Loading

基于saltstack自动化部署高可用kubernetes集群

SaltStack自动化部署HA-Kubernetes

  • 本项目在GitHub上,会不定期更新,大家也可以提交ISSUE,地址为:https://github.com/skymyyang/salt-k8s-ha
  • SaltStack自动化部署Kubernetes v1.12.5版本(支持HA、TLS双向认证、RBAC授权、Flannel网络、ETCD集群、Kuber-Proxy使用LVS等)。
  • SaltStack自动化部署 Kubernetes v1.13.4 版本,请切换到 1.13-Release 分支.

版本明细:Release-v1.12.5

  • 测试通过系统:Centos 7.6
  • salt-ssh:salt-ssh 2018.3.3 (Oxygen)
  • Kubernetes: v1.12.5
  • Etcd:v3.3.10
  • Docker:最新版本即可
  • Flannel:v0.10.0
  • CNI-Plugins:v0.7.0
  • 建议部署节点:最少三个Master节点,请配置好主机名解析(必备)

架构介绍

  1. 使用Salt Grains进行角色定义,增加灵活性。
  2. 使用Salt Pillar进行配置项管理,保证安全性。
  3. 使用Salt SSH执行状态,不需要安装Agent,保证通用性。
  4. 使用Kubernetes当前稳定版本v1.12.5,保证稳定性。
  5. 使用HaProxy和keepalived来保证集群的高可用。

0.系统初始化(必备)

  1. 设置主机名!!!
    [root@linux-node1 ~]# cat /etc/hostname
    linux-node1
    
    [root@linux-node2 ~]# cat /etc/hostname
    linux-node2
    
    [root@linux-node3 ~]# cat /etc/hostname
    linux-node3
    
    [root@linux-node4 ~]# cat /etc/hostname
    linux-node4

     

  2. 设置/etc/hosts保证主机名能够解析
    [root@linux-node1 ~]# cat /etc/hosts
    127.0.0.1   localhost localhost.localdomain localhost4 localhost4.localdomain4
    ::1         localhost localhost.localdomain localhost6 localhost6.localdomain6
    192.168.150.141 linux-node1
    192.168.150.142 linux-node2
    192.168.150.143 linux-node3
    192.168.150.144 linux-node4

     

  3. 关闭SELinux和防火墙以及NetworkManager
     systemctl disable --now firewalld NetworkManager
       setenforce 0
       sed -ri '/^[^#]*SELINUX=/s#=.+$#=disabled#' /etc/selinux/config

     

  4. 设置时间同步客户端
    yum install chrony -y
    
    cat <<EOF > /etc/chrony.conf
    server ntp.aliyun.com iburst
    stratumweight 0
    driftfile /var/lib/chrony/drift
    rtcsync
    makestep 10 3
    bindcmdaddress 127.0.0.1
    bindcmdaddress ::1
    keyfile /etc/chrony.keys
    commandkey 1
    generatecommandkey
    logchange 0.5
    logdir /var/log/chrony
    EOF
    
    systemctl restart chronyd
    systemctl enable --now chronyd

     

  5. 升级内核
    #因为市面上包管理下内核版本过低,安装docker后无论centos还是ubuntu会有如下bug,4.15的内核依然存在
    
    kernel:unregister_netdevice: waiting for lo to become free. Usage count = 1
    
    #安装必要软件包
    
    yum install wget git  jq psmisc vim perl -y
    
    #升级内核需要使用 elrepo 的yum 源,首先我们导入 elrepo 的 key并安装 elrepo 源
    
    rpm --import https://www.elrepo.org/RPM-GPG-KEY-elrepo.org
    rpm -Uvh http://www.elrepo.org/elrepo-release-7.0-2.el7.elrepo.noarch.rpm
    
    #查看可用内核
    yum --disablerepo="*" --enablerepo="elrepo-kernel" list available  --showduplicates
    
