corosync集群构建--高可用web

一、实验环境

  1、集群共4台Contos7机器
  2、关闭selinux，iptables，firewalld
  3、修改主机名分别为node[1-4],并配置hosts
  4、时间同步
  5、考虑是否用到仲裁设备（这里不使用）

二、安装配置

  CentOS 7: corosync v2 + pacemaker
    corosync v2:vote system
    pacemaker:独立服务

  集群全生命周期管理工具
    pcs yum info pcs
    crmsh

  1、安装并启动pcsd（all node）
    [root@node1~]# yum install pcs -y
    [root@node1~]# rpm -ql pcs #查看安装的文件
    [root@node1~]# systemctl start pcsd && systemctl enable pcsd
    [root@node1~]# echo "test123456" | passwd --stdin hacluster #为hacluster用户设置密码

  2、配置corosync （arbitrary node）这里在node1
    [root@node1 ~]# pcs cluster auth node1 node2 node3 node4 -u hacluster #输入刚刚echo的密码，成功后会看到如下提示

pcs集群认证
    [root@node1 ~]# pcs cluster setup --name mycluster node1 node2 node3 node4 #设置集群并同步生成的配置文件到/etc/corosync/
image.png
    [root@node1 ~]# 查看生成的配置文件
image.png
   查看配置文件(这里无需修改)

[root@node1 ~]# cat /etc/corosync/corosync.conf
totem {
    version: 2
    secauth: off
    cluster_name: mycluster
    transport: udpu
}

nodelist {
    node {
        ring0_addr: node1
        nodeid: 1
    }

    node {
        ring0_addr: node2
        nodeid: 2
    }

    node {
        ring0_addr: node3
        nodeid: 3
    }

    node {
        ring0_addr: node4
        nodeid: 4
    }
}

quorum {
    provider: corosync_votequorum
}

logging {
    to_logfile: yes
    logfile: /var/log/cluster/corosync.log
    to_syslog: yes
}
[root@node1 ~]# 

  3、启动集群

[root@node1 ~]# pcs cluster start --all
node1: Starting Cluster...
node2: Starting Cluster...
node3: Starting Cluster...
node4: Starting Cluster...

  4、验证是否启动

[root@node1 ~]# corosync-cfgtool -s
Printing ring status.
Local node ID 1
RING ID 0
    id  = 192.168.66.129
    status  = ring 0 active with no faults

[root@node1 ~]# pcs status 
Cluster name: mycluster
WARNING: no stonith devices and stonith-enabled is not false
Stack: corosync
Current DC: node1 (version 1.1.16-12.el7_4.8-94ff4df) - partition with quorum #全局决策节点
Last updated: Wed Apr 18 14:40:39 2018
Last change: Wed Apr 18 14:37:50 2018 by hacluster via crmd on node1

4 nodes configured
0 resources configured

Online: [ node1 node2 node3 node4 ]

No resources


Daemon Status:
  corosync: active/disabled
  pacemaker: active/disabled
  pcsd: active/enabled
#看到enable 为正常状态
#关闭警告stonith
[root@node1 ~]# pcs property set stonith-enabled=false
[root@node1 ~]# pcs property list
Cluster Properties:
 cluster-infrastructure: corosync
 cluster-name: mycluster
 dc-version: 1.1.16-12.el7_4.8-94ff4df
 have-watchdog: false
 stonith-enabled: false

  5、安装配置crmsh

[root@node1 ~]# cd /etc/yum.repos.d/
[root@node1 yum.repos.d]# wget http://download.opensuse.org/repositories/network:/ha-clustering:/Stable/CentOS_CentOS-7/network:ha-clustering:Stable.repo
[root@node1 ~]#  yum install wget -y
#会提示丢包,去下载单独安装
python-parallax-1.0.1-29.1.noarch: [Errno 256] No more mirrors to try.
[root@node1 ~]# wget ftp://ftp.pbone.net/mirror/ftp5.gwdg.de/pub/opensuse/repositories/devel:/languages:/python/SLE_11_SP3/x86_64/python-parallax-1.0.1-9.8.x86_64.rpm
[root@node1 ~]# yum install -y python-parallax-1.0.1-9.8.x86_64.rpm 
[root@node1 ~]#  yum install wget -y 

