drbd + pacemaker

# yum -y install corosync pacemaker   
# yum -y install crmsh-1.2.6-4.el6.x86_64.rpm  pssh-2.3.1-2.el6.x86_64.rpm 
# umount /mnt/
# service drbd stop
# chkconfig  drbd off
2、配置corosync，（以下命令在node1.magedu.com上执行）

# cd /etc/corosync
# cp corosync.conf.example corosync.conf

接着编辑corosync.conf，添加如下内容：
service {
  ver:  0
  name: pacemaker
  # use_mgmtd: yes
}

aisexec {
  user: root
  group:  root
}

[root@node4 corosync]# mv /dev/random  /dev/h
[root@node4 corosync]# ln /dev/urandom  /dev/random
[root@node4 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.
[root@node4 corosync]# rm -rf /dev/random 
[root@node4 corosync]# mv /dev/h /dev/random

[root@node4 corosync]# service corosync start


[root@node4 corosync]# crm
crm(live)# configure  
pcrm(live)configure# property  stonith-enabled=false
crm(live)configure# property  no-quorum-policy=ignore
crm(live)configure# rsc_defaults  resource-stickiness=100
crm(live)configure# verify 
crm(live)configure# commit 
crm(live)configure# cd 
crm(live)# configure 

1、查看当前集群的配置信息，确保已经配置全局属性参数为两节点集群所适用：
crm(live)configure# show 
node node3.nginx.fx
node node4.mysql.com
property $id="cib-bootstrap-options"     dc-version="1.1.10-14.el6_5.3-368c726"     cluster-infrastructure="classic openais (with plugin)"     expected-quorum-votes="2"     stonith-enabled="false"     no-quorum-policy="ignore"
rsc_defaults $id="rsc-options"     resource-stickiness="100"




crm(live)configure# primitive  mysqlstore ocf:linbit:drbd  params  drbd_resource=mystore op monitor  role=Master interval=30s timeout=20s op monitor  role=Slave interval=60s timeout=20s op sta
rt  timeout=240s op stop  timeout=100s
crm(live)configure# verify 
crm(live)configure# master  ms_mysqlstore mysqlstore  meta master-max=1 master-node-max=1 clone-max=2 clone-node-max=1 notify="True"
crm(live)configure# verify 
crm(live)configure# commit 
crm(live)configure# show 
node node3.nginx.fx
node node4.mysql.com
primitive mysqlstore ocf:linbit:drbd     params drbd_resource="mystore"     op monitor role="Master" interval="30s" timeout="20s"     op monitor role="Slave" interval="60s" timeout="20s"     op start timeout="240s" interval="0"     op stop timeout="100s" interval="0"
ms ms_mysqlstore mysqlstore     meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="True"
property $id="cib-bootstrap-options"     dc-version="1.1.10-14.el6_5.3-368c726"     cluster-infrastructure="classic openais (with plugin)"     expected-quorum-votes="2"     stonith-enabled="false"     no-quorum-policy="ignore"
rsc_defaults $id="rsc-options"     resource-stickiness="100"




crm(live)configure# cd
crm(live)# status 
Last updated: Sun Apr 27 06:11:37 2014
Last change: Sun Apr 27 06:09:29 2014 via cibadmin on node4.mysql.com
Stack: classic openais (with plugin)
Current DC: node4.mysql.com - partition with quorum
Version: 1.1.10-14.el6_5.3-368c726
2 Nodes configured, 2 expected votes
2 Resources configured


Online: [ node3.nginx.fx node4.mysql.com ]

 Master/Slave Set: ms_mysqlstore [mysqlstore]
     Masters: [ node4.mysql.com ]
     Slaves: [ node3.nginx.fx ]


crm(live)# node  
crm(live)node# standby node4.mysql.com 
crm(live)node# cd 
crm(live)# status 
Last updated: Sun Apr 27 06:14:18 2014
Last change: Sun Apr 27 06:14:12 2014 via crm_attribute on node4.mysql.com
Stack: classic openais (with plugin)
Current DC: node4.mysql.com - partition with quorum
Version: 1.1.10-14.el6_5.3-368c726
2 Nodes configured, 2 expected votes
2 Resources configured


Node node4.mysql.com: standby
Online: [ node3.nginx.fx ]

 Master/Slave Set: ms_mysqlstore [mysqlstore]
     Masters: [ node3.nginx.fx ]
     Stopped: [ node4.mysql.com ]
crm(live)# node  online  node4.mysql.com 
crm(live)# status 
Last updated: Sun Apr 27 06:14:46 2014
Last change: Sun Apr 27 06:14:42 2014 via crm_attribute on node4.mysql.com
Stack: classic openais (with plugin)
Current DC: node4.mysql.com - partition with quorum
Version: 1.1.10-14.el6_5.3-368c726
2 Nodes configured, 2 expected votes
2 Resources configured