    #自选版本内核安装方法
    export Kernel_Vsersion=4.18.16-1
    wget  http://mirror.rc.usf.edu/compute_lock/elrepo/kernel/el7/x86_64/RPMS/kernel-ml{,-devel}-${Kernel_Vsersion}.el7.elrepo.x86_64.rpm
    yum localinstall -y kernel-ml*
    
    #查看这个内核里是否有这个内核模块
    find /lib/modules -name '*nf_conntrack_ipv4*' -type f
    
    #修改内核启动顺序,默认启动的顺序应该为1,升级以后内核是往前面插入,为0(如果每次启动时需要手动选择哪个内核,该步骤可以省略)
    grub2-set-default  0 && grub2-mkconfig -o /etc/grub2.cfg
    
    #使用下面命令看看确认下是否启动默认内核指向上面安装的内核
    grubby --default-kernel
    
    #docker官方的内核检查脚本建议(RHEL7/CentOS7: User namespaces disabled; add 'user_namespace.enable=1' to boot command line),使用下面命令开启
    grubby --args="user_namespace.enable=1" --update-kernel="$(grubby --default-kernel)"
    
    #重新加载内核
    reboot

     

  6. 设置IPVS模块所需加载的模块(所有机器)
    $ :> /etc/modules-load.d/ipvs.conf
    $ module=(
      ip_vs
      ip_vs_lc
      ip_vs_wlc
      ip_vs_rr
      ip_vs_wrr
      ip_vs_lblc
      ip_vs_lblcr
      ip_vs_dh
      ip_vs_sh
      ip_vs_fo
      ip_vs_nq
      ip_vs_sed
      ip_vs_ftp
      )
    $ for kernel_module in ${module[@]};do
        /sbin/modinfo -F filename $kernel_module |& grep -qv ERROR && echo $kernel_module >> /etc/modules-load.d/ipvs.conf || :
    done
    $ systemctl enable --now systemd-modules-load.service

     

  7. 需要设定/etc/sysctl.d/k8s.conf的系统参数
    $ cat <<EOF > /etc/sysctl.d/k8s.conf
    # https://github.com/moby/moby/issues/31208 
    # ipvsadm -l --timout
    # 修复ipvs模式下长连接timeout问题 小于900即可
    net.ipv4.tcp_keepalive_time = 600
    net.ipv4.tcp_keepalive_intvl = 30
    net.ipv4.tcp_keepalive_probes = 10
    net.ipv6.conf.all.disable_ipv6 = 1
    net.ipv6.conf.default.disable_ipv6 = 1
    net.ipv6.conf.lo.disable_ipv6 = 1
    net.ipv4.neigh.default.gc_stale_time = 120
    net.ipv4.conf.all.rp_filter = 0
    net.ipv4.conf.default.rp_filter = 0
    net.ipv4.conf.default.arp_announce = 2
    net.ipv4.conf.lo.arp_announce = 2
    net.ipv4.conf.all.arp_announce = 2
    net.ipv4.ip_forward = 1
    net.ipv4.tcp_max_tw_buckets = 5000
    net.ipv4.tcp_syncookies = 1
    net.ipv4.tcp_max_syn_backlog = 1024
    net.ipv4.tcp_synack_retries = 2
    net.bridge.bridge-nf-call-ip6tables = 1
    net.bridge.bridge-nf-call-iptables = 1
    net.netfilter.nf_conntrack_max = 2310720
    fs.inotify.max_user_watches=89100
    fs.may_detach_mounts = 1
    fs.file-max = 52706963
    fs.nr_open = 52706963
    net.bridge.bridge-nf-call-arptables = 1
    vm.swappiness = 0
    vm.overcommit_memory=1
    vm.panic_on_oom=0
    EOF
    
    $ sysctl --system

     

  8. 以上条件必须严格检查,否则,一定不会部署成功!

