实验拓扑图：
node1主机名配置
[root@localhost ~]# vim /etc/sysconfig/network
3 HOSTNAME=node1.a.com
[root@localhost ~]# hostname node1.a.com #配置后需注销才能生效
[root@localhost ~]# hostname #查看主机名
node1.a.com
配置本地DNS解析
[root@node1 ~]# vim /etc/hosts
5 192.168.2.10 node1.a.com
6 192.168.2.11 node2.a.com
同步时间
[root@node1 ~]# hwclock -s
node2主机名配置
[root@localhost ~]# vim /etc/sysconfig/network
3 HOSTNAME=node1.a.com
[root@localhost ~]# hostname node2.a.com #配置后需注销才能生效
[root@localhost ~]# hostname #查看主机名
node1.a.com
配置本地DNS解析
[root@node2 ~]# vim /etc/hosts
5 192.168.2.10 node1.a.com
6 192.168.2.11 node2.a.com
同步时间
[root@node1 ~]# hwclock -s
实现无障碍copy
node1上配置：
产生钥匙对
[root@node1 ~]# ssh-keygen -t rsa
Generating public/private rsa key pair.
Enter file in which to save the key (/root/.ssh/id_rsa):
Created directory '/root/.ssh'.
Enter passphrase (empty for no passphrase):
Enter same passphrase again:
Your identification has been saved in /root/.ssh/id_rsa.
Your public key has been saved in /root/.ssh/id_rsa.pub.
The key fingerprint is:
86:36:c5:c6:70:2b:b9:13:27:b2:c6:6e:f4:2a:ce:ab [email protected]
将公钥copy给node2
[root@node1 ~]# ssh-copy-id -i .ssh/id_rsa.pub [email protected]
15
The authenticity of host 'node2.a.com (192.168.2.11)' can't be established.
RSA key fingerprint is 3a:64:a0:6e:d0:21:14:6c:e9:1e:84:50:89:42:05:29.
Are you sure you want to continue connecting (yes/no)? yes
Warning: Permanently added 'node2.a.com,192.168.2.11' (RSA) to the list of known hosts.
[email protected]'s password:
Now try logging into the machine, with "ssh '[email protected]'", and check in:
[root@localhost ~]# vim /etc/sysconfig/network
3 HOSTNAME=node1.a.com
[root@localhost ~]# hostname node2.a.com #配置后需注销才能生效
[root@localhost ~]# hostname #查看主机名
node1.a.com
配置本地DNS解析
[root@node2 ~]# vim /etc/hosts
5 192.168.2.10 node1.a.com
6 192.168.2.11 node2.a.com
同步时间
[root@node1 ~]# hwclock -s
实现无障碍copy
node1上配置：
产生钥匙对
[root@node1 ~]# ssh-keygen -t rsa
Generating public/private rsa key pair.
Enter file in which to save the key (/root/.ssh/id_rsa):
Created directory '/root/.ssh'.
Enter passphrase (empty for no passphrase):
Enter same passphrase again:
Your identification has been saved in /root/.ssh/id_rsa.
Your public key has been saved in /root/.ssh/id_rsa.pub.
The key fingerprint is:
86:36:c5:c6:70:2b:b9:13:27:b2:c6:6e:f4:2a:ce:ab [email protected]
将公钥copy给node2
[root@node1 ~]# ssh-copy-id -i .ssh/id_rsa.pub [email protected]
15
The authenticity of host 'node2.a.com (192.168.2.11)' can't be established.
RSA key fingerprint is 3a:64:a0:6e:d0:21:14:6c:e9:1e:84:50:89:42:05:29.
Are you sure you want to continue connecting (yes/no)? yes
Warning: Permanently added 'node2.a.com,192.168.2.11' (RSA) to the list of known hosts.
[email protected]'s password:
Now try logging into the machine, with "ssh '[email protected]'", and check in:
.ssh/authorized_keys
to make sure we haven't added extra keys that you weren't expecting.
在node2上同样这样操作
[root@node2 ~]# ssh-keygen -t rsa
Generating public/private rsa key pair.
Enter file in which to save the key (/root/.ssh/id_rsa):
Enter passphrase (empty for no passphrase):
Enter same passphrase again:
Your identification has been saved in /root/.ssh/id_rsa.
Your public key has been saved in /root/.ssh/id_rsa.pub.
The key fingerprint is:
05:fb:ac:d5:83:f0:b2:12:73:1d:87:38:38:8f:2d:04 [email protected]
[root@node2 ~]# ssh-copy-id -i .ssh/id_rsa.pub [email protected]
15
The authenticity of host 'node1.a.com (192.168.2.10)' can't be established.
RSA key fingerprint is 3a:64:a0:6e:d0:21:14:6c:e9:1e:84:50:89:42:05:29.
Are you sure you want to continue connecting (yes/no)? yes
Warning: Permanently added 'node1.a.com,192.168.2.10' (RSA) to the list of known hosts.
[email protected]'s password:
Now try logging into the machine, with "ssh '[email protected]'", and check in:
在node2上同样这样操作
[root@node2 ~]# ssh-keygen -t rsa
Generating public/private rsa key pair.
Enter file in which to save the key (/root/.ssh/id_rsa):
Enter passphrase (empty for no passphrase):
Enter same passphrase again:
Your identification has been saved in /root/.ssh/id_rsa.
