zzgw7-200 ~]# pip3 install docker-compose -i https://pypi.tuna.tsinghua.edu.cn/simple

[root@zzgw7-200 sotf]# docker-compose -version
docker-compose version 1.25.4, build unknown

安装 Harbor

[root@zzgw7-200 sotf]# cd /opt/harbor
[root@zzgw7-200 harbor]# ./install.sh 

查看 Harbor启动状态

[root@zzgw7-200 harbor]# docker-compose ps
      Name                     Command                       State                     Ports          
------------------------------------------------------------------------------------------------------
harbor-core         /harbor/start.sh                 Up (health: starting)                            
harbor-db           /entrypoint.sh postgres          Up (health: starting)   5432/tcp                 
harbor-jobservice   /harbor/start.sh                 Up                                               
harbor-log          /bin/sh -c /usr/local/bin/ ...   Up (health: starting)   127.0.0.1:1514->10514/tcp
harbor-portal       nginx -g daemon off;             Up (health: starting)   80/tcp                   
nginx               nginx -g daemon off;             Up (health: starting)   0.0.0.0:180->80/tcp      
redis               docker-entrypoint.sh redis ...   Up                      6379/tcp                 
registry            /entrypoint.sh /etc/regist ...   Up (health: starting)   5000/tcp                 
registryctl         /harbor/start.sh                 Up (health: starting)  

配置 harbor的DNS内网解析

DNS主机配置:zzgw7-11

[root@zzgw7-11 ~]# vim /var/named/od.com.zone 
$ORIGIN od.com.
$TTL 600  ; 10minutes
@    IN   SOA   dns.od.com.  dnsadmin.od.com. (
                2019122302    ; serial			#修改serial,序列号需要前滚
                10800         ; refresh (3 hours)
                900           ; retry (15 minutes)
                604800        ; expire (1 week)
                86400         ; minimum (1 day)
                )
                NS   dns.od.com.
$TTL 60 ; 1 minute
dns         A     10.4.7.11
harbor      A     10.4.7.200		# 添加harbor的A记录

检查DNS解析

[root@zzgw7-11 ~]# systemctl restart named
[root@zzgw7-11 ~]# dig -t A harbor.od.com +short
10.4.7.200

配置nginx 代理harbor

安装 nginx

[root@zzgw7-200 harbor]# yum install -y nginx

配置 nginx

[root@zzgw7-200 harbor]# vim /etc/nginx/conf.d/harbor.od.com.conf
server {
    listen 80;
    server_name harbor.od.com;
    client_max_body_size 1000m;

    location / {
        proxy_pass http://127.0.0.1:180;
    }
}

启动 nginx

[root@zzgw7-200 harbor]# nginx -t 
nginx: the configuration file /etc/nginx/nginx.conf syntax is ok
nginx: configuration file /etc/nginx/nginx.conf test is successful
[root@zzgw7-200 harbor]# systemctl start nginx
[root@zzgw7-200 harbor]# systemctl enable nginx

Web 访问登录

默认登录名:admin 默认密码:Harbor12345

密码可以在harbor.yml中修改

创建新项目

上传镜像测试

1.下载测试镜像并打给镜像打一个tag

[root@zzgw7-200 ~]# docker pull nginx:1.7.9
[root@zzgw7-200 ~]# docker images |grep  '^nginx'
nginx                           1.7.9                      84581e99d807        5 years ago         91.6MB
[root@zzgw7-200 harbor]# docker tag 84581e99d807 harbor.od.com/public/nginx:v1.7.9

2.登录harbor仓库

[root@zzgw7-200 harbor]# docker login harbor.od.com
Username: admin		#用户名
Password: 			#登录密码
WARNING! Your password will be stored unencrypted in /root/.docker/config.json.
Configure a credential helper to remove this warning. See
https://docs.docker.com/engine/reference/commandline/login/#credentials-store

Login Succeeded

3.上传镜像

[root@zzgw7-200 harbor]# docker push harbor.od.com/public/nginx:v1.7.9 
The push refers to repository [harbor.od.com/public/nginx]
5f70bf18a086: Pushed 
4b26ab29a475: Pushed 
ccb1d68e3fb7: Pushed 
e387107e2065: Pushed 
63bf84221cce: Pushed 
e02dce553481: Pushed 
dea2e4984e29: Pushed 
v1.7.9: digest: sha256:b1f5935eb2e9e2ae89c0b3e2e148c19068d91ca502e857052f14db230443e4c2 size: 3012

4.web 页面检查

image-20200328221013278

部署 Master组件

部署 etcd服务

etcd 集群规划

主机名 IP地址 角色
zzgw7-12.host.com 10.4.7.12 etcd lead
zzgw7-21.host.com 10.4.7.21 etcd follow
zzgw7-22.host.com 10.4.7.22 etcd follow

注意:这里部署文档以zzgw7-12.host.com主机为例,另外两台主机安装部署方法类似。

etcd 签发证书

zzgw7-200主机上创建

创建基于根证书的config配置文件

[root@zzgw7-200 certs]# cat ca-config.json 
{
    "signing": {
        "default": {
            "expiry": "175200h"
        },
        "profiles": {
            "server": {
                "expiry": "175200h",
                "usages": [
                    "signing",
                    "key encipherment",
                    "server auth"
                ]
            },
            "client": {
                "expiry": "175200h",
                "usages": [
                    "signing",
                    "key encipherment",
                    "client auth"
                ]
            },
            "peer": {
                "expiry": "175200h",
                "usages": [
                    "signing",
                    "key encipherment",
                    "server auth",
                    "client auth"
                ]
            }
        }
    }
}

证书类型

client certificate:客户端使用,用于服务端认证客户端,如etcdctl、etcd proxy、fleetctl、docker客户端

server certificate:服务端使用,客户端以此验证服务端身份,例如docker服务端、kube-apiserver

peer certificate:双向证书,用于etcd集群成员间通信

创建生成自签证书的签名请求(csr)的 json配置文件

[root@zzgw7-200 certs]# cat etcd-peer-csr.json 
{
    "CN": "k8s-etcd",
    # hosts 段把有可能成为etcd节点的主机都填写进去。
    "hosts": [
        "10.4.7.11",
        "10.4.7.12",
        "10.4.7.21",
        "10.4.7.22"
    ],
    "key": {
        "algo": "rsa",
        "size": 2048
    },
    "names": [
        {
            "C": "CN",
            "ST": "beijing",
            "L": "beijing",
            "O": "od",
            "OU": "ops"
        }
    ]
}

生成证书

[root@zzgw7-200 certs]# cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=peer etcd-peer-csr.json|cfssl-json -bare etcd-peer

[root@zzgw7-200 certs]# ls |grep etcd
etcd-peer.csr
etcd-peer-csr.json
etcd-peer-key.pem
etcd-peer.pem

创建etcd用户

[root@zzgw7-12 ~]# useradd -M -s /sbin/nologin etcd
[root@zzgw7-12 ~]# id etcd
uid=1000(etcd) gid=1000(etcd) groups=1000(etcd)

安装etcd服务

[root@zzgw7-12 ~]# mkdir -p /data/sotf/
[root@zzgw7-12 ~]# cd /data/sotf/
[root@zzgw7-12 sotf]# wget https://github.com/etcd-io/etcd/releases/download/v3.1.20/etcd-v3.1.20-linux-amd64.tar.gz
[root@zzgw7-12 sotf]# tar xf etcd-v3.1.20-linux-amd64.tar.gz -C /opt/
[root@zzgw7-12 sotf]# mv /opt/etcd-v3.1.20-linux-amd64/ /opt/etcd-v3.1.20
[root@zzgw7-12 sotf]# ln -s /opt/etcd-v3.1.20/ /opt/etcd

创建相关目录

[root@zzgw7-12 ~]# mkdir -p /opt/etcd/certs				// 存放etcd证书
[root@zzgw7-12 ~]# mkdir -p /data/etcd					// 存放etcd数据
[root@zzgw7-12 ~]# mkdir -p /data/logs/etcd-server		// 存放etcd日志
[root@zzgw7-12 ~]# chown -R etcd:etcd /data/etcd /data/logs/etcd-server/ 

拷贝证书与私钥文件

[root@zzgw7-12 ~]# cd /opt/etcd/certs/
[root@zzgw7-12 certs]# scp zzgw7-200:/opt/certs/ca.pem .  
[root@zzgw7-12 certs]# scp zzgw7-200:/opt/certs/etcd-peer.pem .
[root@zzgw7-12 certs]# scp zzgw7-200:/opt/certs/etcd-peer-key.pem .
[root@zzgw7-12 certs]# ls
ca.pem  etcd-peer-key.pem  etcd-peer.pem

创建etcd服务启动脚本

[root@zzgw7-12 certs]# cat /opt/etcd/etcd-server-startup.sh
#!/bin/sh
./etcd --name etcd-server-7-12 \
       --data-dir /data/etcd/etcd-server \
       --listen-peer-urls https://10.4.7.12:2380 \
       --listen-client-urls https://10.4.7.12:2379,http://127.0.0.1:2379 \
       --quota-backend-bytes 8000000000 \
       --initial-advertise-peer-urls https://10.4.7.12:2380 \
       --advertise-client-urls https://10.4.7.12:2379,http://127.0.0.1:2379 \
       --initial-cluster  etcd-server-7-12=https://10.4.7.12:2380,etcd-server-7-21=https://10.4.7.21:2380,etcd-server-7-22=https://10.4.7.22:2380 \
       --ca-file ./certs/ca.pem \
       --cert-file ./certs/etcd-peer.pem \
       --key-file ./certs/etcd-peer-key.pem \
       --client-cert-auth  \
       --trusted-ca-file ./certs/ca.pem \
       --peer-ca-file ./certs/ca.pem \
       --peer-cert-file ./certs/etcd-peer.pem \
       --peer-key-file ./certs/etcd-peer-key.pem \
       --peer-client-cert-auth \
       --peer-trusted-ca-file ./certs/ca.pem \
       --log-output stdout

######################################
#各etcd节点,脚本不同的地方(#根据宿主机IP变化)
	--name   etcd-server-7-12	
	--listen-peer-urls
	--listen-client-urls
	--initial-advertise-peer-urls
	--advertise-client-urls
######################################

调整权限

[root@zzgw7-12 certs]# chmod +x /opt/etcd/etcd-server-startup.sh
[root@zzgw7-12 certs]# chown etcd:etcd /opt/etcd-v3.1.20/ -R

安装supervisor

Supervisor是用Python开发的一个client/server服务,是Linux/Unix系统下的一个进程管理工具,不支持Windows系统。它可以很方便的监听、启动、停止、重启一个或多个进程。用Supervisor管理的进程,当一个进程意外被杀死,supervisort监听到进程死后,会自动将它重新拉起,很方便的做到进程自动恢复的功能,

[root@zzgw7-12 certs]# yum install -y supervisor
[root@zzgw7-12 certs]# systemctl start supervisord.service 
[root@zzgw7-12 certs]# systemctl enable supervisord.service 

创建etcd-server的启动配置

[root@zzgw7-12 certs]# cat /etc/supervisord.d/etcd-server.ini
[program:etcd-server-7-12]                  ; 根据主机改变
command=/opt/etcd/etcd-server-startup.sh    ; the program (relative uses PATH, can take args)
numprocs=1                                  ; number of processes copies to start (def 1)
directory=/opt/etcd                         ; directory to cwd to before exec (def no cwd)
autostart=true                              ; start at supervisord start (default: true)
autorestart=true                            ; retstart at unexpected quit (default: true)
startsecs=30                                ; number of secs prog must stay running (def. 1)
startretries=3                              ; max # of serial start failures (default 3)
exitcodes=0,2                               ; 'expected' exit codes for process (default 0,2)
stopsignal=QUIT                             ; signal used to kill process (default TERM)
stopwaitsecs=10                             ; max num secs to wait b4 SIGKILL (default 10)
user=etcd                                   ; setuid to this UNIX account to run the program
redirect_stderr=true                        ; redirect proc stderr to stdout (default false)
stdout_logfile=/data/logs/etcd-server/etcd.stdout.log     ; stdout log path, NONE for none; default AUTO
stdout_logfile_maxbytes=64MB                ; max # logfile bytes b4 rotation (default 50MB)
stdout_logfile_backups=4                    ; # of stdout logfile backups (default 10)
stdout_capture_maxbytes=1MB                 ; number of bytes in 'capturemode' (default 0)
stdout_events_enabled=false                 ; emit events on stdout writes (default false)
stderr_logfile=/data/logs/etcd-server/etcd.stderr.log      ; stderr log path, NONE for none; default AUTO
stderr_logfile_maxbytes=64MB                ; max # logfile bytes b4 rotation (default 50MB)
stderr_logfile_backups=4                    ; # of stderr logfile backups (default 10)
stderr_capture_maxbytes=1MB                 ; number of bytes in 'capturemode' (default 0)
stderr_events_enabled=false                 ; emit events on stderr writes (default false)