1.设置部署节点到其它所有节点的SSH免密码登录(包括本机)

[root@linux-node1 ~]# ssh-keygen -t rsa
[root@linux-node1 ~]# ssh-copy-id linux-node1
[root@linux-node1 ~]# ssh-copy-id linux-node2
[root@linux-node1 ~]# ssh-copy-id linux-node3
[root@linux-node1 ~]# ssh-copy-id linux-node4
[root@linux-node1 ~]# scp /etc/hosts linux-node2:/etc/
[root@linux-node1 ~]# scp /etc/hosts linux-node3:/etc/
[root@linux-node1 ~]# scp /etc/hosts linux-node4:/etc/

2.安装Salt-SSH并克隆本项目代码。

2.1 安装Salt SSH(注意:老版本的Salt SSH不支持Roster定义Grains,需要2017.7.4以上版本)

[root@linux-node1 ~]# yum install -y https://mirrors.aliyun.com/saltstack/yum/redhat/salt-repo-latest-2.el7.noarch.rpm
[root@linux-node1 ~]# sed -i "s/repo.saltstack.com/mirrors.aliyun.com\/saltstack/g" /etc/yum.repos.d/salt-latest.repo
[root@linux-node1 ~]# yum install -y salt-ssh git unzip

 

2.2 获取本项目代码,并放置在 /srv 目录

[root@linux-node1 ~]# git clone https://github.com/skymyyang/salt-k8s-ha.git
[root@linux-node1 ~]# cd salt-k8s-ha/
[root@linux-node1 ~]# mv * /srv/
[root@linux-node1 srv]# /bin/cp /srv/roster /etc/salt/roster
[root@linux-node1 srv]# /bin/cp /srv/master /etc/salt/master

 

2.3 下载二进制文件,也可以自行官方下载,为了方便国内用户访问,请在百度云盘下载,下载k8s-v1.12.5-auto.zip。 下载完成后,将 files 目录移动到 /srv/salt/k8s/ 目录下,并解压 Kubernetes二进制文件下载地址: https://pan.baidu.com/s/1Ag2ocpVmkg-uEoV13A7HFw

[root@linux-node1 ~]# cd /srv/salt/k8s/
[root@linux-node1 k8s]# unzip k8s-v1.12.5-auto.zip
[root@linux-node1 k8s]# rm -f k8s-v1.12.5-auto.zip
[root@linux-node1 k8s]# ls -l files/
total 0
drwxr-xr-x 2 root root  94 Jan 18 19:19 cfssl-1.2
drwxr-xr-x 2 root root 195 Jan 18 19:19 cni-plugins-amd64-v0.7.4
drwxr-xr-x 3 root root 123 Jan 18 19:19 etcd-v3.3.10-linux-amd64
drwxr-xr-x 2 root root  47 Jan 18 19:19 flannel-v0.10.0-linux-amd64
drwxr-xr-x 3 root root  17 Jan 18 19:19 k8s-v1.12.5

 

 

3.Salt SSH管理的机器以及角色分配

  • k8s-role: 用来设置K8S的角色
  • etcd-role: 用来设置etcd的角色,如果只需要部署一个etcd,只需要在一台机器上设置即可
  • etcd-name: 如果对一台机器设置了etcd-role就必须设置etcd-name
[root@linux-node1 ~]# vim /etc/salt/roster
linux-node1:
  host: 192.168.150.141
  user: root
  priv: /root/.ssh/id_rsa
  minion_opts:
    grains:
      k8s-role: master
      etcd-role: node
      etcd-name: etcd-node1

linux-node2:
  host: 192.168.150.142
  user: root
  priv: /root/.ssh/id_rsa
  minion_opts:
    grains:
      k8s-role: master
      etcd-role: node
      etcd-name: etcd-node2

linux-node3:
  host: 192.168.150.143
  user: root
  priv: /root/.ssh/id_rsa
  minion_opts:
    grains:
      k8s-role: master
      etcd-role: node
      etcd-name: etcd-node3

linux-node4:
  host: 192.168.150.144
  user: root
  priv: /root/.ssh/id_rsa
  minion_opts:
    grains:
      k8s-role: node