Your public key has been saved in /root/.ssh/id_rsa.pub.
The key fingerprint is:
05:fb:ac:d5:83:f0:b2:12:73:1d:87:38:38:8f:2d:04 [email protected]
[root@node2 ~]# ssh-copy-id -i .ssh/id_rsa.pub [email protected]
15
The authenticity of host 'node1.a.com (192.168.2.10)' can't be established.
RSA key fingerprint is 3a:64:a0:6e:d0:21:14:6c:e9:1e:84:50:89:42:05:29.
Are you sure you want to continue connecting (yes/no)? yes
Warning: Permanently added 'node1.a.com,192.168.2.10' (RSA) to the list of known hosts.
[email protected]'s password:
Now try logging into the machine, with "ssh '[email protected]'", and check in:
.ssh/authorized_keys
to make sure we haven't added extra keys that you weren't expecting.
导入实验所需的软件包，如图：
安装服务：（提前配置好yum环境）
[root@node1 ~]# yum localinstall -y *.rpm --nogpgcheck
安装成功，如下图：
[root@node1 ~]# yum localinstall -y *.rpm --nogpgcheck
安装成功，如下图：
把软件包copy到node2
[root@node1 ~]# scp *.rpm node2:/root
如下图：
安装服务：（提前配置好yum环境）
[root@node2 ~]# yum localinstall -y *.rpm --nogpgcheck
安装成功，如下图：
[root@node1 ~]# scp *.rpm node2:/root
如下图：
安装服务：（提前配置好yum环境）
[root@node2 ~]# yum localinstall -y *.rpm --nogpgcheck
安装成功，如下图：
修改配置文件
[root@node1 ~]# cd /etc/corosync/
[root@node1 corosync]# ls
amf.conf.example corosync.conf.example service.d uidgid.d
[root@node1 corosync]# cp corosync.conf.example corosync.conf
[root@node1 corosync]# vim corosync.conf
[root@node1 corosync]# vim corosync.conf
bindnetaddr: 192.168.2.0
补充一些东西，前面只是底层的东西，因为要用
[root@node1 ~]# cd /etc/corosync/
[root@node1 corosync]# ls
amf.conf.example corosync.conf.example service.d uidgid.d
[root@node1 corosync]# cp corosync.conf.example corosync.conf
[root@node1 corosync]# vim corosync.conf
[root@node1 corosync]# vim corosync.conf
bindnetaddr: 192.168.2.0
补充一些东西，前面只是底层的东西，因为要用
pacemakerservice {
ver: 0
name: pacemaker
}
虽然用不到openais ，但是会用到一些子选项
ver: 0
name: pacemaker
}
虽然用不到openais ，但是会用到一些子选项
aisexec {
user: root
group: root
}
在node1，node2上创建目录
[root@node1 corosync]# mkdir /var/log/cluster
[root@node1 corosync]# ssh node2.a.com 'mkdir /var/log/cluster'
为了便面其他主机加入该集群，需要认证，生成一个authkey
[root@node1 corosync]# corosync-keygen
Corosync Cluster Engine Authentication key generator.
Gathering 1024 bits for key from /dev/random.
Press keys on your keyboard to generate entropy.
Writing corosync key to /etc/corosync/authkey.
将authkey，配置文件copy到node2上
[root@node1 corosync]# scp -p authkey corosync.conf node2.a.com:/etc/corosync/
authkey 100% 128 0.1KB/s 00:00
corosync.conf
在node1，node2上启动服务
[root@node1 corosync]# service corosync start
Starting Corosync Cluster Engine (corosync): [ OK ]
[root@node1 corosync]# ssh node2.a.com 'service corosync start'
Starting Corosync Cluster Engine (corosync): [ OK ]
[root@node1 corosync]#
验证corosync引擎是否正常启动了
[root@node1 corosync]# grep -i -e "corosync cluster engine" -e "configuration file" /var/log/messages
Sep 18 01:52:10 localhost smartd[3123]: Opened configuration file /etc/smartd.conf
Sep 18 01:52:10 localhost smartd[3123]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Sep 18 02:02:24 localhost smartd[2991]: Opened configuration file /etc/smartd.conf
Sep 18 02:02:24 localhost smartd[2991]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Oct 18 18:30:10 localhost smartd[2990]: Opened configuration file /etc/smartd.conf
Oct 18 18:30:10 localhost smartd[2990]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Oct 19 19:30:18 localhost smartd[2990]: Opened configuration file /etc/smartd.conf
Oct 19 19:30:18 localhost smartd[2990]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Oct 19 20:31:22 localhost corosync[3391]: [MAIN ] Corosync Cluster Engine ('1.2.7'): started and ready to provide service.
Oct 19 20:31:22 localhost corosync[3391]: [MAIN ] Successfully read main configuration file '/etc/corosync/corosync.conf'.
Oct 19 20:40:32 localhost corosync[3391]: [MAIN ] Corosync Cluster Engine exiting with status 0 at main.c:170.
Oct 19 20:40:32 localhost corosync[13918]: [MAIN ] Corosync Cluster Engine ('1.2.7'): started and ready to provide service.
Oct 19 20:40:32 localhost corosync[13918]: [MAIN ] Successfully read main configuration file '/etc/corosync/corosync.conf'.