基础的集群已经配置完毕，下面配置高可用httpd

三、高可用web服务

  1、资源为httpd 和 vip
  2、所有节点安装httpd [root@node1 ~]# yum install httpd -y

#为演示效果，为每个节点提供不同的页面
[root@node1 ~]# echo '<h1>node1</h1>' >> /var/www/html/index.html
[root@node1 ~]# 
[root@node1 ~]# systemctl disable httpd     #启动哪个节点的httpd有rm决定 (7不用 ，以为就算开机启动，在7也是第一次访问才启动)

  3、配置资源

[root@node1 ~]# crm ra
crm(live)ra# list systemctl
ERROR: ra.list: class systemctl does not exist
crm(live)ra# list systemd    #找到httpd  7必须enable httpd
getty@tty1                                                gssproxy
httpd                                                     ip6tables
ipset                                                     iptables
crm(live)ra# 
#配置vip资源
crm(live)ra# info ocf:heartbeat:IPaddr
crm(live)ra# cd
crm(live)# configure
crm(live)configure# primitive webip ocf:heartbeat:IPaddr params ip=192.168.66.200
crm(live)configure# show
node 1: node1
node 2: node2
node 3: node3
node 4: node4
primitive webip IPaddr \
    params ip=192.168.66.200
property cib-bootstrap-options: \
    have-watchdog=false \
    dc-version=1.1.16-12.el7_4.8-94ff4df \
    cluster-infrastructure=corosync \
    cluster-name=mycluster \
    stonith-enabled=false

#验证webip 并提交
crm(live)configure# verify    
crm(live)configure# commit
crm(live)configure# cd
crm(live)# status
Stack: corosync
Current DC: node1 (version 1.1.16-12.el7_4.8-94ff4df) - partition with quorum
Last updated: Wed Apr 18 15:46:56 2018
Last change: Wed Apr 18 15:46:51 2018 by root via cibadmin on node1

4 nodes configured
1 resource configured

Online: [ node1 node2 node3 node4 ]

Full list of resources:

 webip  (ocf::heartbeat:IPaddr):    Started node1

crm(live)# 

#node standby 节点软下线  可以测试资源转移
#同样的方式定义httpd资源
crm(live)# configure
crm(live)configure# primitive webserver systemd:httpd 
#验证webserver并提交
crm(live)configure# verify    
crm(live)configure# commit
crm(live)configure# cd
crm(live)# status
Stack: corosync
Current DC: node1 (version 1.1.16-12.el7_4.8-94ff4df) - partition with quorum
Last updated: Wed Apr 18 15:55:57 2018
Last change: Wed Apr 18 15:55:09 2018 by root via cibadmin on node1

4 nodes configured
2 resources configured

Online: [ node1 node2 node3 node4 ]

Full list of resources:

 webip  (ocf::heartbeat:IPaddr):    Started node2
 webserver  (systemd:httpd):    Started node1
#此时 webip 和 webserver在不同节点，不是我们期望的，下面定义组资源，让他们在同一个节点

crm(live)# configure
crm(live)configure# group webservice webip webserver  #ip先启动
crm(live)configure# verify
crm(live)configure# commit
crm(live)configure# cd
crm(live)# status
Stack: corosync
Current DC: node1 (version 1.1.16-12.el7_4.8-94ff4df) - partition with quorum
Last updated: Wed Apr 18 15:59:54 2018
Last change: Wed Apr 18 15:59:49 2018 by root via cibadmin on node1

4 nodes configured
2 resources configured

Online: [ node1 node2 node3 node4 ]

Full list of resources:

 Resource Group: webservice
     webip  (ocf::heartbeat:IPaddr):    Started node2
     webserver  (systemd:httpd):    Started node2

至此高可用httpd就完成了