 

 

4.修改对应的配置参数,本项目使用Salt Pillar保存配置

[root@k8s-m1 ~]# vim /srv/pillar/k8s.sls
#设置Master的IP地址(必须修改)
MASTER_IP_M1: "192.168.150.141"
MASTER_IP_M2: "192.168.150.142"
MASTER_IP_M3: "192.168.150.143"
#设置Master的HOSTNAME完整的FQDN名称(必须修改)
MASTER_H1: "linux-node1"
MASTER_H2: "linux-node2"
MASTER_H3: "linux-node3"

#设置ETCD集群访问地址(必须修改)
ETCD_ENDPOINTS: "https://192.168.150.141:2379,https://192.168.150.142:2379,https://192.168.150.143:2379"

FLANNEL_ETCD_PREFIX: "/kubernetes/network"

#设置ETCD集群初始化列表(必须修改)
ETCD_CLUSTER: "etcd-node1=https://192.168.150.141:2380,etcd-node2=https://192.168.150.142:2380,etcd-node3=https://192.168.150.143:2380"

#通过Grains FQDN自动获取本机IP地址,请注意保证主机名解析到本机IP地址
NODE_IP: {{ grains['fqdn_ip4'][0] }}
HOST_NAME: {{ grains['fqdn'] }}
#设置BOOTSTARP的TOKEN,可以自己生成
BOOTSTRAP_TOKEN: "be8dad.da8a699a46edc482"
TOKEN_ID: "be8dad"
TOKEN_SECRET: "da8a699a46edc482"
ENCRYPTION_KEY: "8eVtmpUpYjMvH8wKZtKCwQPqYRqM14yvtXPLJdhu0gA="
#配置Service IP地址段
SERVICE_CIDR: "10.1.0.0/16"

#Kubernetes服务 IP (从 SERVICE_CIDR 中预分配)
CLUSTER_KUBERNETES_SVC_IP: "10.1.0.1"

#Kubernetes DNS 服务 IP (从 SERVICE_CIDR 中预分配)
CLUSTER_DNS_SVC_IP: "10.1.0.2"

#设置Node Port的端口范围
NODE_PORT_RANGE: "20000-40000"

#设置POD的IP地址段
POD_CIDR: "10.2.0.0/16"

#设置集群的DNS域名
CLUSTER_DNS_DOMAIN: "cluster.local."

#设置Docker Registry地址
#DOCKER_REGISTRY: "https://192.168.150.135:5000"

#设置Master的VIP地址(必须修改)
MASTER_VIP: "192.168.150.253"

#设置网卡名称
VIP_IF: "ens32"

 

5.执行SaltStack状态

  1. 测试Salt SSH联通性
    [root@k8s-m1 ~]# salt-ssh '*' test.ping

    执行高级状态,会根据定义的角色再对应的机器部署对应的服务

  2. 部署Etcd,由于Etcd是基础组建,需要先部署,目标为部署etcd的节点
    [root@linux-node1 ~]# salt-ssh -L 'linux-node1,linux-node2,linux-node3' state.sls k8s.etcd

     

  3. 部署K8S集群
    [root@linux-node1 ~]# salt-ssh '*' state.highstate

    由于包比较大,根据电脑硬件配置,这里执行时间较长,5分钟+,喝杯咖啡休息一下,如果执行有失败可以再次执行即可!