查看初始化成员节点通知是否发出
[root@node1 corosync]# grep -i totem /var/log/messages
Oct 19 20:40:33 localhost corosync[13918]: [TOTEM ] The network interface [192.168.2.10] is now up.
Oct 19 20:40:33 localhost corosync[13918]: [TOTEM ] Process pause detected for 748 ms, flushing membership messages.
Oct 19 20:40:33 localhost corosync[13918]: [TOTEM ] A processor joined or left the membership and a new membership was formed.
Oct 19 20:41:11 localhost corosync[13918]: [TOTEM ] A processor joined or left the membership and a new membership was formed.
检查过程中是否有错误产生
[root@node1 corosync]# grep -i error: /var/log/messages
检查pacemaker时候已经启动了
[root@node1 corosync]# grep -i pcmk_startup /var/log/messages
Oct 19 20:31:22 localhost corosync[3391]: [pcmk ] info: pcmk_startup: CRM: Initialized
Oct 19 20:31:22 localhost corosync[3391]: [pcmk ] Logging: Initialized pcmk_startup
Oct 19 20:31:22 localhost corosync[3391]: [pcmk ] info: pcmk_startup: Maximum core file size is: 4294967295
Oct 19 20:31:22 localhost corosync[3391]: [pcmk ] info: pcmk_startup: Service: 9
Oct 19 20:31:22 localhost corosync[3391]: [pcmk ] info: pcmk_startup: Local hostname: node1.a.com
Oct 19 20:40:33 localhost corosync[13918]: [pcmk ] info: pcmk_startup: CRM: Initialized
Oct 19 20:40:33 localhost corosync[13918]: [pcmk ] Logging: Initialized pcmk_startup
Oct 19 20:40:33 localhost corosync[13918]: [pcmk ] info: pcmk_startup: Maximum core file size is: 4294967295
Oct 19 20:40:33 localhost corosync[13918]: [pcmk ] info: pcmk_startup: Service: 9
Oct 19 20:40:33 localhost corosync[13918]: [pcmk ] info: pcmk_startup: Local hostname: node1.a.com
[root@node1 corosync]#
user: root
group: root
}
在node1，node2上创建目录
[root@node1 corosync]# mkdir /var/log/cluster
[root@node1 corosync]# ssh node2.a.com 'mkdir /var/log/cluster'
为了便面其他主机加入该集群，需要认证，生成一个authkey
[root@node1 corosync]# corosync-keygen
Corosync Cluster Engine Authentication key generator.
Gathering 1024 bits for key from /dev/random.
Press keys on your keyboard to generate entropy.
Writing corosync key to /etc/corosync/authkey.
将authkey，配置文件copy到node2上
[root@node1 corosync]# scp -p authkey corosync.conf node2.a.com:/etc/corosync/
authkey 100% 128 0.1KB/s 00:00
corosync.conf
在node1，node2上启动服务
[root@node1 corosync]# service corosync start
Starting Corosync Cluster Engine (corosync): [ OK ]
[root@node1 corosync]# ssh node2.a.com 'service corosync start'
Starting Corosync Cluster Engine (corosync): [ OK ]
[root@node1 corosync]#
验证corosync引擎是否正常启动了
[root@node1 corosync]# grep -i -e "corosync cluster engine" -e "configuration file" /var/log/messages
Sep 18 01:52:10 localhost smartd[3123]: Opened configuration file /etc/smartd.conf
Sep 18 01:52:10 localhost smartd[3123]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Sep 18 02:02:24 localhost smartd[2991]: Opened configuration file /etc/smartd.conf
Sep 18 02:02:24 localhost smartd[2991]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Oct 18 18:30:10 localhost smartd[2990]: Opened configuration file /etc/smartd.conf
Oct 18 18:30:10 localhost smartd[2990]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Oct 19 19:30:18 localhost smartd[2990]: Opened configuration file /etc/smartd.conf
Oct 19 19:30:18 localhost smartd[2990]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Oct 19 20:31:22 localhost corosync[3391]: [MAIN ] Corosync Cluster Engine ('1.2.7'): started and ready to provide service.
Oct 19 20:31:22 localhost corosync[3391]: [MAIN ] Successfully read main configuration file '/etc/corosync/corosync.conf'.
Oct 19 20:40:32 localhost corosync[3391]: [MAIN ] Corosync Cluster Engine exiting with status 0 at main.c:170.
Oct 19 20:40:32 localhost corosync[13918]: [MAIN ] Corosync Cluster Engine ('1.2.7'): started and ready to provide service.
Oct 19 20:40:32 localhost corosync[13918]: [MAIN ] Successfully read main configuration file '/etc/corosync/corosync.conf'.
查看初始化成员节点通知是否发出
[root@node1 corosync]# grep -i totem /var/log/messages
Oct 19 20:40:33 localhost corosync[13918]: [TOTEM ] The network interface [192.168.2.10] is now up.
Oct 19 20:40:33 localhost corosync[13918]: [TOTEM ] Process pause detected for 748 ms, flushing membership messages.
Oct 19 20:40:33 localhost corosync[13918]: [TOTEM ] A processor joined or left the membership and a new membership was formed.
Oct 19 20:41:11 localhost corosync[13918]: [TOTEM ] A processor joined or left the membership and a new membership was formed.