启动etcd

[root@zzgw7-12 certs]# supervisorctl update
etcd-server-7-12: added process group
[root@zzgw7-12 certs]# supervisorctl status
etcd-server-7-12                 RUNNING   pid 17477, uptime 0:01:54
[root@zzgw7-12 opt]# netstat -luntp|grep etcd
tcp        0      0 10.4.7.12:2379          0.0.0.0:*               LISTEN      17478/./etcd        
tcp        0      0 127.0.0.1:2379          0.0.0.0:*               LISTEN      17478/./etcd        
tcp        0      0 10.4.7.12:2380          0.0.0.0:*               LISTEN      17478/./etcd 

安装部署启动检查所有集群

和上述无区别,最主要是修改两个配置文件:
1、/opt/etcd/etcd-server-startup.sh的ip地址

2、/etc/supervisord.d/etcd-server.ini

//修改supervisord启动ini文件的program标签,是为了更好区分主机,生产规范,强迫症患者的福音,不修改不会造成启动失败

检查集群状态

任意节点

# 查看集群健康状态
[root@zzgw7-22 opt]# /opt/etcd/etcdctl cluster-health
member 988139385f78284 is healthy: got healthy result from http://127.0.0.1:2379
member 5a0ef2a004fc4349 is healthy: got healthy result from http://127.0.0.1:2379
member f4a0cb0a765574a8 is healthy: got healthy result from http://127.0.0.1:2379
cluster is healthy

# 查看etcd集群列表
[root@zzgw7-22 opt]# /opt/etcd/etcdctl member list
988139385f78284: name=etcd-server-7-22 peerURLs=https://10.4.7.22:2380 clientURLs=http://127.0.0.1:2379,https://10.4.7.22:2379 isLeader=false
5a0ef2a004fc4349: name=etcd-server-7-21 peerURLs=https://10.4.7.21:2380 clientURLs=http://127.0.0.1:2379,https://10.4.7.21:2379 isLeader=false
f4a0cb0a765574a8: name=etcd-server-7-12 peerURLs=https://10.4.7.12:2380 clientURLs=http://127.0.0.1:2379,https://10.4.7.12:2379 isLeader=true

部署 kube-apiserver服务

集群规划

主机名 IP地址 角色
zzgw7-21.host.com 10.4.7.21 kube-apiserver
zzgw7-22.host.com 10.4.7.22 kube-apiserver
zzgw7-11.host.com 10.4.7.11 4层负载均衡
zzgw7-11.host.com 10.4.7.12 4层负载均衡

这里10.4.7.1110.4.7.12使用nginx做4层负载均衡器,用keepalived跑一个vip:10.4.7.10,代理两个kube-apiserver,实现高可用

这里以hdss21为例,另外一台运算节点部署方法类似

签发client证书

操作主机:zzgw7-200

1. 创建生成证书签名请求(csr)的json配置文件

[root@zzgw7-200 certs]# cat /opt/certs/client-crs.json
{
    "CN": "k8s-node",
    "hosts": [
    ],
    "key": {
        "algo": "rsa",
        "size": 2048
    },
    "names": [
        {
            "C": "CN",
            "ST": "beijing",
            "L": "beijing",
            "O": "od",
            "OU": "ops"
        }
    ]
}

2. 生成client证书和私钥

[root@hdss7-200 certs]# cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=client client-csr.json |cfssl-json -bare client

3. 检查client证书和私钥

[root@zzgw7-200 certs]# ls |grep client
client.csr
client-csr.json
client-key.pem
client.pem

签发apiserver证书

1.创建生成证书签名请求(csr)的json配置文件

[root@zzgw7-200 certs]# vim /opt/certs/apiserver-csr.json
{
    "CN": "apiserver",
    "hosts": [
        "127.0.0.1",
        "192.168.0.1",
        "kubernetes.default",
        "kubernetes.default.svc",
        "kubernetes.default.svc.cluster",
        "kubernetes.default.svc.cluster.local",
        "10.4.7.10",
        "10.4.7.21",
        "10.4.7.22",
        "10.4.7.23"
    ],
    "key": {
        "algo": "rsa",
        "size": 2048
    },
    "names": [
        {
            "C": "CN",
            "ST": "beijing",
            "L": "beijing",
            "O": "od",
            "OU": "ops"
        }

2. 生成kube-apiserver证书和私钥

[root@zzgw7-200 certs]# cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=server apiserver-csr.json |cfssl-json -bare apiserver

3. 检查kube-apiserver证书与私钥

[root@zzgw7-200 certs]# ls |grep apiserver
apiserver.csr
apiserver-csr.json
apiserver-key.pem
apiserver.pem

下载软件,解压,做软链接

下载地址:https://github.com/kubernetes/kubernetes/releases

[root@zzgw7-21 sotf]# tar xf kubernetes-server-linux-amd64.tar.gz -C /opt/
[root@zzgw7-21 sotf]# mv /opt/kubernetes/ /opt/kubernetes-v1.15.2
[root@zzgw7-21 sotf]# ln -s /opt/kubernetes-v1.15.2/ /opt/kubernetes

# 删掉无用的源码包,bin下无用的tag,tar文件,不用adm方式部署,所以不需要这些文件
[root@zzgw7-21 sotf]# cd /opt/kubernetes
[root@zzgw7-21 kubernetes]# rm -rf kubernetes-src.tar.gz 
[root@zzgw7-21 kubernetes]# 
[root@zzgw7-21 kubernetes]# cd server/bin/
[root@zzgw7-21 bin]# rm -rf *.tar
[root@zzgw7-21 bin]# rm -rf *_tag

# 保留以下文件即可
[root@zzgw7-21 kubernetes]# tree 
.
├── addons
├── LICENSES
└── server
    └── bin
        ├── apiextensions-apiserver
        ├── cloud-controller-manager
        ├── hyperkube
        ├── kubeadm
        ├── kube-apiserver
        ├── kube-controller-manager
        ├── kubectl
        ├── kubelet
        ├── kube-proxy
        ├── kube-scheduler
        └── mounter

拷贝证书

[root@zzgw7-21 kubernetes]# mkdir -p /opt/kubernetes/server/bin/certs/
[root@zzgw7-21 kubernetes]# cd /opt/kubernetes/server/bin/certs/

[root@zzgw7-21 certs]# scp zzgw7-200:/opt/certs/apiserver.pem . 
[root@zzgw7-21 certs]# scp zzgw7-200:/opt/certs/apiserver-key.pem . 
[root@zzgw7-21 certs]# scp zzgw7-200:/opt/certs/client-key.pem .
[root@zzgw7-21 certs]# scp zzgw7-200:/opt/certs/client.pem .
[root@zzgw7-21 certs]# scp zzgw7-200:/opt/certs/ca.pem . 
[root@zzgw7-21 certs]# scp zzgw7-200:/opt/certs/ca-key.pem .

[root@zzgw7-21 certs]# ll
total 24
-rw------- 1 root root 1675 Mar 29 01:08 apiserver-key.pem
-rw-r--r-- 1 root root 1598 Mar 29 01:07 apiserver.pem
-rw------- 1 root root 1675 Mar 29 01:37 ca-key.pem
-rw-r--r-- 1 root root 1354 Mar 29 01:36 ca.pem
-rw------- 1 root root 1675 Mar 29 01:08 client-key.pem
-rw-r--r-- 1 root root 1371 Mar 29 01:09 client.pem

创建配置

k8s资源配置清单,专门给k8s做日志审计

[root@zzgw7-21 certs]#  mkdir /opt/kubernetes/server/bin/conf
[root@zzgw7-21 certs]# cat /opt/kubernetes/server/bin/conf/audit.yaml
apiVersion: audit.k8s.io/v1beta1 # This is required.
kind: Policy
# Don't generate audit events for all requests in RequestReceived stage.
omitStages:
  - "RequestReceived"
rules:
  # Log pod changes at RequestResponse level
  - level: RequestResponse
    resources:
    - group: ""
      # Resource "pods" doesn't match requests to any subresource of pods,
      # which is consistent with the RBAC policy.
      resources: ["pods"]
  # Log "pods/log", "pods/status" at Metadata level
  - level: Metadata
    resources:
    - group: ""
      resources: ["pods/log", "pods/status"]
  # Don't log requests to a configmap called "controller-leader"
  - level: None
    resources:
    - group: ""
      resources: ["configmaps"]
      resourceNames: ["controller-leader"]
  # Don't log watch requests by the "system:kube-proxy" on endpoints or services
  - level: None
    users: ["system:kube-proxy"]
    verbs: ["watch"]
    resources:
    - group: "" # core API group
      resources: ["endpoints", "services"]
  # Don't log authenticated requests to certain non-resource URL paths.
  - level: None
    userGroups: ["system:authenticated"]
    nonResourceURLs:
    - "/api*" # Wildcard matching.
    - "/version"
  # Log the request body of configmap changes in kube-system.
  - level: Request
    resources:
    - group: "" # core API group
      resources: ["configmaps"]
    # This rule only applies to resources in the "kube-system" namespace.
    # The empty string "" can be used to select non-namespaced resources.
    namespaces: ["kube-system"]
  # Log configmap and secret changes in all other namespaces at the Metadata level.
  - level: Metadata
    resources:
    - group: "" # core API group
      resources: ["secrets", "configmaps"]
  # Log all other resources in core and extensions at the Request level.
  - level: Request
    resources:
    - group: "" # core API group
    - group: "extensions" # Version of group should NOT be included.
  # A catch-all rule to log all other requests at the Metadata level.
  - level: Metadata
    # Long-running requests like watches that fall under this rule will not
    # generate an audit event in RequestReceived.
    omitStages:
      - "RequestReceived"

创建启动脚本

[root@zzgw7-21 bin]# vim /opt/kubernetes/server/bin/kube-apiserver.sh
#!/bin/bash
./kube-apiserver \
  --apiserver-count 2 \
  --audit-log-path /data/logs/kubernetes/kube-apiserver/audit-log \
  --audit-policy-file ./conf/audit.yaml \
  --authorization-mode RBAC \
  --client-ca-file ./certs/ca.pem \
  --requestheader-client-ca-file ./certs/ca.pem \
  --enable-admission-plugins NamespaceLifecycle,LimitRanger,ServiceAccount,DefaultStorageClass,DefaultTolerationSeconds,MutatingAdmissionWebhook,ValidatingAdmissionWebhook,ResourceQuota \
  --etcd-cafile ./certs/ca.pem \
  --etcd-certfile ./certs/client.pem \
  --etcd-keyfile ./certs/client-key.pem \
  --etcd-servers https://10.4.7.12:2379,https://10.4.7.21:2379,https://10.4.7.22:2379 \
  --service-account-key-file ./certs/ca-key.pem \
  --service-cluster-ip-range 192.168.0.0/16 \
  --service-node-port-range 3000-29999 \
  --target-ram-mb=1024 \
  --kubelet-client-certificate ./certs/client.pem \
  --kubelet-client-key ./certs/client-key.pem \
  --log-dir  /data/logs/kubernetes/kube-apiserver \
  --tls-cert-file ./certs/apiserver.pem \
  --tls-private-key-file ./certs/apiserver-key.pem \
  --v 2

####################### 参数说明 #######################
  --apiserver-count 2 			// apiserver数量                 
  --audit-log-path   			// 日志存放位置
  --audit-policy-file			// 日志审计规则文件
  --authorization-mode 	RBAC	// RBAC --基于角色访问的控制
  #详细参数说明:  ./kube-apiserver  help
#######################################################

调整权限与目录

[root@zzgw7-21 bin]# chmod +x kube-apiserver.sh
[root@zzgw7-21 bin]# mkdir -p /data/logs/kubernetes/kube-apiserver

创建supervisor配置

[root@zzgw7-21 bin]#  vi /etc/supervisord.d/kube-apiserver.ini
[program:kube-apiserver-7-21]
command=/opt/kubernetes/server/bin/kube-apiserver.sh            ; the program (relative uses PATH, can take args)
numprocs=1                                                      ; number of processes copies to start (def 1)
directory=/opt/kubernetes/server/bin                            ; directory to cwd to before exec (def no cwd)
autostart=true                                                  ; start at supervisord start (default: true)
autorestart=true                                                ; retstart at unexpected quit (default: true)
startsecs=30                                                    ; number of secs prog must stay running (def. 1)
startretries=3                                                  ; max # of serial start failures (default 3)
exitcodes=0,2                                                   ; 'expected' exit codes for process (default 0,2)
stopsignal=QUIT                                                 ; signal used to kill process (default TERM)
stopwaitsecs=10                                                 ; max num secs to wait b4 SIGKILL (default 10)
user=root                                                       ; setuid to this UNIX account to run the program
redirect_stderr=true                                            ; redirect proc stderr to stdout (default false)
stdout_logfile=/data/logs/kubernetes/kube-apiserver/apiserver.stdout.log        ; stderr log path, NONE for none; default AUTO
stdout_logfile_maxbytes=64MB                                    ; max # logfile bytes b4 rotation (default 50MB)
stdout_logfile_backups=4                                        ; # of stdout logfile backups (default 10)
stdout_capture_maxbytes=1MB                                     ; number of bytes in 'capturemode' (default 0)
stdout_events_enabled=false                                     ; emit events on stdout writes (default false)