6.测试Kubernetes安装

#先验证etcd
[root@linux-node1 ~]# source /etc/profile
[root@linux-node1 ~]# etcdctl --endpoints=https://192.168.150.141:2379 \
  --ca-file=/opt/kubernetes/ssl/ca.pem \
  --cert-file=/opt/kubernetes/ssl/etcd.pem \
  --key-file=/opt/kubernetes/ssl/etcd-key.pem cluster-health
[root@linux-node1 ~]# etcdctl --endpoints=https://192.168.150.141:2379 \
  --ca-file=/opt/kubernetes/ssl/ca.pem \
  --cert-file=/opt/kubernetes/ssl/etcd.pem \
  --key-file=/opt/kubernetes/ssl/etcd-key.pem member list
[root@linux-node1 ~]# kubectl get cs
NAME                 STATUS    MESSAGE             ERROR
controller-manager   Healthy   ok                  
scheduler            Healthy   ok                  
etcd-2               Healthy   {"health":"true"}   
etcd-1               Healthy   {"health":"true"}   
etcd-0               Healthy   {"health":"true"}  
[root@k8s-m1 ~]# kubectl get node
NAME          STATUS   ROLES    AGE   VERSION
linux-node1   Ready    master   14m   v1.12.5
linux-node2   Ready    master   24m   v1.12.5
linux-node3   Ready    master   24m   v1.12.5
linux-node4   Ready    node     30m   v1.12.5

 

7.测试Kubernetes集群和Flannel网络

[root@linux-node1 ~]# kubectl create deployment nginx --image=nginx:alpine
deployment.apps/nginx created
需要等待拉取镜像,可能稍有的慢,请等待。
[root@linux-node1 ~]# kubectl get pod
NAME                     READY   STATUS    RESTARTS   AGE
nginx-54458cd494-8fj47   1/1     Running   0          13s

[root@linux-node1 ~]# kubectl get pod -o wide
NAME                     READY   STATUS    RESTARTS   AGE    IP          NODE          NOMINATED NODE   READINESS GATES
nginx-54458cd494-8fj47   1/1     Running   0          111s   10.2.70.3   linux-node1   <none>           <none>



测试联通性
[root@linux-node1 ~]# ping -c 1 10.2.70.3
PING 10.2.69.2 (10.2.69.2) 56(84) bytes of data.
64 bytes from 10.2.69.2: icmp_seq=1 ttl=61 time=2.02 ms

--- 10.2.69.2 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 2.028/2.028/2.028/0.000 ms

[root@linux-node1 ~]# curl --head http://10.2.70.3
HTTP/1.1 200 OK
Server: nginx/1.15.8
Date: Wed, 27 Feb 2019 09:52:48 GMT
Content-Type: text/html
Content-Length: 612
Last-Modified: Thu, 31 Jan 2019 23:32:11 GMT
Connection: keep-alive
ETag: "5c53857b-264"
Accept-Ranges: bytes

测试扩容,将Nginx应用的Pod副本数量拓展到2个节点
[root@linux-node1 ~]# kubectl scale deployment nginx --replicas=2
deployment.extensions/nginx scaled

[root@linux-node1 ~]# kubectl get pod
NAME                     READY   STATUS    RESTARTS   AGE
nginx-54458cd494-8fj47   1/1     Running   0          5m4s
nginx-54458cd494-qzhpf   1/1     Running   0          17s

8.如何新增Kubernetes节点

  • 设置SSH无密码登录,并且在 /etc/hosts 中继续增加对应的解析。确保所有节点都能解析
  • 在 /etc/salt/roster 里面,增加对应的机器
  • 执行SaltStack状态 salt-ssh '*' state.highstate
[root@linux-node5 ~]# vim /etc/salt/roster
linux-node5:
  host: 192.168.150.145
  user: root
  priv: /root/.ssh/id_rsa
  minion_opts:
    grains:
      k8s-role: node
[root@linux-node1 ~]# salt-ssh 'linux-node5' state.highstate

9.下一步要做什么?

你可以安装Kubernetes必备的插件。如何安装必备的插件。请参考该项目的原地址

 

posted @ 2019-03-12 18:39  Devops、小铁匠  阅读(1939)  评论(1编辑  收藏  举报