检查过程中是否有错误产生
[root@node1 corosync]# grep -i error: /var/log/messages
检查pacemaker时候已经启动了
[root@node1 corosync]# grep -i pcmk_startup /var/log/messages
Oct 19 20:31:22 localhost corosync[3391]: [pcmk ] info: pcmk_startup: CRM: Initialized
Oct 19 20:31:22 localhost corosync[3391]: [pcmk ] Logging: Initialized pcmk_startup
Oct 19 20:31:22 localhost corosync[3391]: [pcmk ] info: pcmk_startup: Maximum core file size is: 4294967295
Oct 19 20:31:22 localhost corosync[3391]: [pcmk ] info: pcmk_startup: Service: 9
Oct 19 20:31:22 localhost corosync[3391]: [pcmk ] info: pcmk_startup: Local hostname: node1.a.com
Oct 19 20:40:33 localhost corosync[13918]: [pcmk ] info: pcmk_startup: CRM: Initialized
Oct 19 20:40:33 localhost corosync[13918]: [pcmk ] Logging: Initialized pcmk_startup
Oct 19 20:40:33 localhost corosync[13918]: [pcmk ] info: pcmk_startup: Maximum core file size is: 4294967295
Oct 19 20:40:33 localhost corosync[13918]: [pcmk ] info: pcmk_startup: Service: 9
Oct 19 20:40:33 localhost corosync[13918]: [pcmk ] info: pcmk_startup: Local hostname: node1.a.com
[root@node1 corosync]#
在node2上同样要进行将前面的验证步骤
[root@node2 corosync]# grep -i -e "corosync cluster engine" -e "configuration file" /var/log/messages
Sep 18 01:52:10 localhost smartd[3123]: Opened configuration file /etc/smartd.conf
Sep 18 01:52:10 localhost smartd[3123]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Sep 18 02:02:24 localhost smartd[2991]: Opened configuration file /etc/smartd.conf
Sep 18 02:02:24 localhost smartd[2991]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Oct 18 18:30:10 localhost smartd[2990]: Opened configuration file /etc/smartd.conf
Oct 18 18:30:10 localhost smartd[2990]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Oct 18 18:36:17 localhost smartd[3074]: Opened configuration file /etc/smartd.conf
Oct 18 18:36:18 localhost smartd[3074]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Oct 19 20:32:11 localhost corosync[17180]: [MAIN ] Corosync Cluster Engine ('1.2.7'): started and ready to provide service.
Oct 19 20:32:11 localhost corosync[17180]: [MAIN ] Successfully read main configuration file '/etc/corosync/corosync.conf'.
Oct 19 20:41:10 localhost corosync[17180]: [MAIN ] Corosync Cluster Engine exiting with status 0 at main.c:170.
Oct 19 20:41:10 localhost corosync[3045]: [MAIN ] Corosync Cluster Engine ('1.2.7'): started and ready to provide service.
Oct 19 20:41:10 localhost corosync[3045]: [MAIN ] Successfully read main configuration file '/etc/corosync/corosync.conf'.
[root@node2 corosync]# grep -i totem /var/log/messages
Oct 19 20:32:11 localhost corosync[17180]: [TOTEM ] Initializing transport (UDP/IP).
Oct 19 20:32:11 localhost corosync[17180]: [TOTEM ] Initializing transmit/receive security: libtomcrypt SOBER128/SHA1HMAC (mode 0).
Oct 19 20:32:11 localhost corosync[17180]: [TOTEM ] The network interface is down.
Oct 19 20:32:12 localhost corosync[17180]: [TOTEM ] Process pause detected for 1187 ms, flushing membership messages.
Oct 19 20:32:12 localhost corosync[17180]: [TOTEM ] A processor joined or left the membership and a new membership was formed.
Oct 19 20:41:10 localhost corosync[3045]: [TOTEM ] Initializing transport (UDP/IP).
Oct 19 20:41:10 localhost corosync[3045]: [TOTEM ] Initializing transmit/receive security: libtomcrypt SOBER128/SHA1HMAC (mode 0).
Oct 19 20:41:11 localhost corosync[3045]: [TOTEM ] The network interface [192.168.2.11] is now up.
Oct 19 20:41:12 localhost corosync[3045]: [TOTEM ] A processor joined or left the membership and a new membership was formed.
Oct 19 20:41:12 localhost corosync[3045]: [TOTEM ] A processor joined or left the membership and a new membership was formed.