启动服务并检查

[root@zzgw7-21 bin]# supervisorctl update
kube-apiserver-7-21: added process group

[root@zzgw7-21 certs]# supervisorctl status
etcd-server-7-21                 RUNNING   pid 17862, uptime 1:32:00
kube-apiserver-7-21              RUNNING   pid 18689, uptime 0:02:38

[root@zzgw7-21 certs]# netstat -lntup|grep kube-api
tcp        0      0 127.0.0.1:8080          0.0.0.0:*               LISTEN      18690/./kube-apiser 
tcp6       0      0 :::6443                 :::*                    LISTEN      18690/./kube-apiser 

安装部署启动检查所有节点

zzgw7-22 跟上述基本相同
/etc/supervisord.d/kube-apiserver.ini
需要更改成[program:kube-apiserver-7-22]

配置4层反向代理

操作主机:zzgw7-11,zzgw7-12

俩个节点除了keepalived.conf配置文件有所不同,其余配置完全一致。

部署nginx

安装nginx

yum install -y nginx

配置nginx

~] # vim /etc/nginx/nginx.conf

//追加到文件最后
stream {
    upstream kube-apiserver {
        server 10.4.7.21:6443     max_fails=3 fail_timeout=30s;
        server 10.4.7.22:6443     max_fails=3 fail_timeout=30s;
    }
    server {
        listen 7443;
        proxy_connect_timeout 2s;
        proxy_timeout 900s;
        proxy_pass kube-apiserver;
    }
}

启动nginx

nginx -t
systemctl start nginx
systemctl enable nginx

部署 keepalive

安装keepalive

[root@zzgw7-11 ~]# yum install -y keepalived

编写监控脚本

[root@zzgw7-11 ~]# cat /etc/keepalived/check_port.sh
#!/bin/bash
#keepalived 监控端口脚本
#使用方法:
#在keepalived的配置文件中
#vrrp_script check_port {#创建一个vrrp_script脚本,检查配置
#    script "/etc/keepalived/check_port.sh 6379" #配置监听的端口
#    interval 2 #检查脚本的频率,单位(秒)
#}
CHK_PORT=$1
if [ -n "$CHK_PORT" ];then
        PORT_PROCESS=`ss -lnt|grep $CHK_PORT|wc -l`
        if [ $PORT_PROCESS -eq 0 ];then
                echo "Port $CHK_PORT Is Not Used,End."
                exit 1
        fi
else
        echo "Check Port Cant Be Empty!"
fi

添加执行权限

[root@zzgw7-11 ~]# chmod +x /etc/keepalived/check_port.sh

配置keepalive(主)

[root@zzgw7-11 ~]# vim /etc/keepalived/keepalived.conf 
! Configuration File for keepalived

global_defs {
   router_id 10.4.7.11

}

vrrp_script chk_nginx {
    script "/etc/keepalived/check_port.sh 7443"
    interval 2
    weight -20
}

vrrp_instance VI_1 {
    state MASTER
    interface eth0
    virtual_router_id 251
    priority 100
    advert_int 1
    mcast_src_ip 10.4.7.11
    nopreempt		# 非抢占。当VIP漂移后,即使主节点恢复,VPI也不会漂移回来。
    authentication {
        auth_type PASS
        auth_pass 11111111
    }
    track_script {
         chk_nginx
    }
    virtual_ipaddress {
        10.4.7.10/24 dev eth0
    }
}

配置keepalive(备)

[root@zzgw7-12 opt]# vim /etc/keepalived/keepalived.conf 
! Configuration File for keepalived
global_defs {
    router_id 10.4.7.12
}
vrrp_script chk_nginx {
    script "/etc/keepalived/check_port.sh 7443"
    interval 2
    weight -20
}
vrrp_instance VI_1 {
    state BACKUP
    interface eth0
    virtual_router_id 251
    mcast_src_ip 10.4.7.12
    priority 90
    advert_int 1
    authentication {
        auth_type PASS
        auth_pass 11111111
    }
    track_script {
        chk_nginx
    }
    virtual_ipaddress {
        10.4.7.10/24 dev eth0
    }

启动keepalive

systemctl start keepalived.service 
systemctl enable keepalived.service 

部署 kube-controller-manager服务

部署主机

主机名 ip地址 角色
zzgw7-21.host.com 10.4.7.21 controller-manager
zzgw7-22.host.com 10.4.7.22 controller-manager

注意:这里部署文档以HDSS7-21.host.com主机为例,另外一台运算节点安装部署方法类似

创建服务启动脚本

[root@zzgw7-21 ~]# vim /opt/kubernetes/server/bin/kube-controller-manager.sh 
#!/bin/sh
./kube-controller-manager \
  --cluster-cidr 172.7.0.0/16 \
  --leader-elect true \
  --log-dir /data/logs/kubernetes/kube-controller-manager \
  --master http://127.0.0.1:8080 \
  --service-account-private-key-file ./certs/ca-key.pem \
  --service-cluster-ip-range 192.168.0.0/16 \
  --root-ca-file ./certs/ca.pem \
  --v 2

授权、创建目录

[root@zzgw7-21 ~]# chmod +x /opt/kubernetes/server/bin/kube-controller-manager.sh 
[root@zzgw7-21 ~]# mkdir -p /data/logs/kubernetes/kube-controller-manager

创建supervisor配置

[root@zzgw7-21 ~]# cat /etc/supervisord.d/kube-controller-manager.ini
[program:kube-controller-manager-7-21]
command=/opt/kubernetes/server/bin/kube-controller-manager.sh		; the program (relative uses PATH, can take args)
numprocs=1                             				 	; number of processes copies to start (def 1)
directory=/opt/kubernetes/server/bin 					; directory to cwd to before exec (def no cwd)
autostart=true                         					; start at supervisord start (default: true)
autorestart=true                        				; retstart at unexpected quit (default: true)
startsecs=22                            				; number of secs prog must stay running (def. 1)
startretries=3                          				; max # of serial start failures (default 3)
exitcodes=0,2                           				; 'expected' exit codes for process (default 0,2)
stopsignal=QUIT                         				; signal used to kill process (default TERM)
stopwaitsecs=10                         				; max num secs to wait b4 SIGKILL (default 10)
user=root                               				; setuid to this UNIX account to run the program
redirect_stderr=false                   				; redirect proc stderr to stdout (default false)
stdout_logfile=/data/logs/kubernetes/kube-controller-manager/controll.stdout.log  ; stdout log path, NONE for none; default AUTO
stdout_logfile_maxbytes=64MB            				; max # logfile bytes b4 rotation (default 50MB)
stdout_logfile_backups=4                				; # of stdout logfile backups (default 10)
stdout_capture_maxbytes=1MB            	 				; number of bytes in 'capturemode' (default 0)
stdout_events_enabled=false             				; emit events on stdout writes (default false)
stderr_logfile=/data/logs/kubernetes/kube-controller-manager/controll.stderr.log  ; stderr log path, NONE for none; default AUTO
stderr_logfile_maxbytes=64MB        					; max # logfile bytes b4 rotation (default 50MB)
stderr_logfile_backups=4                				; # of stderr logfile backups (default 10)
stderr_capture_maxbytes=1MB             				; number of bytes in 'capturemode' (default 0)
stderr_events_enabled=false             				; emit events on stderr writes (default false)

启动服务并检查

[root@zzgw7-21 ~]# supervisorctl update
kube-controller-manager-7-21: added process group
[root@zzgw7-21 ~]# supervisorctl status
etcd-server-7-21                 RUNNING   pid 1456, uptime 0:01:13
kube-apiserver-7-21              RUNNING   pid 1458, uptime 0:01:13
kube-controller-manager-7-21     RUNNING   pid 1455, uptime 0:01:13

安装部署启动检查所有集群规划主机

zzgw7-22 跟上述基本相同
/etc/supervisord.d/kube-controller-manager.ini
需要更改成[program:kube-controller-manager-7-22]

部署 kube-scheduler服务

部署主机

主机名 ip地址 角色
zzgw7-21.host.com 10.4.7.21 kube-scheduler
zzgw7-22.host.com 10.4.7.22 kube-scheduler

注意:这里部署文档以zzgw7-21为例,另一运算节点类似

创建启动脚本

[root@hdss7-21 ~]# vi /opt/kubernetes/server/bin/kube-scheduler.sh
#!/bin/sh
./kube-scheduler \
  --leader-elect  \
  --log-dir /data/logs/kubernetes/kube-scheduler \
  --master http://127.0.0.1:8080 \
  --v 2

如果主控节点组件在不同的地方,是需要证书验证的('client-key.pem和client.pem'),实验环境是在一个宿主机,所以这里无需证书.

授权、创建目录

[root@zzgw7-21 ~]# chmod +x  /opt/kubernetes/server/bin/kube-scheduler.sh
[root@zzgw7-21 ~]# mkdir -p /data/logs/kubernetes/kube-scheduler

创建supervisor配置

[root@zzgw7-21 ~]# vim /etc/supervisord.d/kube-scheduler.ini
[program:kube-scheduler-7-21]
command=/opt/kubernetes/server/bin/kube-scheduler.sh                     ; the program (relative uses PATH, can take args)
numprocs=1                                                               ; number of processes copies to start (def 1)
directory=/opt/kubernetes/server/bin                                     ; directory to cwd to before exec (def no cwd)
autostart=true                                                           ; start at supervisord start (default: true)
autorestart=true                                                         ; retstart at unexpected quit (default: true)
startsecs=22                                                             ; number of secs prog must stay running (def. 1)
startretries=3                                                           ; max # of serial start failures (default 3)
exitcodes=0,2                                                            ; 'expected' exit codes for process (default 0,2)
stopsignal=QUIT                                                          ; signal used to kill process (default TERM)
stopwaitsecs=10                                                          ; max num secs to wait b4 SIGKILL (default 10)
user=root                                                                ; setuid to this UNIX account to run the program
redirect_stderr=false                                                    ; redirect proc stderr to stdout (default false)
stdout_logfile=/data/logs/kubernetes/kube-scheduler/scheduler.stdout.log ; stdout log path, NONE for none; default AUTO
stdout_logfile_maxbytes=64MB                                             ; max # logfile bytes b4 rotation (default 50MB)
stdout_logfile_backups=4                                                 ; # of stdout logfile backups (default 10)
stdout_capture_maxbytes=1MB                                              ; number of bytes in 'capturemode' (default 0)
stdout_events_enabled=false                                              ; emit events on stdout writes (default false)
stderr_logfile=/data/logs/kubernetes/kube-scheduler/scheduler.stderr.log ; stderr log path, NONE for none; default AUTO
stderr_logfile_maxbytes=64MB                                             ; max # logfile bytes b4 rotation (default 50MB)
stderr_logfile_backups=4                                                 ; # of stderr logfile backups (default 10)
stderr_capture_maxbytes=1MB                                              ; number of bytes in 'capturemode' (default 0)
stderr_events_enabled=false                                              ; emit events on stderr writes (default false)

启动服务并检查

[root@zzgw7-21 ~]# supervisorctl update
kube-scheduler-7-21: added process group
[root@zzgw7-21 ~]# supervisorctl status
etcd-server-7-21                 RUNNING   pid 1456, uptime 0:14:56
kube-apiserver-7-21              RUNNING   pid 1458, uptime 0:14:56
kube-controller-manager-7-21     RUNNING   pid 1455, uptime 0:14:56
kube-scheduler-7-21              RUNNING   pid 1741, uptime 0:00:45

安装部署启动检查所有集群规划主机

zzgw7-22 跟上述基本相同
/etc/supervisord.d/ kube-scheduler.ini
需要更改成[program:kube-scheduler-7-22]

查看主控节点健康状态

# 设置软连接
[root@zzgw7-21 ~]# ln -s /opt/kubernetes/server/bin/kubectl /usr/bin/kubectl

# 查看状态
[root@zzgw7-21 ~]# kubectl get cs
NAME                 STATUS    MESSAGE              ERROR
scheduler            Healthy   ok                   
controller-manager   Healthy   ok                   
etcd-2               Healthy   {"health": "true"}   
etcd-1               Healthy   {"health": "true"}   
etcd-0               Healthy   {"health": "true"}   

部署 Node组件

部署 kubelet服务

部署主机

主机名 角色 ip
HDSS7-21.host.com 10.4.7.21 kubelet
HDSS7-22.host.com 10.4.7.22 kubelet

注意:这里部署文档以 hdss7-21主机为例,另外一台运算节点安装部署方法类似

签发 kubelet证书

运维主机zzgw7-200操作

创建生成证书签名请求(csr)的json配置文件

[root@zzgw7-200 ~]# cd /opt/certs/
[root@zzgw7-200 certs]# cat /opt/certs/kubelet-csr.json
{
    "CN": "k8s-kubelet",
    "hosts": [
    "127.0.0.1",
    "10.4.7.10",
    "10.4.7.21",
    "10.4.7.22",
    "10.4.7.23",
    "10.4.7.24",
    "10.4.7.25",
    "10.4.7.26",
    "10.4.7.27",
    "10.4.7.28"
    ],
    "key": {
        "algo": "rsa",
        "size": 2048
    },
    "names": [
        {
            "C": "CN",
            "ST": "beijing",
            "L": "beijing",
            "O": "od",
            "OU": "ops"
        }
    ]
}

生成证书与私钥文件

[root@zzgw7-200 certs]# cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=server kubelet-csr.json | cfssl-json -bare kubelet

[root@zzgw7-200 certs]# ls |grep kubelet
kubelet.csr
kubelet-csr.json
kubelet-key.pem
kubelet.pem

各节点拷贝kueblet证书

[root@zzgw7-21 ~]# cd /opt/kubernetes/server/bin/certs/
[root@zzgw7-21 certs]# scp zzgw7-200:/opt/certs/kubelet.pem . 
[root@zzgw7-21 certs]# scp zzgw7-200:/opt/certs/kubelet-key.pem .   