[root@node2 corosync]# grep -i error: /var/log/messages
[root@node2 corosync]# grep -i pcmk_startup /var/log/messages
Oct 19 20:32:11 localhost corosync[17180]: [pcmk ] info: pcmk_startup: CRM: Initialized
Oct 19 20:32:11 localhost corosync[17180]: [pcmk ] Logging: Initialized pcmk_startup
Oct 19 20:32:11 localhost corosync[17180]: [pcmk ] info: pcmk_startup: Maximum core file size is: 4294967295
Oct 19 20:32:11 localhost corosync[17180]: [pcmk ] info: pcmk_startup: Service: 9
Oct 19 20:32:11 localhost corosync[17180]: [pcmk ] info: pcmk_startup: Local hostname: node2.a.com
Oct 19 20:41:11 localhost corosync[3045]: [pcmk ] info: pcmk_startup: CRM: Initialized
Oct 19 20:41:11 localhost corosync[3045]: [pcmk ] Logging: Initialized pcmk_startup
Oct 19 20:41:11 localhost corosync[3045]: [pcmk ] info: pcmk_startup: Maximum core file size is: 4294967295
Oct 19 20:41:11 localhost corosync[3045]: [pcmk ] info: pcmk_startup: Service: 9
Oct 19 20:41:11 localhost corosync[3045]: [pcmk ] info: pcmk_startup: Local hostname: node2.a.com
[root@node2 corosync]#
[root@node2 corosync]# grep -i -e "corosync cluster engine" -e "configuration file" /var/log/messages
Sep 18 01:52:10 localhost smartd[3123]: Opened configuration file /etc/smartd.conf
Sep 18 01:52:10 localhost smartd[3123]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Sep 18 02:02:24 localhost smartd[2991]: Opened configuration file /etc/smartd.conf
Sep 18 02:02:24 localhost smartd[2991]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Oct 18 18:30:10 localhost smartd[2990]: Opened configuration file /etc/smartd.conf
Oct 18 18:30:10 localhost smartd[2990]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Oct 18 18:36:17 localhost smartd[3074]: Opened configuration file /etc/smartd.conf
Oct 18 18:36:18 localhost smartd[3074]: Configuration file /etc/smartd.conf was parsed, found DEVICESCAN, scanning devices
Oct 19 20:32:11 localhost corosync[17180]: [MAIN ] Corosync Cluster Engine ('1.2.7'): started and ready to provide service.
Oct 19 20:32:11 localhost corosync[17180]: [MAIN ] Successfully read main configuration file '/etc/corosync/corosync.conf'.
Oct 19 20:41:10 localhost corosync[17180]: [MAIN ] Corosync Cluster Engine exiting with status 0 at main.c:170.
Oct 19 20:41:10 localhost corosync[3045]: [MAIN ] Corosync Cluster Engine ('1.2.7'): started and ready to provide service.
Oct 19 20:41:10 localhost corosync[3045]: [MAIN ] Successfully read main configuration file '/etc/corosync/corosync.conf'.
[root@node2 corosync]# grep -i totem /var/log/messages
Oct 19 20:32:11 localhost corosync[17180]: [TOTEM ] Initializing transport (UDP/IP).
Oct 19 20:32:11 localhost corosync[17180]: [TOTEM ] Initializing transmit/receive security: libtomcrypt SOBER128/SHA1HMAC (mode 0).
Oct 19 20:32:11 localhost corosync[17180]: [TOTEM ] The network interface is down.
Oct 19 20:32:12 localhost corosync[17180]: [TOTEM ] Process pause detected for 1187 ms, flushing membership messages.
Oct 19 20:32:12 localhost corosync[17180]: [TOTEM ] A processor joined or left the membership and a new membership was formed.
Oct 19 20:41:10 localhost corosync[3045]: [TOTEM ] Initializing transport (UDP/IP).
Oct 19 20:41:10 localhost corosync[3045]: [TOTEM ] Initializing transmit/receive security: libtomcrypt SOBER128/SHA1HMAC (mode 0).
Oct 19 20:41:11 localhost corosync[3045]: [TOTEM ] The network interface [192.168.2.11] is now up.
Oct 19 20:41:12 localhost corosync[3045]: [TOTEM ] A processor joined or left the membership and a new membership was formed.
Oct 19 20:41:12 localhost corosync[3045]: [TOTEM ] A processor joined or left the membership and a new membership was formed.
[root@node2 corosync]# grep -i error: /var/log/messages
[root@node2 corosync]# grep -i pcmk_startup /var/log/messages
Oct 19 20:32:11 localhost corosync[17180]: [pcmk ] info: pcmk_startup: CRM: Initialized
Oct 19 20:32:11 localhost corosync[17180]: [pcmk ] Logging: Initialized pcmk_startup
Oct 19 20:32:11 localhost corosync[17180]: [pcmk ] info: pcmk_startup: Maximum core file size is: 4294967295
Oct 19 20:32:11 localhost corosync[17180]: [pcmk ] info: pcmk_startup: Service: 9
Oct 19 20:32:11 localhost corosync[17180]: [pcmk ] info: pcmk_startup: Local hostname: node2.a.com
Oct 19 20:41:11 localhost corosync[3045]: [pcmk ] info: pcmk_startup: CRM: Initialized
Oct 19 20:41:11 localhost corosync[3045]: [pcmk ] Logging: Initialized pcmk_startup
Oct 19 20:41:11 localhost corosync[3045]: [pcmk ] info: pcmk_startup: Maximum core file size is: 4294967295
Oct 19 20:41:11 localhost corosync[3045]: [pcmk ] info: pcmk_startup: Service: 9
Oct 19 20:41:11 localhost corosync[3045]: [pcmk ] info: pcmk_startup: Local hostname: node2.a.com
[root@node2 corosync]#
在任何一个节点上 查看集群的成员状态
[root@node1 corosync]# crm status
如图：
[root@node1 corosync]# crm status
如图：
[root@node2 corosync]# crm status
如图：
提供高可用服务
在corosync中，定义服务可以用两种接口
1.图形接口 （使用hb—gui）
2.crm （pacemaker 提供,是一个shell）
例如：
[root@node1 corosync]# ssh node2.a.com 'date'
Fri Oct 19 21:01:16 CST 2012
[root@node1 corosync]#
在corosync中，定义服务可以用两种接口
1.图形接口 （使用hb—gui）
2.crm （pacemaker 提供,是一个shell）
例如：
[root@node1 corosync]# ssh node2.a.com 'date'
Fri Oct 19 21:01:16 CST 2012
[root@node1 corosync]#
[root@node2 corosync]# crm status
============
Last updated: Fri Oct 19 20:54:47 2012
Stack: openais
Current DC: node1.a.com - partition with quorum
Version: 1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f
2 Nodes configured, 2 expected votes
0 Resources configured.
============
============
Last updated: Fri Oct 19 20:54:47 2012
Stack: openais
Current DC: node1.a.com - partition with quorum
Version: 1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f
2 Nodes configured, 2 expected votes
0 Resources configured.
============
Online: [ node1.a.com node2.a.com ]
[root@node2 corosync]# crm
crm(live)# configure
crm(live)configure# show
node node1.a.com
node node2.a.com
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2"
crm(live)configure# exit
bye
如何验证该文件的语法错误
[root@node1 corosync]# crm_verify -L
crm_verify[2532]: 2012/10/19_21:03:12 ERROR: unpack_resources: Resource start-up disabled since no STONITH resources have been defined
crm_verify[2532]: 2012/10/19_21:03:12 ERROR: unpack_resources: Either configure some or disable STONITH with the stonith-enabled option
crm_verify[2532]: 2012/10/19_21:03:12 ERROR: unpack_resources: NOTE: Clusters with shared data need STONITH to ensure data integrity
Errors found during check: config not valid
-V may provide more details
可以看到有stonith错误，在高可用的环境里面，会禁止实用任何资源
可以禁用stonith
[root@node1 corosync]# crm
crm(live)# configure
crm(live)configure# property stonith-enabled=false
crm(live)configure# commit
crm(live)configure# show
node node1.a.com
node node2.a.com
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false"
crm(live)configure# exit
bye
crm(live)# configure
crm(live)configure# show
node node1.a.com
node node2.a.com
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2"
crm(live)configure# exit
bye
如何验证该文件的语法错误
[root@node1 corosync]# crm_verify -L
crm_verify[2532]: 2012/10/19_21:03:12 ERROR: unpack_resources: Resource start-up disabled since no STONITH resources have been defined
crm_verify[2532]: 2012/10/19_21:03:12 ERROR: unpack_resources: Either configure some or disable STONITH with the stonith-enabled option
crm_verify[2532]: 2012/10/19_21:03:12 ERROR: unpack_resources: NOTE: Clusters with shared data need STONITH to ensure data integrity
Errors found during check: config not valid
-V may provide more details
可以看到有stonith错误，在高可用的环境里面，会禁止实用任何资源
可以禁用stonith
[root@node1 corosync]# crm
crm(live)# configure
crm(live)configure# property stonith-enabled=false
crm(live)configure# commit
crm(live)configure# show
node node1.a.com
node node2.a.com
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false"
crm(live)configure# exit
bye
[root@node2 corosync]# crm
crm(live)# configure
crm(live)configure# property stonith-enabled=false
crm(live)configure# commit
crm(live)configure# show
node node1.a.com
node node2.a.com
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false"
crm(live)configure# bye
bye
再次进行检查
[root@node1 corosync]# crm_verify -L
[root@node1 corosync]# crm_verify -L
可以看到没有错误了
显示stonith所指示的类型
[root@node1 corosync]# stonith -L
crm(live)# configure
crm(live)configure# property stonith-enabled=false
crm(live)configure# commit
crm(live)configure# show
node node1.a.com
node node2.a.com
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false"
crm(live)configure# bye
bye
再次进行检查
[root@node1 corosync]# crm_verify -L
[root@node1 corosync]# crm_verify -L
可以看到没有错误了
显示stonith所指示的类型
[root@node1 corosync]# stonith -L
集群的资源类型有4种
primitive 本地主资源 （只能运行在一个节点上）
group 把多个资源轨道一个组里面，便于管理
clone 需要在多个节点上同时启用的 （如ocfs2 ，stonith ，没有主次之分）
master 有主次之分，如drbd
查看资源代理类型
[root@node1 corosync]# crm
crm(live)# configure
crm(live)configure# ra
crm(live)configure ra# list
usage: list []
crm(live)configure ra# classes
heartbeat
lsb
ocf / heartbeat pacemaker
stonith
比如查看lsb
crm(live)configure ra# list lsb
如图：
primitive 本地主资源 （只能运行在一个节点上）
group 把多个资源轨道一个组里面，便于管理
clone 需要在多个节点上同时启用的 （如ocfs2 ，stonith ，没有主次之分）
master 有主次之分，如drbd
查看资源代理类型
[root@node1 corosync]# crm
crm(live)# configure
crm(live)configure# ra
crm(live)configure ra# list
usage: list
crm(live)configure ra# classes
heartbeat
lsb
ocf / heartbeat pacemaker
stonith
比如查看lsb
crm(live)configure ra# list lsb
如图：
举例：
查看ocf的heartbeat
crm(live)configure ra# list ocf heartbeat
crm(live)configure ra# meta ocf:heartbeat:IPaddr
查看ocf的heartbeat
crm(live)configure ra# list ocf heartbeat
crm(live)configure ra# meta ocf:heartbeat:IPaddr
配置一个资源，可以在configuration 下面进行配置
1.先资源名字
[root@node1 corosync]# crm
crm(live)# configure
crm(live)configure# primitive webIP ocf:heartbeat:IPaddr params ip=192.168.2.20