创建配置

只需在一个节点操作即可

set-cluster

[root@zzgw7-21 certs]# cd /opt/kubernetes/server/bin/conf/
[root@zzgw7-21 conf]# kubectl config set-cluster myk8s \
  --certificate-authority=/opt/kubernetes/server/bin/certs/ca.pem \
  --embed-certs=true \
  --server=https://10.4.7.10:7443 \
  --kubeconfig=kubelet.kubeconfig

#返回结果:
Cluster "myk8s" set.

set-credentials

[root@zzgw7-21 conf]# kubectl config set-credentials k8s-node \
  --client-certificate=/opt/kubernetes/server/bin/certs/client.pem \
  --client-key=/opt/kubernetes/server/bin/certs/client-key.pem \
  --embed-certs=true \
  --kubeconfig=kubelet.kubeconfig 

#返回结果:
User "k8s-node" set.

set-context

[root@zzgw7-21 conf]# kubectl config set-context myk8s-context \
  --cluster=myk8s \
  --user=k8s-node \
  --kubeconfig=kubelet.kubeconfig

#返回结果:
Context "myk8s-context" modified.

use-context

[root@zzgw7-21 conf]# kubectl config use-context myk8s-context --kubeconfig=kubelet.kubeconfig

# 返回结果
Switched to context "myk8s-context".

查看生成的文件

[root@zzgw7-21 conf]# ll
total 12
-rw-r--r-- 1 root root 2216 Mar 29 01:14 audit.yaml
-rw------- 1 root root 6215 Mar 29 16:45 kubelet.kubeconfig

集群角色绑定到用户

只需在一个节点操作即可

1.创建资源配置文件

[root@zzgw7-21 conf]# cat k8s-node.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: k8s-node
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: system:node
subjects:
- apiGroup: rbac.authorization.k8s.io
  kind: User
  name: k8s-node

2.根据配置文件创建用户

[root@zzgw7-21 conf]# kubectl create -f k8s-node.yaml	
// 返回结果.创建角色后会存到etcd里
clusterrolebinding.rbac.authorization.k8s.io/k8s-node created

3.查询集群角色

[root@zzgw7-21 conf]# kubectl get clusterrolebinding k8s-node
NAME       AGE
k8s-node   80s

4.拷贝kubelet.kubeconfig 到zzgw7-22上

[root@zzgw7-21 conf]# scp kubelet.kubeconfig zzgw7-22:`pwd`
root@zzgw7-22's password: 
kubelet.kubeconfig                                       100% 6215     5.8MB/s   00:00

准备pause基础镜像

操作主机:zzgw7-200

1.为什么需要这个pause基础镜像?

原因:需要用一个pause基础镜像把这台机器的pod拉起来,因为kubelet是干活的节点,它帮我们调度docker引擎,边车模式,让kebelet控制一个小镜像,先于我们的业务容器起来,让它帮我们业务容器去设置:UTC、NET、IPC,让它先把命名空间占上,业务容易还没起来的时候,pod的ip已经分配出来

2.下载pause镜像

[root@hdss7-200 certs]# docker pull kubernetes/pause

3.提交至docker私有仓库(harbor)中

#查看镜像ID
[root@zzgw7-200 certs]# docker images|grep pause
kubernetes/pause       latest        f9d5de079539        5 years ago         240kB

#打标签
[root@hdss7-200 certs]# docker tag f9d5de079539 harbor.od.com/public/pause:latest

#推送到harbor仓库
[root@zzgw7-200 certs]# docker push harbor.od.com/public/pause:latest

创建kubelet启动脚本

[root@zzgw7-21 conf]# vim /opt/kubernetes/server/bin/kubelet.sh
#!/bin/sh
./kubelet \
  # 匿名登陆,这里设置为不允许
  --anonymous-auth=false \
  # 这里需要和docker的daemon.json保持一直
  --cgroup-driver systemd \
  --cluster-dns 192.168.0.2 \
  --cluster-domain cluster.local \
  --runtime-cgroups=/systemd/system.slice \
  --kubelet-cgroups=/systemd/system.slice \
  # 设置为不关闭swap分区也正常启动,正常需要关闭swap分区的。
  --fail-swap-on="false" \
  --client-ca-file ./certs/ca.pem \
  --tls-cert-file ./certs/kubelet.pem \
  --tls-private-key-file ./certs/kubelet-key.pem \
  # 主机名
  --hostname-override zzgw7-21.host.com \
  --image-gc-high-threshold 20 \
  --image-gc-low-threshold 10 \
  --kubeconfig ./conf/kubelet.kubeconfig \
  --log-dir /data/logs/kubernetes/kube-kubelet \
  --pod-infra-container-image harbor.od.com/public/pause:latest \
  --root-dir /data/kubelet

注意:kubelet集群各主机的启动脚本略不同,其他节点注意修改:--hostname-override

授权并创建日志目录

[root@zzgw7-21 bin]# chmod +x /opt/kubernetes/server/bin/kubelet.sh 
[root@zzgw7-21 bin]# mkdir -p /data/logs/kubernetes/kube-kubelet /data/kubelet

创建 supervisor配置

[root@zzgw7-21 bin]# cat /etc/supervisord.d/kube-kubelet.ini
[program:kube-kubelet-7-21]
command=/opt/kubernetes/server/bin/kubelet.sh         ; the program (relative uses PATH, can take args)
numprocs=1                                            ; number of processes copies to start (def 1)
directory=/opt/kubernetes/server/bin                  ; directory to cwd to before exec (def no cwd) 
autostart=true                                        ; start at supervisord start (default: true)
autorestart=true                                      ; retstart at unexpected quit (default: true)
startsecs=22                                          ; number of secs prog must stay running (def. 1)
startretries=3                                        ; max # of serial start failures (default 3)
exitcodes=0,2                                         ; 'expected' exit codes for process (default 0,2)
stopsignal=QUIT                                       ; signal used to kill process (default TERM)
stopwaitsecs=10                                       ; max num secs to wait b4 SIGKILL (default 10)
user=root                                             ; setuid to this UNIX account to run the program
redirect_stderr=false                                 ; redirect proc stderr to stdout (default false)
stdout_logfile=/data/logs/kubernetes/kube-kubelet/kubelet.stdout.log       ; stdout log path, NONE for none; default AUTO
stdout_logfile_maxbytes=64MB                          ; max # logfile bytes b4 rotation (default 50MB)
stdout_logfile_backups=4                              ; # of stdout logfile backups (default 10)
stdout_capture_maxbytes=1MB                           ; number of bytes in 'capturemode' (default 0)
stdout_events_enabled=false                           ; emit events on stdout writes (default false)
stderr_logfile=/data/logs/kubernetes/kube-kubelet/kubelet.stderr.log       ; stderr log path, NONE for none; default AUTO
stderr_logfile_maxbytes=64MB                          ; max # logfile bytes b4 rotation (default 50MB)
stderr_logfile_backups=4                              ; # of stderr logfile backups (default 10)
stderr_capture_maxbytes=1MB                           ; number of bytes in 'capturemode' (default 0)
stderr_events_enabled=false                           ; emit events on stderr writes (default false)

注意:其他主机部署时请注意修改program标签

启动服务并检查

[root@zzgw7-21 bin]# supervisorctl update
kube-kubelet-7-21: added process group
[root@zzgw7-21 bin]# supervisorctl status
etcd-server-7-21                 RUNNING   pid 1456, uptime 1:24:18
kube-apiserver-7-21              RUNNING   pid 1458, uptime 1:24:18
kube-controller-manager-7-21     RUNNING   pid 1455, uptime 1:24:18
kube-kubelet-7-21                RUNNING   pid 2116, uptime 0:01:38
kube-scheduler-7-21              RUNNING   pid 2078, uptime 0:03:55

部署启动检查所有集群规划主机

其他节点类似,有些需要稍许调整:
/opt/kubernetes/server/bin/kubelet.sh
/etc/supervisord.d/kube-kubelet.ini

检查运算节点集群

[root@zzgw7-22 certs]# kubectl get node
NAME                STATUS   ROLES    AGE   VERSION
zzgw7-21.host.com   Ready    <none>   9m    v1.15.2
zzgw7-22.host.com   Ready    <none>   59s   v1.15.2

给主机打上角色标签

标签功能是特色管理功能之一

[root@zzgw7-22 certs]# kubectl label node zzgw7-21.host.com node-role.kubernetes.io/node=
// 返回结果
node/zzgw7-21.host.com labeled

[root@zzgw7-22 certs]# kubectl get node
NAME                STATUS   ROLES    AGE     VERSION
zzgw7-21.host.com   Ready    node     11m     v1.15.2
zzgw7-22.host.com   Ready    <none>   3m21s   v1.15.2

[root@zzgw7-22 certs]# kubectl label node zzgw7-21.host.com node-role.kubernetes.io/master=
// 返回结果
node/zzgw7-21.host.com labeled

[root@zzgw7-22 certs]# kubectl get node
NAME                STATUS   ROLES         AGE     VERSION
zzgw7-21.host.com   Ready    master,node   11m     v1.15.2
zzgw7-22.host.com   Ready    <none>        3m51s   v1.15.2

部署 kube-proxy服务

部署主机

主机名 角色 ip
zzgw7-21.host.com kube-proxy 10.4.7.21
zzgw7-22.host.com kube-proxy 10.4.7.21

注意:这里部署以hdss7-21主机为例,其他运算节点类似

签发kube-proxy证书

运维主机zzgw7-200操作

创建生成证书签名请求(csr)的json配置文件

[root@hdss7-200 certs]# cd /opt/certs/
[root@hdss7-200 certs]# vi kube-proxy-csr.json
i{
    "CN": "system:kube-proxy",
    "key": {
        "algo": "rsa",
        "size": 2048
    },
    "names": [
        {
            "C": "CN",
            "ST": "beijing",
            "L": "beijing",
            "O": "od",
            "OU": "ops"
        }
    ]
}

生成kubelet证书和私钥

[root@zzgw7-200 certs]# cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=client kube-proxy-csr.json |cfssl-json -bare kube-proxy-client

检查证书与私钥

[root@zzgw7-200 certs]# ll |grep proxy
-rw-r--r-- 1 root root 1005 Mar 29 17:46 kube-proxy-client.csr
-rw------- 1 root root 1675 Mar 29 17:46 kube-proxy-client-key.pem
-rw-r--r-- 1 root root 1383 Mar 29 17:46 kube-proxy-client.pem
-rw-r--r-- 1 root root  267 Mar 29 17:43 kube-proxy-csr.json

各节点拷贝kube-proxy证书

[root@zzgw7-21 ~]# cd /opt/kubernetes/server/bin/certs/
[root@zzgw7-21 certs]# scp zzgw7-200:/opt/certs/kube-proxy-client.pem .
[root@zzgw7-21 certs]# scp zzgw7-200:/opt/certs/kube-proxy-client-key.pem . 

创建配置

只需要在zzgw7-21主机操作,再将生成的配置文件拷贝到各规划节点即可。

1.切换至conf目录

[root@zzgw7-21 certs]# cd ../conf/
[root@zzgw7-21 conf]# pwd
/opt/kubernetes/server/bin/conf

set-cluster

kubectl config set-cluster myk8s \
  --certificate-authority=/opt/kubernetes/server/bin/certs/ca.pem \
  --embed-certs=true \
  --server=https://10.4.7.10:7443 \
  --kubeconfig=kube-proxy.kubeconfig

//返回结果
Cluster "myk8s" set.

set-credentials

kubectl config set-credentials kube-proxy \
  --client-certificate=/opt/kubernetes/server/bin/certs/kube-proxy-client.pem \
  --client-key=/opt/kubernetes/server/bin/certs/kube-proxy-client-key.pem \
  --embed-certs=true \
  --kubeconfig=kube-proxy.kubeconfig
  
//返回结果
User "kube-proxy" set.

set-context

kubectl config set-context myk8s-context \
  --cluster=myk8s \
  --user=kube-proxy \
  --kubeconfig=kube-proxy.kubeconfig

//返回结果
Context "myk8s-context" created.

use-context

kubectl config use-context myk8s-context --kubeconfig=kube-proxy.kubeconfig

//返回结果
Switched to context "myk8s-context".