crm(live)configure# show
node node1.a.com
node node2.a.com
primitive webIP ocf:heartbeat:IPaddr \
params ip="192.168.2.20"
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false"
crm(live)configure# commit
安装apache服务
[root@node1 corosync]# yum install httpd -y
[root@node1 corosync]# echo "node1.a.com" >/var/www/html/index.html
[root@node2 corosync]# yum install httpd -y
[root@node2 corosync]# echo "node2.a.com" >/var/www/html/index.html
查看状态，可以看到资源在node1上启动
[root@node1 corosync]# crm
crm(live)# status
============
Last updated: Fri Oct 19 21:32:25 2012
Stack: openais
Current DC: node1.a.com - partition with quorum
Version: 1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
1.先资源名字
[root@node1 corosync]# crm
crm(live)# configure
crm(live)configure# primitive webIP ocf:heartbeat:IPaddr params ip=192.168.2.20
crm(live)configure# show
node node1.a.com
node node2.a.com
primitive webIP ocf:heartbeat:IPaddr \
params ip="192.168.2.20"
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false"
crm(live)configure# commit
安装apache服务
[root@node1 corosync]# yum install httpd -y
[root@node1 corosync]# echo "node1.a.com" >/var/www/html/index.html
[root@node2 corosync]# yum install httpd -y
[root@node2 corosync]# echo "node2.a.com" >/var/www/html/index.html
查看状态，可以看到资源在node1上启动
[root@node1 corosync]# crm
crm(live)# status
============
Last updated: Fri Oct 19 21:32:25 2012
Stack: openais
Current DC: node1.a.com - partition with quorum
Version: 1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
Online: [ node1.a.com node2.a.com ]
webIP (ocf::heartbeat:IPaddr): Started node1.a.com
crm(live)#
使用ifconfig 在节点1上进行查看，如下图：
crm(live)#
使用ifconfig 在节点1上进行查看，如下图：
定义web服务资源
[root@node1 corosync]# crm
crm(live)# ra
crm(live)ra# meta lsb:httpd
lsb:httpd
[root@node1 corosync]# crm
crm(live)# ra
crm(live)ra# meta lsb:httpd
lsb:httpd
Apache is a World Wide Web server. It is used to serve \
HTML files and CGI.
HTML files and CGI.
Operations' defaults (advisory minimum):
start timeout=15
stop timeout=15
status timeout=15
restart timeout=15
force-reload timeout=15
monitor interval=15 timeout=15 start-delay=15
crm(live)ra# end
crm(live)# configure
crm(live)configure# primitive webserver lsb:httpd
crm(live)configure# commit
crm(live)configure# show
node node1.a.com
node node2.a.com
primitive webIP ocf:heartbeat:IPaddr \
params ip="192.168.2.20"
primitive webserver lsb:httpd
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false"
crm(live)configure#
crm(live)configure# end
crm(live)# status
============
Last updated: Fri Oct 19 21:38:00 2012
Stack: openais
Current DC: node1.a.com - partition with quorum
Version: 1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f
2 Nodes configured, 2 expected votes
2 Resources configured.
============
stop timeout=15
status timeout=15
restart timeout=15
force-reload timeout=15
monitor interval=15 timeout=15 start-delay=15
crm(live)ra# end
crm(live)# configure
crm(live)configure# primitive webserver lsb:httpd
crm(live)configure# commit
crm(live)configure# show
node node1.a.com
node node2.a.com
primitive webIP ocf:heartbeat:IPaddr \
params ip="192.168.2.20"
primitive webserver lsb:httpd
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false"
crm(live)configure#
crm(live)configure# end
crm(live)# status
============
Last updated: Fri Oct 19 21:38:00 2012
Stack: openais
Current DC: node1.a.com - partition with quorum
Version: 1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f
2 Nodes configured, 2 expected votes
2 Resources configured.
============
Online: [ node1.a.com node2.a.com ]
webIP (ocf::heartbeat:IPaddr): Started node1.a.com
webserver (lsb:httpd): Started node2.a.com
在node1，node2上查看http服务状态
[root@node1 ~]# service httpd status
httpd is stopped
[root@node2 ~]# service httpd status
httpd (pid 3334) is running...
vip在node1上，而httpd服务在node2上启动，这显然不对，下面定义group
[root@node1 ~]# crm
crm(live)# configure
crm(live)configure# group web webIP webserver
crm(live)configure# show
node node1.a.com
node node2.a.com
primitive webIP ocf:heartbeat:IPaddr \
params ip="192.168.2.20"
primitive webserver lsb:httpd
group web webIP webserver
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false"
crm(live)configure# commit
crm(live)configure# end
查看状态
crm(live)# status
============
Last updated: Sat Oct 20 16:48:00 2012
Stack: openais
Current DC: node1.a.com - partition with quorum
Version: 1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
webserver (lsb:httpd): Started node2.a.com
在node1，node2上查看http服务状态
[root@node1 ~]# service httpd status
httpd is stopped
[root@node2 ~]# service httpd status
httpd (pid 3334) is running...