查看生成配置文件

[root@zzgw7-21 conf]# ll 
total 24
-rw-r--r-- 1 root root 2216 Mar 29 01:14 audit.yaml
-rw-r--r-- 1 root root  258 Mar 29 16:52 k8s-node.yaml
-rw------- 1 root root 6215 Mar 29 16:45 kubelet.kubeconfig
-rw------- 1 root root 6235 Mar 29 17:57 kube-proxy.kubeconfig	## 生成的文件

拷贝kube-proxy.kubeconfig 到 zzgw7-22

[root@zzgw7-21 conf]# scp kube-proxy.kubeconfig zzgw7-22:/opt/kubernetes/server/bin/conf/
root@zzgw7-22's password: 
kube-proxy.kubeconfig                          100% 6235     5.0MB/s   00:00

配置ipvs 转发

查看ipvs模块是否开启

[root@zzgw7-21 conf]# lsmod |grep ip_vs		//无结果,说明未开启

开启ipvs模块

[root@zzgw7-21 conf]# vi /root/ipvs.sh
#!/bin/bash
ipvs_mods_dir="/usr/lib/modules/$(uname -r)/kernel/net/netfilter/ipvs"
for i in $(ls $ipvs_mods_dir|grep -o "^[^.]*")
do
  /sbin/modinfo -F filename $i &>/dev/null
  if [ $? -eq 0 ];then
    /sbin/modprobe $i
  fi
done

[root@zzgw7-21 conf]# sh /root/ipvs.sh

检测ipvs模块是否开启

[root@zzgw7-21 conf]# lsmod |grep ip_vs
ip_vs_wrr              12697  0 
ip_vs_wlc              12519  0 
ip_vs_sh               12688  0 
ip_vs_sed              12519  0 
ip_vs_rr               12600  0 
ip_vs_pe_sip           12740  0 
nf_conntrack_sip       33780  1 ip_vs_pe_sip
ip_vs_nq               12516  0 
ip_vs_lc               12516  0 
ip_vs_lblcr            12922  0 
ip_vs_lblc             12819  0 
ip_vs_ftp              13079  0 
ip_vs_dh               12688  0 
ip_vs                 145497  24 ip_vs_dh,ip_vs_lc,ip_vs_nq,ip_vs_rr,ip_vs_sh,ip_vs_ftp,ip_vs_sed,ip_vs_wlc,ip_vs_wrr,ip_vs_pe_sip,ip_vs_lblcr,ip_vs_lblc
nf_nat                 26583  3 ip_vs_ftp,nf_nat_ipv4,nf_nat_masquerade_ipv4
nf_conntrack          139224  8 ip_vs,nf_nat,nf_nat_ipv4,xt_conntrack,nf_nat_masquerade_ipv4,nf_conntrack_netlink,nf_conntrack_sip,nf_conntrack_ipv4
libcrc32c              12644  4 xfs,ip_vs,nf_nat,nf_conntrack

创建kube-proxy启动脚本

[root@zzgw7-21 conf]# cd /opt/kubernetes/server/bin/
[root@zzgw7-21 bin]# vim kube-proxy.sh
#!/bin/bash
./kube-proxy \
  --cluster-cidr 172.7.0.0/16 \
  --hostname-override zzgw7-21.host.com \
  --proxy-mode=ipvs \
  --ipvs-scheduler=nq \
  --kubeconfig ./conf/kube-proxy.kubeconfig

注意:其他主机部署时请注意修改--hostname-override该主机的主机名

检查配置、授权、创建日志目录

[root@zzgw7-21 bin]# ll conf/|grep kube-proxy
-rw------- 1 root root 6235 Mar 29 17:57 kube-proxy.kubeconfig
[root@zzgw7-21 bin]# chmod +x kube-proxy.sh 
[root@zzgw7-21 bin]# mkdir -p /data/logs/kubernetes/kube-proxy

创建supervisor配置

[root@zzgw7-21 bin]# cat /etc/supervisord.d/kube-proxy.ini
[program:kube-proxy-7-21]
command=/opt/kubernetes/server/bin/kube-proxy.sh                 ; the program (relative uses PATH, can take args)
numprocs=1                                                       ; number of processes copies to start (def 1)
directory=/opt/kubernetes/server/bin                             ; directory to cwd to before exec (def no cwd)
autostart=true                                                   ; start at supervisord start (default: true)
autorestart=true                                                 ; retstart at unexpected quit (default: true)
startsecs=22                                                     ; number of secs prog must stay running (def. 1)
startretries=3                                                   ; max # of serial start failures (default 3)
exitcodes=0,2                                                    ; 'expected' exit codes for process (default 0,2)
stopsignal=QUIT                                                  ; signal used to kill process (default TERM)
stopwaitsecs=10                                                  ; max num secs to wait b4 SIGKILL (default 10)
user=root                                                        ; setuid to this UNIX account to run the program
redirect_stderr=false                                            ; redirect proc stderr to stdout (default false)
stdout_logfile=/data/logs/kubernetes/kube-proxy/proxy.stdout.log     ; stdout log path, NONE for none; default AUTO
stdout_logfile_maxbytes=64MB                                     ; max # logfile bytes b4 rotation (default 50MB)
stdout_logfile_backups=4                                         ; # of stdout logfile backups (default 10)
stdout_capture_maxbytes=1MB                                      ; number of bytes in 'capturemode' (default 0)
stdout_events_enabled=false                                      ; emit events on stdout writes (default false)
stderr_logfile=/data/logs/kubernetes/kube-proxy/proxy.stderr.log     ; stderr log path, NONE for none; default AUTO
stderr_logfile_maxbytes=64MB                                     ; max # logfile bytes b4 rotation (default 50MB)
stderr_logfile_backups=4                                         ; # of stderr logfile backups (default 10)
stderr_capture_maxbytes=1MB                                      ; number of bytes in 'capturemode' (default 0)
stderr_events_enabled=false                                      ; emit events on stderr writes (default false)

注意:其他主机部署时请注意修改program标签

启动服务并检查

[root@zzgw7-21 bin]# supervisorctl update
kube-proxy-7-21: added process group

[root@zzgw7-21 bin]# supervisorctl status
etcd-server-7-21                 RUNNING   pid 1456, uptime 2:10:21
kube-apiserver-7-21              RUNNING   pid 1458, uptime 2:10:21
kube-controller-manager-7-21     RUNNING   pid 1455, uptime 2:10:21
kube-kubelet-7-21                RUNNING   pid 2116, uptime 0:47:41
kube-proxy-7-21                  RUNNING   pid 12875, uptime 0:00:33
kube-scheduler-7-21              RUNNING   pid 2078, uptime 0:49:58

安装部署启动检查所有集群规划主机

zzgw7-22 跟上述基本相同
/etc/supervisord.d/kube-proxy.ini
需要更改成[program:kube-proxy-7-21]

/opt/kubernetes/server/bin/kube-proxy.sh
需要改成 --hostname-override zzgw-22.host.com

验证kubernetes集群

创建一个资源配置清单

[root@zzgw7-22 certs]# vim /root/nginx-ds.yml
apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
  name: nginx-ds
spec:
  template:
    metadata:
      labels:
        app: nginx-ds
    spec:
      containers:
      - name: my-nginx
        image: harbor.od.com/public/nginx:v1.7.9
        ports:
        - containerPort: 80

应用资源配置,并检查

[root@zzgw7-22 certs]# kubectl create -f /root/nginx-ds.yml 
daemonset.extensions/nginx-ds created

[root@zzgw7-22 certs]# kubectl get pod
NAME             READY   STATUS    RESTARTS   AGE
nginx-ds-5jsnc   1/1     Running   0          55s
nginx-ds-rtq7d   1/1     Running   0          55s

[root@zzgw7-22 certs]# kubectl get pods -o wide
NAME             READY   STATUS    RESTARTS   AGE   IP           NODE                NOMINATED NODE   READINESS GATES
nginx-ds-5jsnc   1/1     Running   0          27m   172.7.22.2   zzgw7-22.host.com   <none>           <none>
nginx-ds-rtq7d   1/1     Running   0          27m   172.7.21.2   zzgw7-21.host.com   <none>           <none>

访问pod资源测试

[root@zzgw7-22 certs]# curl -I 172.7.22.2
HTTP/1.1 200 OK
Server: nginx/1.7.9
Date: Sun, 29 Mar 2020 10:55:11 GMT
Content-Type: text/html
Content-Length: 612
Last-Modified: Tue, 23 Dec 2014 16:25:09 GMT
Connection: keep-alive
ETag: "54999765-264"
Accept-Ranges: bytes

[root@zzgw7-22 certs]# curl -I 172.7.21.2
curl: (7) Failed connect to 172.7.21.2:80; Connection timed out

问题:跨宿主机的pod资源,无法访问。

解决方案:通过CNI网络插件实现POD资源能够跨宿主机就行通信

部署 Addons插件

K8S的CNI网络插件-Flannel

部署主机

主机名 服务 ip
zzgw7-21.host.com flannel 10.4.7.21
zzgw7-22.host.com flannel 10.4.7.22

注意:这里部署文档以zzgw7-21.host.com主机为例,另外一台运算节点安装部署方法类似

下载软件,解压,做软链

[root@hdss7-21 ~]# wget https://github.com/coreos/flannel/releases/download/v0.11.0/flannel-v0.11.0-linux-amd64.tar.gz
[root@zzgw7-21 ~]# mkdir /opt/flannel-v0.11.0
[root@zzgw7-21 ~]# tar xf flannel-v0.11.0-linux-amd64.tar.gz -C /opt/flannel-v0.11.0/
[root@zzgw7-21 ~]# ln -s /opt/flannel-v0.11.0/ /opt/flannel

拷贝证书

[root@zzgw7-21 ~]# mkdir /opt/flannel/cert
[root@zzgw7-21 ~]# cd /opt/flannel/cert/
[root@zzgw7-21 cert]# scp zzgw7-200:/opt/certs/ca.pem .
[root@zzgw7-21 cert]# scp zzgw7-200:/opt/certs/client.pem . 
[root@zzgw7-21 cert]# scp zzgw7-200:/opt/certs/client-key.pem .
[root@zzgw7-21 cert]# ll
total 12
-rw-r--r-- 1 root root 1354 Mar 29 19:39 ca.pem
-rw------- 1 root root 1675 Mar 29 19:40 client-key.pem
-rw-r--r-- 1 root root 1371 Mar 29 19:39 client.pem

创建配置文件

[root@zzgw7-21 cert]# cat /opt/flannel/cert/subnet.env
FLANNEL_NETWORK=172.7.0.0/16		#pod资源的IP范围
FLANNEL_SUBNET=172.7.21.1/24		#本机的IP范围
FLANNEL_MTU=1500
FLANNEL_IPMASQ=fals

注意:lannel集群各主机的配置略有不同,SUBNET需要更改

创建flanneld启动脚本

[root@zzgw7-21 cert]# vim /opt/flannel/flanneld.sh
#!/bin/sh
./flanneld \
  --public-ip=10.4.7.21 \
  --etcd-endpoints=https://10.4.7.12:2379,https://10.4.7.21:2379,https://10.4.7.22:2379 \
  --etcd-keyfile=./cert/client-key.pem \
  --etcd-certfile=./cert/client.pem \
  --etcd-cafile=./cert/ca.pem \
  --iface=eth0 \
  --subnet-file=./subnet.env \
  --healthz-port=2401

授权、创建日志目录

[root@zzgw7-21 cert]# chmod +x /opt/flannel/flanneld.sh 
[root@zzgw7-21 cert]# mkdir -p /data/logs/flanneld

操作etcd,增加host-gw

启动flannel之前,需要在etcd中添加网络配置记录

# 给etcdctl做个软连接
[root@zzgw7-21 cert]# ln -s /opt/etcd/etcdctl /usr/bin/

# 写入etcd
[root@zzgw7-21 cert]#   etcdctl set /coreos.com/network/config '{"Network": "172.7.0.0/16", "Backend": {"Type": "host-gw"}}'
//返回结果
{"Network": "172.7.0.0/16", "Backend": {"Type": "host-gw"}}