vip在node1上，而httpd服务在node2上启动，这显然不对，下面定义group
[root@node1 ~]# crm
crm(live)# configure
crm(live)configure# group web webIP webserver
crm(live)configure# show
node node1.a.com
node node2.a.com
primitive webIP ocf:heartbeat:IPaddr \
params ip="192.168.2.20"
primitive webserver lsb:httpd
group web webIP webserver
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false"
crm(live)configure# commit
crm(live)configure# end
查看状态
crm(live)# status
============
Last updated: Sat Oct 20 16:48:00 2012
Stack: openais
Current DC: node1.a.com - partition with quorum
Version: 1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
Online: [ node1.a.com node2.a.com ]
Resource Group: web
webIP (ocf::heartbeat:IPaddr): Started node1.a.com
webserver (lsb:httpd): Started node1.a.com
crm(live)#
这次结果对了
用个client测试：
如图：
webIP (ocf::heartbeat:IPaddr): Started node1.a.com
webserver (lsb:httpd): Started node1.a.com
crm(live)#
这次结果对了
用个client测试：
如图：
在node1把corosync停用
[root@node1 ~]# service corosync stop
Signaling Corosync Cluster Engine (corosync) to terminate: [ OK ]
Waiting for corosync services to unload:........ [ OK ]
在node1，node2上查看状态
[root@node1 ~]# crm status
Connection to cluster failed: connection failed
[root@node2 ~]# crm status
============
Last updated: Sat Oct 20 16:52:52 2012
Stack: openais
Current DC: node2.a.com - partition WITHOUT quorum
Version: 1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
[root@node2 ~]# crm status
============
Last updated: Sat Oct 20 16:52:52 2012
Stack: openais
Current DC: node2.a.com - partition WITHOUT quorum
Version: 1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
Online: [ node2.a.com ]
OFFLINE: [ node1.a.com ]
可以看到没有票数
关闭 quorum
可选的参数有如下
ignore （忽略）
freeze （冻结，表示已经启用的资源继续实用，没有启用的资源不能启用）
stop（默认）
suicide （所有的资源杀掉）
下面将节点1 的corosync 服务启动起来改变quorum
[root@node1 ~]# service corosync start
Starting Corosync Cluster Engine (corosync): [ OK ]
[root@node1 ~]# crm
crm(live)# configure
crm(live)configure# property no-quorum-policy=ignore
crm(live)configure# commit
crm(live)configure# show
node node1.a.com
node node2.a.com
primitive webIP ocf:heartbeat:IPaddr \
params ip="192.168.2.20"
primitive webserver lsb:httpd
group web webIP webserver
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false" \
no-quorum-policy="ignore"
crm(live)configure# end
crm(live)# bye
bye
[root@node1 ~]# service corosync stop
Signaling Corosync Cluster Engine (corosync) to terminate: [ OK ]
Waiting for corosync services to unload:...... [ OK ]
在node2上查看状态
[root@node2 ~]# crm status
============
Last updated: Sat Oct 20 17:02:25 2012
Stack: openais
Current DC: node2.a.com - partition WITHOUT quorum
Version: 1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
OFFLINE: [ node1.a.com ]
可以看到没有票数
关闭 quorum
可选的参数有如下
ignore （忽略）
freeze （冻结，表示已经启用的资源继续实用，没有启用的资源不能启用）
stop（默认）
suicide （所有的资源杀掉）
下面将节点1 的corosync 服务启动起来改变quorum
[root@node1 ~]# service corosync start
Starting Corosync Cluster Engine (corosync): [ OK ]
[root@node1 ~]# crm
crm(live)# configure
crm(live)configure# property no-quorum-policy=ignore
crm(live)configure# commit
crm(live)configure# show
node node1.a.com
node node2.a.com
primitive webIP ocf:heartbeat:IPaddr \
params ip="192.168.2.20"
primitive webserver lsb:httpd
group web webIP webserver
property $id="cib-bootstrap-options" \
dc-version="1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f" \
cluster-infrastructure="openais" \
expected-quorum-votes="2" \
stonith-enabled="false" \
no-quorum-policy="ignore"
crm(live)configure# end
crm(live)# bye
bye
[root@node1 ~]# service corosync stop
Signaling Corosync Cluster Engine (corosync) to terminate: [ OK ]
Waiting for corosync services to unload:...... [ OK ]
在node2上查看状态
[root@node2 ~]# crm status
============
Last updated: Sat Oct 20 17:02:25 2012
Stack: openais
Current DC: node2.a.com - partition WITHOUT quorum
Version: 1.1.5-1.1.el5-01e86afaaa6d4a8c4836f68df80ababd6ca3902f
2 Nodes configured, 2 expected votes
1 Resources configured.
============
Online: [ node2.a.com ]
OFFLINE: [ node1.a.com ]
OFFLINE: [ node1.a.com ]
Resource Group: web
webIP (ocf::heartbeat:IPaddr): Started node2.a.com
webserver (lsb:httpd): Started node2.a.com
[root@node2 ~]#
显然，这是我们想要的结果
测试：
如图：
webIP (ocf::heartbeat:IPaddr): Started node2.a.com
webserver (lsb:httpd): Started node2.a.com
[root@node2 ~]#
显然，这是我们想要的结果
测试：
如图：
文章最后附录本次实验所需的rpm安装包及整理的文档，由于大小限制，分两部分上传的。