# 查看
[root@zzgw7-21 cert]# etcdctl  get /coreos.com/network/config
//返回结果
{"Network": "172.7.0.0/16", "Backend": {"Type": "host-gw"}}

host-gw:直接路由的方式,将容器网络的路由信息直接更新到主机的路由表中,仅适用于二层直接可达的网络

创建supervisor配置

[root@hdss7-21 etcd]# vim /etc/supervisord.d/flannel.ini
[program:flanneld-7-21]
command=/opt/flannel/flanneld.sh            ; the program (relative uses PATH, can take args)
numprocs=1                                  ; number of processes copies to start (def 1)
directory=/opt/flannel                      ; directory to cwd to before exec (def no cwd)
autostart=true                              ; start at supervisord start (default: true)
autorestart=true                            ; retstart at unexpected quit (default: true)
startsecs=30                                ; number of secs prog must stay running (def. 1)
startretries=3                              ; max # of serial start failures (default 3)
exitcodes=0,2                               ; 'expected' exit codes for process (default 0,2)
stopsignal=QUIT                             ; signal used to kill process (default TERM)
stopwaitsecs=10                             ; max num secs to wait b4 SIGKILL (default 10)
user=root                                   ; setuid to this UNIX account to run the program
redirect_stderr=true                        ; redirect proc stderr to stdout (default false)
stdout_logfile=/data/logs/flanneld/flanneld.stdout.log       ; stderr log path, NONE for none; default AUTO
stdout_logfile_maxbytes=64MB                ; max # logfile bytes b4 rotation (default 50MB)
stdout_logfile_backups=4                    ; # of stdout logfile backups (default 10)
stdout_capture_maxbytes=1MB                 ; number of bytes in 'capturemode' (default 0)
stdout_events_enabled=false                 ; emit events on stdout writes (default false)
stopasgroup=true                            ;默认为false,进程被杀死时,是否向这个进程组发送stop信号,包括子进程
killasgroup=true                            ;默认为false,向进程组发送kill信号,包括子进程

启动服务并检查

[root@zzgw7-21 cert]# supervisorctl  update
flanneld-7-21: added process group
[root@zzgw7-21 cert]# supervisorctl  status
etcd-server-7-21                 RUNNING   pid 1456, uptime 3:50:11
flanneld-7-21                    RUNNING   pid 41119, uptime 0:00:33 #
kube-apiserver-7-21              RUNNING   pid 1458, uptime 3:50:11
kube-controller-manager-7-21     RUNNING   pid 1455, uptime 3:50:11
kube-kubelet-7-21                RUNNING   pid 2116, uptime 2:27:31
kube-proxy-7-21                  RUNNING   pid 12875, uptime 1:40:23
kube-scheduler-7-21              RUNNING   pid 2078, uptime 2:29:48

安装部署启动检查所有集群规划节点

其他节点基本和zzgw7-21相同,注意修改一下文件:

# subnet.env	
	FLANNEL_SUBNET=172.7.22.1/24
	
# flanneld.sh 	
	--public-ip=10.4.7.22

# /etc/supervisord.d/flannel.ini
	[program:flanneld-7-22]

验证集群pod之间的网络互通

[root@zzgw7-21 ~]# ping 172.7.21.2
PING 172.7.21.2 (172.7.21.2) 56(84) bytes of data.
64 bytes from 172.7.21.2: icmp_seq=1 ttl=64 time=2.00 ms
64 bytes from 172.7.21.2: icmp_seq=2 ttl=64 time=0.036 ms

[root@zzgw7-21 ~]# ping 172.7.22.2
PING 172.7.22.2 (172.7.22.2) 56(84) bytes of data.
64 bytes from 172.7.22.2: icmp_seq=1 ttl=63 time=0.301 ms
64 bytes from 172.7.22.2: icmp_seq=2 ttl=63 time=0.367 ms

在各运算节点上优化iptables规则

注意:iptables规则各主机的略有不同,其他运算节点上执行时注意修改。

安装iptables

[root@zzgw7-21 ~]# yum install -y iptables-services
[root@zzgw7-21 ~]#  systemctl start iptables
[root@zzgw7-21 ~]#  systemctl enable iptables

优化SNAT规则,各运算节点之间的各POD之间的网络通信不再出网

[root@zzgw7-21 ~]# iptables -t nat -D POSTROUTING -s 172.7.21.0/24 ! -o docker0 -j MASQUERADE
[root@zzgw7-21 ~]# iptables -t nat -I POSTROUTING -s 172.7.21.0/24 ! -d 172.7.0.0/16 ! -o docker0 -j MASQUERADE

10.4.7.21主机上的,来源是172.7.21.0/24段的docker的ip,目标ip不是172.7.0.0/16段,网络发包不从docker0桥设备出站的,才进行SNAT转换

删除拒绝所有的规则

[root@zzgw7-21 ~]# iptables-save|grep -i reject
 -A INPUT -j REJECT --reject-with icmp-host-prohibited
 -A FORWARD -j REJECT --reject-with icmp-host-prohibited

[root@zzgw7-21 ~]# iptables -t filter -D INPUT -j REJECT --reject-with icmp-host-prohibited
[root@zzgw7-21 ~]# iptables -t filter -D FORWARD -j REJECT --reject-with icmp-host-prohibited

各运算节点保存iptables规则

[root@zzgw7-21 ~]# iptables-save >/etc/sysconfig/iptables
[root@zzgw7-21 ~]# service iptables save
iptables: Saving firewall rules to /etc/sysconfig/iptables:[  OK  ]
[root@hdss7-21 ~]# systemctl restart docker

容器网络里坦诚相待,不需要遮掩

容器直接直接的访问,将会记录容器的IP地址,而不是宿主机的IP地址。

K8S资源配置清单的内网http服务

在运维主机zzgw7-200.host.com上,配置一个nginx虚拟主机,用以提供k8s统一的资源配置清单访问入口。

配置nginx(zzgw7-200)

[root@zzgw7-200 ~]#  /etc/nginx/conf.d/k8s-yaml.od.com.conf
server {
    listen       80;
    server_name  k8s-yaml.od.com;

    location / {
        autoindex on;
        default_type text/plain;
        root /data/k8s-yaml;
    }
}


#检查并重启
[root@hdss7-200 html]# nginx -t
[root@hdss7-200 html]# nginx -s reload

#建立yaml目录和coredns的yaml目录
[root@hdss7-200 ~]# mkdir -p /data/k8s-yaml/coredns

添加A记录(zzgw7-11)

[root@zzgw7-11 ~]# vim /var/named/od.com.zone 
$ORIGIN od.com.
$TTL 600  ; 10minutes
@    IN   SOA   dns.od.com.  dnsadmin.od.com. (
                2019122303    ; serial
                10800         ; refresh (3 hours)
                900           ; retry (15 minutes)
                604800        ; expire (1 week)
                86400         ; minimum (1 day)
                )
                NS   dns.od.com.
$TTL 60 ; 1 minute
dns         A     10.4.7.11
harbor      A     10.4.7.200
k8s-yaml    A  10.4.7.200

[root@zzgw7-11 ~]# systemctl restart named
[root@zzgw7-11 ~]# dig -t A k8s-yaml.od.com  @10.4.7.11 +short
10.4.7.200

浏览器访问测试

K8S的服务发现插件-CoreDNS

准备coredns镜像

[root@zzgw7-200 ~]# docker pull coredns/coredns:1.6.5
[root@zzgw7-200 ~]# docker tag 70f311871ae1 harbor.od.com/public/coredns:v1.6.5
[root@zzgw7-200 ~]# docker push harbor.od.com/public/coredns:v1.6.5

准备资源配置清单

zzgw7-200操作

进入存放资源清单目录

[root@zzgw7-200 ~]# cd /data/k8s-yaml/coredns/

rbac.yaml

apiVersion: v1
kind: ServiceAccount
metadata:
  name: coredns
  namespace: kube-system
  labels:
      kubernetes.io/cluster-service: "true"
      addonmanager.kubernetes.io/mode: Reconcile
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    kubernetes.io/bootstrapping: rbac-defaults
    addonmanager.kubernetes.io/mode: Reconcile
  name: system:coredns
rules:
- apiGroups:
  - ""
  resources:
  - endpoints
  - services
  - pods
  - namespaces
  verbs:
  - list
  - watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  annotations:
    rbac.authorization.kubernetes.io/autoupdate: "true"
  labels:
    kubernetes.io/bootstrapping: rbac-defaults
    addonmanager.kubernetes.io/mode: EnsureExists
  name: system:coredns
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: system:coredns
subjects:
- kind: ServiceAccount
  name: coredns
  namespace: kube-system

configmap.yaml

apiVersion: v1
kind: ConfigMap
metadata:
  name: coredns
  namespace: kube-system
data:
  Corefile: |
    .:53 {
        errors
        log
        health
        ready
        kubernetes cluster.local 192.168.0.0/16
        forward . 10.4.7.11
        cache 30
        loop
        reload
        loadbalance
       }

deployment.yaml

IapiVersion: apps/v1
kind: Deployment
metadata:
  name: coredns
  namespace: kube-system
  labels:
    k8s-app: coredns
    kubernetes.io/name: "CoreDNS"
spec:
  replicas: 1
  selector:
    matchLabels:
      k8s-app: coredns
  template:
    metadata:
      labels:
        k8s-app: coredns
    spec:
      priorityClassName: system-cluster-critical
      serviceAccountName: coredns
      containers:
      - name: coredns
        image: harbor.od.com/public/coredns:v1.6.5
        args:
        - -conf
        - /etc/coredns/Corefile
        volumeMounts:
        - name: config-volume
          mountPath: /etc/coredns
        ports:
        - containerPort: 53
          name: dns
          protocol: UDP
        - containerPort: 53
          name: dns-tcp
          protocol: TCP
        - containerPort: 9153
          name: metrics
          protocol: TCP
        livenessProbe:
          httpGet:
            path: /health
            port: 8080
            scheme: HTTP
          initialDelaySeconds: 60
          timeoutSeconds: 5
          successThreshold: 1
          failureThreshold: 5
      dnsPolicy: Default
      volumes:
        - name: config-volume
          configMap:
            name: coredns
            items:
            - key: Corefile
              path: Corefile

service.yaml

apiVersion: v1
kind: Service
metadata:
  name: coredns
  namespace: kube-system
  labels:
    k8s-app: coredns
    kubernetes.io/cluster-service: "true"
    kubernetes.io/name: "CoreDNS"
spec:
  selector:
    k8s-app: coredns
  clusterIP: 192.168.0.2
  ports:
  - name: dns
    port: 53
    protocol: UDP
  - name: dns-tcp
    port: 53
  - name: metrics
    port: 9153
    protocol: TCP

检查资源配置清单

[root@zzgw7-200 coredns]# ll
total 16
-rw-r--r-- 1 root root  319 Mar 29 23:34 configmap.yaml
-rw-r--r-- 1 root root 1294 Mar 29 23:35 deployment.yaml
-rw-r--r-- 1 root root  954 Mar 29 23:32 rbac.yaml
-rw-r--r-- 1 root root  387 Mar 29 23:39 service.yaml

应用资源配置清单

任意计算节点(zzgw7-21、zzgw7-22)

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/coredns/rbac.yaml
serviceaccount/coredns created
clusterrole.rbac.authorization.k8s.io/system:coredns created
clusterrolebinding.rbac.authorization.k8s.io/system:coredns created

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/coredns/configmap.yaml
configmap/coredns created

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/coredns/deployment.yaml
deployment.apps/coredns created

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/coredns/service.yaml
service/coredns created

查看创建的资源

[root@zzgw7-21 ~]# kubectl get all -n kube-system
NAME                          READY   STATUS    RESTARTS   AGE
pod/coredns-9bc44c684-9m9mb   1/1     Running   0          34m


NAME              TYPE        CLUSTER-IP    EXTERNAL-IP   PORT(S)                  AGE
service/coredns   ClusterIP   192.168.0.2   <none>        53/UDP,53/TCP,9153/TCP   34m


NAME                      READY   UP-TO-DATE   AVAILABLE   AGE
deployment.apps/coredns   1/1     1            1           34m

NAME                                DESIRED   CURRENT   READY   AGE
replicaset.apps/coredns-9bc44c684   1         1         1       34m

验证coredns

[root@zzgw7-21 ~]# dig -t A www.baidu.com @192.168.0.2 +short
www.a.shifen.com.
36.152.44.95
36.152.44.96

[root@zzgw7-21 ~]# dig -t A zzgw7-21.host.com  @192.168.0.2 +short
10.4.7.21	////自建dns是coredns上级dns,所以可以查询到

解析测试

# 创建dp资源
[root@zzgw7-21 ~]# kubectl create  deployment nginx-dp  --image=harbor.od.com/public/nginx:v1.7.9 -n kube-public
deployment.apps/nginx-dp created
[root@zzgw7-21 ~]#  kubectl get pods -n kube-public
NAME                        READY   STATUS    RESTARTS   AGE
nginx-dp-5dfc689474-m2bq5   1/1     Running   0          5m21s

# 暴露dp资源
[root@zzgw7-21 ~]# kubectl expose deployment nginx-dp --port=80 -n kube-public
service/nginx-dp exposed
[root@zzgw7-21 ~]# kubectl get svc -n kube-public
NAME       TYPE        CLUSTER-IP        EXTERNAL-IP   PORT(S)   AGE
nginx-dp   ClusterIP   192.168.157.217   <none>        80/TCP    2s

# dig解析测试
[root@zzgw7-22 ~]#  dig -t A nginx-dp.kube-public.svc.cluster.local.  @192.168.0.2 +short
192.168.197.109

容器中测试

[root@zzgw7-22 ~]# kubectl get pods -o wide
NAME             READY   STATUS    RESTARTS   AGE   IP           NODE                NOMINATED NODE   READINESS GATES
nginx-ds-4l68x   1/1     Running   1          15h   172.7.22.3   zzgw7-22.host.com   <none>           <none>
nginx-ds-b29w7   1/1     Running   1          15h   172.7.21.2   zzgw7-21.host.com   <none>           <none>


[root@zzgw7-22 ~]# kubectl exec -it nginx-ds-4l68x bash
root@nginx-ds-4l68x:/# ping 192.168.197.109
PING 192.168.197.109 (192.168.197.109): 48 data bytes
56 bytes from 192.168.197.109: icmp_seq=0 ttl=64 time=0.112 ms
56 bytes from 192.168.197.109: icmp_seq=1 ttl=64 time=0.048 ms

K8S的服务暴露插件-Traefik

ingress控制器

Traefik是一个用Golang开发的轻量级的Http反向代理和负载均衡器。由于可以自动配置和刷新backend节点,目前可以被绝大部分容器平台支持,例如Kubernetes,Swarm,Rancher等。由于traefik会实时与Kubernetes API交互,所以对于Service的节点变化,traefik的反应会更加迅速。总体来说traefik可以在Kubernetes中完美的运行.

准备traefik镜像

[root@zzgw7-200 ~]# docker pull traefik:v1.7.2
[root@zzgw7-200 ~]# docker tag traefik:v1.7.2 harbor.od.com/public/traefik:v1.7.2
[root@zzgw7-200 harbor]#  docker push harbor.od.com/public/traefik:v1.7.2

准备资源配置清单

官网yaml文件地址:https://github.com/containous/traefik/tree/v1.7/examples/k8s

创建并进入资源清单目录

[root@zzgw7-200 ~]# mkdir -p /data/k8s-yaml/traefik
[root@zzgw7-200 ~]# cd /data/k8s-yaml/traefik
[root@zzgw7-200 traefik]# 

rbac.yaml

apiVersion: v1
kind: ServiceAccount
metadata:
  name: traefik-ingress-controller
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRole
metadata:
  name: traefik-ingress-controller
rules:
  - apiGroups:
      - ""
    resources:
      - services
      - endpoints
      - secrets
    verbs:
      - get
      - list
      - watch
  - apiGroups:
      - extensions
    resources:
      - ingresses
    verbs:
      - get
      - list
      - watch
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1beta1
metadata:
  name: traefik-ingress-controller
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: traefik-ingress-controller
subjects:
- kind: ServiceAccount
  name: traefik-ingress-controller
  namespace: kube-system

daemonset.yaml

apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
  name: traefik-ingress
  namespace: kube-system
  labels:
    k8s-app: traefik-ingress
spec:
  template:
    metadata:
      labels:
        k8s-app: traefik-ingress
        name: traefik-ingress
    spec:
      serviceAccountName: traefik-ingress-controller
      terminationGracePeriodSeconds: 60
      containers:
      - image: harbor.od.com/public/traefik:v1.7.2
        name: traefik-ingress
        ports:
        - name: controller
          containerPort: 80 
          hostPort: 81              
        - name: admin-web      
          containerPort: 8080
        securityContext:
          capabilities:
            drop:
            - ALL
            add:
            - NET_BIND_SERVICE
        args:
        - --api
        - --kubernetes
        - --logLevel=INFO
        - --insecureskipverify=true
        - --kubernetes.endpoint=https://10.4.7.10:7443      
        - --accesslog
        - --accesslog.filepath=/var/log/traefik_access.log
        - --traefiklog
        - --traefiklog.filepath=/var/log/traefik.log
        - --metrics.prometheus

service.yaml

kind: Service
apiVersion: v1
metadata:
  name: traefik-ingress-service
  namespace: kube-system
spec:
  selector:
    k8s-app: traefik-ingress
  ports:
    - protocol: TCP
      port: 80
      name: controller
    - protocol: TCP
      port: 8080
      name: admin-web

ingress.yaml

apiVersion: extensions/v1beta1
kind: Ingress
metadata:
  name: traefik-web-ui
  namespace: kube-system
  annotations:
    kubernetes.io/ingress.class: traefik
spec:
  rules:
  - host: traefik.od.com
    http:
      paths:
      - path: /
        backend:
          serviceName: traefik-ingress-service
          servicePort: 8080

应用资源配置清单

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/traefik/rbac.yaml
serviceaccount/traefik-ingress-controller created
clusterrole.rbac.authorization.k8s.io/traefik-ingress-controller created
clusterrolebinding.rbac.authorization.k8s.io/traefik-ingress-controller created

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/traefik/daemonset.yaml
daemonset.extensions/traefik-ingress created

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/traefik/service.yaml
service/traefik-ingress-service created

[root@zzgw7-21 ~]#  kubectl apply -f http://k8s-yaml.od.com/traefik/ingress.yaml
ingress.extensions/traefik-web-ui created

检查创建的资源

[root@zzgw7-21 ~]# kubectl get pods -n kube-system
NAME                      READY   STATUS    RESTARTS   AGE
coredns-9bc44c684-rb99c   1/1     Running   0          33m
traefik-ingress-fksht     1/1     Running   0          73s
traefik-ingress-mlzzg     1/1     Running   0          73s

添加A记录解析

操作主机:zzgw7-11

[root@zzgw7-11 ~]# cat /var/named/od.com.zone
$ORIGIN od.com.
$TTL 600  ; 10minutes
@    IN   SOA   dns.od.com.  dnsadmin.od.com. (
                2019122304    ; serial			# serial序列号前滚
                10800         ; refresh (3 hours)
                900           ; retry (15 minutes)
                604800        ; expire (1 week)
                86400         ; minimum (1 day)
                )
                NS   dns.od.com.
$TTL 60 ; 1 minute
dns         A     10.4.7.11
harbor      A     10.4.7.200
k8s-yaml    A     10.4.7.200
traefik     A     10.4.7.10		# 添加该条记录

[root@zzgw-11 ~]# systemctl restart named

配置Nginx反向

zzgw7-11和zzgw7-12两台主机上的nginx均需要配置

[root@zzgw7-11 ~]# vim /etc/nginx/conf.d/od.com.conf
upstream default_backend_traefik {
    server 10.4.7.21:81    max_fails=3 fail_timeout=10s;
    server 10.4.7.22:81    max_fails=3 fail_timeout=10s;
}
server {
    server_name *.od.com;
  
    location / {
        proxy_pass http://default_backend_traefik;
        proxy_set_header Host       $http_host;
        proxy_set_header x-forwarded-for $proxy_add_x_forwarded_for;
    }
}


[root@zzgw7-11 ~]# nginx -t
nginx: the configuration file /etc/nginx/nginx.conf syntax is ok
nginx: configuration file /etc/nginx/nginx.conf test is successful
[root@zzgw7-11 ~]# nginx -s reload

注:泛域名,访问任何业务域,会调用vip,分发流量至traefik81端口

浏览器访问

K8S的GUI资源管理插件-dashboard

准备dashboard镜像

# 下载镜像
[root@zzgw7-200 ~]#   docker pull k8scn/kubernetes-dashboard-amd64:v1.8.3

# 打标签
[root@zzgw7-200 ~]# docker tag k8scn/kubernetes-dashboard-amd64:v1.8.3 harbor.od.com/public/kubernetes-dashboard:v1.8.3

# 推送到harbor仓库
[root@zzgw7-200 ~]# docker push harbor.od.com/public/kubernetes-dashboard:v1.8.3

准备资源配置清单

创建并进入dashboard资源清单目录

[root@zzgw7-200 ~]# mkdir -p /data/k8s-yaml/dashboard
[root@zzgw7-200 ~]# cd /data/k8s-yaml/dashboard
[root@zzgw7-200 dashboard]# 

rbac.yaml

apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    k8s-app: kubernetes-dashboard
    addonmanager.kubernetes.io/mode: Reconcile
  name: kubernetes-dashboard-admin
  namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: kubernetes-dashboard-admin
  namespace: kube-system
  labels:
    k8s-app: kubernetes-dashboard
    addonmanager.kubernetes.io/mode: Reconcile
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: cluster-admin
subjects:
- kind: ServiceAccount
  name: kubernetes-dashboard-admin
  namespace: kube-system

deployment.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: kubernetes-dashboard
  namespace: kube-system
  labels:
    k8s-app: kubernetes-dashboard
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
spec:
  selector:
    matchLabels:
      k8s-app: kubernetes-dashboard
  template:
    metadata:
      labels:
        k8s-app: kubernetes-dashboard
      annotations:
        scheduler.alpha.kubernetes.io/critical-pod: ''
    spec:
      priorityClassName: system-cluster-critical
      containers:
      - name: kubernetes-dashboard
        image: harbor.od.com/public/kubernetes-dashboard:v1.8.3
        resources:
          limits:
            cpu: 100m
            memory: 300Mi
          requests:
            cpu: 50m
            memory: 100Mi
        ports:
        - containerPort: 8443
          protocol: TCP
        args:
          # PLATFORM-SPECIFIC ARGS HERE
          - --auto-generate-certificates
          - --token-ttl=43200 
        volumeMounts:
        - name: tmp-volume
          mountPath: /tmp
        livenessProbe:
          httpGet:
            scheme: HTTPS
            path: /
            port: 8443
          initialDelaySeconds: 30
          timeoutSeconds: 30
      volumes:
      - name: tmp-volume
        emptyDir: {}
      serviceAccountName: kubernetes-dashboard-admin
      tolerations:
      - key: "CriticalAddonsOnly"
        operator: "Exists"

service.yaml

apiVersion: v1
kind: Service
metadata:
  name: kubernetes-dashboard
  namespace: kube-system
  labels:
    k8s-app: kubernetes-dashboard
    kubernetes.io/cluster-service: "true"
    addonmanager.kubernetes.io/mode: Reconcile
spec:
  selector:
    k8s-app: kubernetes-dashboard
  ports:
  - port: 443
    targetPort: 8443

ingress.yaml

apiVersion: extensions/v1beta1
kind: Ingress
metadata:
  name: kubernetes-dashboard
  namespace: kube-system
  annotations:
    kubernetes.io/ingress.class: traefik
spec:
  rules:
  - host: dashboard.od.com
    http:
      paths:
      - backend:
          serviceName: kubernetes-dashboard
          servicePort: 443

应用资源配置清单

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/dashboard/rbac.yaml
serviceaccount/kubernetes-dashboard-admin created
clusterrolebinding.rbac.authorization.k8s.io/kubernetes-dashboard-admin created

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/dashboard/deployment.yaml
deployment.apps/kubernetes-dashboard created

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/dashboard/service.yaml
service/kubernetes-dashboard created

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/dashboard/ingress.yaml
ingress.extensions/kubernetes-dashboard created

查看创建的资源

[root@zzgw7-21 ~]# kubectl get pods -n kube-system|grep dashboard
kubernetes-dashboard-59dfb9868d-d45zr   1/1     Running   0          2m7s

[root@zzgw7-21 ~]# kubectl get svc -n kube-system|grep dashboard
kubernetes-dashboard      ClusterIP   192.168.102.181   <none>        443/TCP                  2m48

[root@zzgw7-21 ~]# kubectl get ingress -n kube-system|grep dashboard
kubernetes-dashboard   dashboard.od.com             80      3m10s

添加A记录解析

[root@zzgw7-11 ~]# cat /var/named/od.com.zone 
$ORIGIN od.com.
$TTL 600  ; 10minutes
@    IN   SOA   dns.od.com.  dnsadmin.od.com. (
                2019122305    ; serial
                10800         ; refresh (3 hours)
                900           ; retry (15 minutes)
                604800        ; expire (1 week)
                86400         ; minimum (1 day)
                )
                NS   dns.od.com.
$TTL 60 ; 1 minute
dns         A     10.4.7.11
harbor      A     10.4.7.200
k8s-yaml    A     10.4.7.200
traefik     A     10.4.7.10
dashboard   A     10.4.7.10		# 添加该条记录,serial序列号需要前滚

# 重启named
[root@zzgw7-11 ~]# systemctl restart named
# 任意节点测试
[root@zzgw7-11 ~]# dig -t A dashboard.od.com @10.4.7.11 +short
10.4.7.10

# 注意:运算节点操作
[root@zzgw7-21 ~]# dig -t A dashboard.od.com @192.168.0.2 +short
10.4.7.10

浏览器访问

注意:dashboardv1.8.3直接可以跳过。拿令牌登陆,需要https。

配置认证

使用token(令牌)需要https协议,因为treafik代理的http,所以要创建证书去https访问dashboard

cfssl签发证书

#setp1:创建csr.json
[root@zzgw7-200 dashboard]# cd /opt/certs/
[root@zzgw7-200 certs]# vi od.com-csr.json
{
    "CN": "*.od.com",
    "hosts": [
    ],
    "key": {
        "algo": "rsa",
        "size": 2048
    },
    "names": [
        {
            "C": "CN",
            "ST": "beijing",
            "L": "beijing",
            "O": "od",
            "OU": "ops"
        }
    ]
}

#setp2:签发
[root@zzgw7-200 certs]# cfssl gencert -ca=ca.pem -ca-key=ca-key.pem -config=ca-config.json -profile=server od.com-csr.json |cfssl-json -bare od.com

#setp3:检查生成证书
[root@zzgw7-200 certs]# ll |grep od
-rw-r--r-- 1 root root  993 Mar 30 17:46 od.com.csr
-rw-r--r-- 1 root root  280 Mar 30 17:46 od.com-csr.json
-rw------- 1 root root 1675 Mar 30 17:46 od.com-key.pem
-rw-r--r-- 1 root root 1371 Mar 30 17:46 od.com.pem

拷贝证书

代理节点(zzgw7-11,zzgw7-12)

[root@zzgw7-11 ~]# mkdir -p /etc/nginx/certs
[root@zzgw7-11 ~]# cd /etc/nginx/certs
[root@zzgw7-11 certs]# scp zzgw7-200:/opt/certs/od.com.pem .  
[root@zzgw7-11 certs]# scp zzgw7-200:/opt/certs/od.com-key.pem .

创建nginx 配置

[root@zzgw7-12 nginx]# cat /etc/nginx/conf.d/dashboard.od.com.conf
server {
    listen 80;
    server_name dashboard.od.com;   
    rewrite ^(.*)$ https://${server_name}$1 permanent;
}

server {
    listen 443 ssl;
    server_name dashboard.od.com;
    ssl_certificate "certs/od.com.pem";
    ssl_certificate_key "certs/od.com-key.pem";
    ssl_session_cache shared:SSL:1m;
    ssl_session_timeout  10m;
    ssl_ciphers HIGH:!aNULL:!MD5;
    ssl_prefer_server_ciphers on;

    location / {
        proxy_pass http://default_backend_traefik;
        proxy_set_header Host       $http_host;
        proxy_set_header x-forwarded-for $proxy_add_x_forwarded_for;
    }

}

[root@zzgw7-12 nginx]# nginx -t
nginx: the configuration file /etc/nginx/nginx.conf syntax is ok
nginx: configuration file /etc/nginx/nginx.conf test is successful

[root@zzgw7-12 nginx]# systemctl reload nginx

浏览器访问

使用token登录

获取token

[root@zzgw7-21 ~]# kubectl get secret -n kube-system
NAME                                     TYPE                                  DATA   AGE
coredns-token-5pklg                      kubernetes.io/service-account-token   3      140m
default-token-rjzdp                      kubernetes.io/service-account-token   3      20h
kubernetes-dashboard-admin-token-wbb8m   kubernetes.io/service-account-token   3      46m
kubernetes-dashboard-key-holder          Opaque                                2      45m
traefik-ingress-controller-token-vf94h   kubernetes.io/service-account-token   3      104m


[root@zzgw7-21 ~]#  kubectl describe secret kubernetes-dashboard-admin-token-wbb8m -n kube-system

浏览器登录

K8S的资源监控插件-Heapster

该项目将被官方废弃(RETIRED),在1.8版本以后由metricserver替代

准备heapster镜像

[root@zzgw7-200 ~]# docker pull quay.io/bitnami/heapster:1.5.4
[root@zzgw7-200 ~]# docker tag quay.io/bitnami/heapster:1.5.4 harbor.od.com/public/heapster:v1.5.4
[root@zzgw7-200 ~]# docker push harbor.od.com/public/heapster:v1.5.4 

准备资源配置清单

创建并进入资源配置清单目录

[root@zzgw7-200 ~]# mkdir -p /data/k8s-yaml/heapster
[root@zzgw7-200 ~]# cd /data/k8s-yaml/heapster
[root@zzgw7-200 heapster]# 

rbac.yaml

apiVersion: v1
kind: ServiceAccount
metadata:
  name: heapster
  namespace: kube-system
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1beta1
metadata:
  name: heapster
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: system:heapster
subjects:
- kind: ServiceAccount
  name: heapster
  namespace: kube-system

deployment.yaml

apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: heapster
  namespace: kube-system
spec:
  replicas: 1
  template:
    metadata:
      labels:
        task: monitoring
        k8s-app: heapster
    spec:
      serviceAccountName: heapster
      containers:
      - name: heapster
        image: harbor.od.com/public/heapster:v1.5.4
        imagePullPolicy: IfNotPresent
        command:
        - /opt/bitnami/heapster/bin/heapster
        - --source=kubernetes:https://kubernetes.default

service.yaml

apiVersion: v1
kind: Service
metadata:
  labels:
    task: monitoring
    kubernetes.io/cluster-service: 'true'
    kubernetes.io/name: Heapster
  name: heapster
  namespace: kube-system
spec:
  ports:
  - port: 80
    targetPort: 8082
  selector:
    k8s-app: heapster

应用资源配置清单

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/heapster/rbac.yaml
serviceaccount/heapster created
clusterrolebinding.rbac.authorization.k8s.io/heapster created

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/heapster/deployment.yaml
deployment.extensions/heapster created

[root@zzgw7-21 ~]# kubectl apply -f http://k8s-yaml.od.com/heapster/service.yaml
service/heapster created

查看创建的资源

[root@zzgw7-21 ~]# kubectl get pods -n kube-system|grep heapster
heapster-b5b9f794-qt8p8                 1/1     Running   0          3m24s

重启dashboard,访问

K8S集群平滑升级

注意:生产根据业务来规划升级时间,这里以zzgw7-21为例。

环境描述

目前使用版本为V1.15.2,升级版本为V1.15.4

[root@zzgw7-21 ~]# kubectl get node
NAME                STATUS   ROLES    AGE   VERSION
zzgw7-21.host.com   Ready    <none>   23h   v1.15.2
zzgw7-22.host.com   Ready    <none>   23h   v1.15.2

准备 V1.15.4版本软件

# 下载软件、需要FQ
[root@hdss7-21 src]# wget https://dl.k8s.io/v1.15.4/kubernetes-server-linux-amd64.tar.gz    

# 创建软件存放目录
[root@hdss7-21 src]# mkdir /opt/kubernetes-v1.15.4

# 解压软件
[root@zzgw7-21 src]# tar xf kubernetes-server-linux-amd64-v1.15.4.tar.gz  -C /opt/kubernetes-v1.15.4/
[root@zzgw7-21 ~]# cd /opt/kubernetes-v1.15.4/
[root@zzgw7-21 kubernetes-v1.15.4]# mv kubernetes/* .

# 删除无用的文件
[root@zzgw7-21 kubernetes-v1.15.4]# rm -rf kubernetes*
[root@zzgw7-21 kubernetes-v1.15.4]# rm -rf server/bin/*_tag
[root@zzgw7-21 kubernetes-v1.15.4]# rm -rf server/bin/*.tar 

# 最终文件结构
[root@zzgw7-21 kubernetes-v1.15.4]# tree
.
├── addons
├── LICENSES
└── server
    └── bin
        ├── apiextensions-apiserver
        ├── cloud-controller-manager
        ├── hyperkube
        ├── kubeadm
        ├── kube-apiserver
        ├── kube-controller-manager
        ├── kubectl
        ├── kubelet
        ├── kube-proxy
        ├── kube-scheduler
        └── mounter

拷贝脚本与证书

# 拷贝证书
[root@zzgw7-21 bin]# cp -a /opt/kubernetes-v1.15.2/server/bin/certs/ /opt/kubernetes-v1.15.4/server/bin/

# 拷贝启动脚本
[root@zzgw7-21 bin]# cp /opt/kubernetes-v1.15.2/server/bin/*.sh /opt/kubernetes-v1.15.4/server/bin/

# 拷贝配置
[root@zzgw7-21 opt]# cp -a kubernetes-v1.15.2/server/bin/conf/ /opt/kubernetes-v1.15.4/server/bin/

下线升级节点

生存环境需要修改nginx.conf,把升级节点从upstream中注释掉

[root@zzgw7-21 bin]# kubectl delete node zzgw7-21.host.com
node "zzgw7-21.host.com" deleted
[root@zzgw7-21 bin]# kubectl get node
NAME                STATUS   ROLES    AGE   VERSION
zzgw7-22.host.com   Ready    <none>   24h   v1.15.2


# 此时所有pod都调度到了zzgw7-22 节点上
[root@zzgw7-21 bin]# kubectl get pods  -n kube-system -o wide
NAME                                    READY   STATUS    RESTARTS   AGE     IP           NODE                NOMINATED NODE   READINESS GATES
coredns-9bc44c684-rb99c                 1/1     Running   0          5h35m   172.7.22.2   zzgw7-22.host.com   <none>           <none>
heapster-b5b9f794-7tgv5                 1/1     Running   0          2m42s   172.7.22.7   zzgw7-22.host.com   <none>           <none>
kubernetes-dashboard-59dfb9868d-hlph5   1/1     Running   0          134m    172.7.22.5   zzgw7-22.host.com   <none>           <none>
traefik-ingress-fksht                   1/1     Running   0          5h2m    172.7.22.4   zzgw7-22.host.com   <none>           <none>

重做软连接

删除软连接要特别注意,目录后面不要带上/

[root@zzgw7-21 bin]# cd /opt/
[root@zzgw7-21 opt]# rm -rf kubernetes
[root@zzgw7-21 opt]# ln -s /opt/kubernetes-v1.15.4/ /opt/kubernetes

重启服务

[root@zzgw7-21 opt]# supervisorctl restart kube-apiserver-7-21
kube-apiserver-7-21: stopped
kube-apiserver-7-21: started

[root@zzgw7-21 opt]# supervisorctl restart kube-controller-manager-7-21
kube-controller-manager-7-22: stopped
kube-controller-manager-7-22: started
![](https://img2020.cnblogs.com/blog/1851025/202003/1851025-20200331192923007-186371108.png)

[root@zzgw7-21 opt]# supervisorctl restart kube-scheduler-7-21          
kube-scheduler-7-21: stopped
kube-scheduler-7-21: started

[root@hdss7-21 opt]# supervisorctl restart kube-proxy-7-21
kube-proxy-7-21: stopped
kube-proxy-7-21: started

[root@hdss7-21 opt]# supervisorctl restart kube-kubelet-7-21
kube-kubelet-7-21: stopped
kube-kubelet-7-21: started

[root@zzgw7-21 opt]# supervisorctl  status
etcd-server-7-21                 RUNNING   pid 119511, uptime 0:04:06
flanneld-7-21                    RUNNING   pid 120624, uptime 0:02:35
kube-apiserver-7-21              RUNNING   pid 119282, uptime 0:04:13
kube-controller-manager-7-21     RUNNING   pid 119305, uptime 0:04:13
kube-kubelet-7-21                RUNNING   pid 119278, uptime 0:04:13
kube-proxy-7-21                  RUNNING   pid 119306, uptime 0:04:13
kube-scheduler-7-21              RUNNING   pid 119280, uptime 0:04:13

检查节点

[root@zzgw7-21 opt]# kubectl get node 
NAME                STATUS   ROLES    AGE     VERSION
zzgw7-21.host.com   Ready    <none>   2m32s   v1.15.4
zzgw7-22.host.com   Ready    <none>   24h     v1.15.2

[root@zzgw7-21 opt]# kubectl get pod -o wide
NAME             READY   STATUS    RESTARTS   AGE     IP           NODE                NOMINATED NODE   READINESS GATES
nginx-ds-4l68x   1/1     Running   1          21h     172.7.22.3   zzgw7-22.host.com   <none>           <none>
nginx-ds-6sxqd   1/1     Running   0          6m26s   172.7.21.3   zzgw7-21.host.com   <none>           <none>


[root@zzgw7-21 opt]# kubectl get pods -n kube-system -o wide 
NAME                                    READY   STATUS    RESTARTS   AGE     IP           NODE                NOMINATED NODE   READINESS GATES
coredns-9bc44c684-rb99c                 1/1     Running   0          6h10m   172.7.22.2   zzgw7-22.host.com   <none>           <none>
heapster-b5b9f794-7tgv5                 1/1     Running   0          37m     172.7.22.7   zzgw7-22.host.com   <none>           <none>
kubernetes-dashboard-59dfb9868d-n8t89   1/1     Running   0          25m     172.7.22.8   zzgw7-22.host.com   <none>           <none>
traefik-ingress-fksht                   1/1     Running   0          5h37m   172.7.22.4   zzgw7-22.host.com   <none>           <none>
traefik-ingress-m9cl4                   1/1     Running   0          10m     172.7.21.2   zzgw7-21.host.com   <none>           <none>
posted @ 2019-12-24 22:08  OneLpc  阅读(706)  评论(0编辑  收藏  举报