Online: [ node3.nginx.fx node4.mysql.com ]

 Master/Slave Set: ms_mysqlstore [mysqlstore]
     Masters: [ node3.nginx.fx ]
     Slaves: [ node4.mysql.com ]




crm(live)# configure  show
node node3.nginx.fx
node node4.mysql.com     attributes standby="off"
primitive mysqlstore ocf:linbit:drbd     params drbd_resource="mystore"     op monitor role="Master" interval="30s" timeout="20s"     op monitor role="Slave" interval="60s" timeout="20s"     op start timeout="240s" interval="0"     op stop timeout="100s" interval="0"
ms ms_mysqlstore mysqlstore     meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="True"
property $id="cib-bootstrap-options"     dc-version="1.1.10-14.el6_5.3-368c726"     cluster-infrastructure="classic openais (with plugin)"     expected-quorum-votes="2"     stonith-enabled="false"     no-quorum-policy="ignore"
rsc_defaults $id="rsc-options"     resource-stickiness="100"

Online: [ node3.nginx.fx node4.mysql.com ]

 Master/Slave Set: ms_mysqlstore [mysqlstore]
     Masters: [ node3.nginx.fx ]
     Slaves: [ node4.mysql.com ]


[root@node3 ~]# service drbd status
drbd driver loaded OK; device status:
version: 8.4.3 (api:1/proto:86-101)
GIT-hash: 89a294209144b68adb3ee85a73221f964d3ee515 build by gardner@, 2013-11-29 12:28:00
m:res      cs         ro                 ds                 p  mounted  fstype
0:mystore  Connected  Primary/Secondary  UpToDate/UpToDate  C

[root@node4 ~]# service drbd status
drbd driver loaded OK; device status:
version: 8.4.3 (api:1/proto:86-101)
GIT-hash: 89a294209144b68adb3ee85a73221f964d3ee515 build by gardner@, 2013-11-29 12:28:00
m:res      cs         ro                 ds                 p  mounted  fstype
0:mystore  Connected  Secondary/Primary  UpToDate/UpToDate  C

1、查看当前集群的配置信息，确保已经配置全局属性参数为两节点集群所适用：

# crm configure show
node node1.a.org
node node2.a.org
property $id="cib-bootstrap-options"  dc-version="1.0.11-1554a83db0d3c3e546cfd3aaff6af1184f79ee87"  cluster-infrastructure="openais"  expected-quorum-votes="2"  stonith-enabled="false"  last-lrm-refresh="1308059765"  no-quorum-policy="ignore"




在如上输出的信息中，请确保有stonith-enabled和no-quorum-policy出现且其值与如上输出信息中相同。否则，可以分别使用如下命令进行配置：
# crm configure property stonith-enabled=false
# crm configure property no-quorum-policy=ignore

2、将已经配置好的drbd设备/dev/drbd0定义为集群服务；

1）按照集群服务的要求，首先确保两个节点上的drbd服务已经停止，且不会随系统启动而自动启动：

# drbd-overview
 0:web Unconfigured . . . . 

# chkconfig drbd off 

2）配置drbd为集群资源：

提供drbd的RA目前由OCF归类为linbit，其路径为/usr/lib/ocf/resource.d/linbit/drbd。我们可以使用如下命令来查看此RA及RA的meta信息：

# crm ra classes
heartbeat
lsb
ocf / heartbeat linbit pacemaker
stonith

# crm ra list ocf linbit
drbd 

# crm ra info ocf:linbit:drbd
This resource agent manages a DRBD resource
as a master/slave resource. DRBD is a shared-nothing replicated storage
device. (ocf:linbit:drbd)

Master/Slave OCF Resource Agent for DRBD

Parameters (* denotes required, [] the default):

drbd_resource* (string): drbd resource name
 The name of the drbd resource from the drbd.conf file.

drbdconf (string, [/etc/drbd.conf]): Path to drbd.conf
 Full path to the drbd.conf file.

Operations‘ defaults (advisory minimum):

 start timeout=240
 promote timeout=90
 demote timeout=90
 notify timeout=90
 stop timeout=100
 monitor_Slave interval=20 timeout=20 start-delay=1m
 monitor_Master interval=10 timeout=20 start-delay=1m


drbd需要同时运行在两个节点上，但只能有一个节点（primary/secondary模型）是Master，而另一个节点为Slave；因此，它是一种比较特殊的集群资源，其资源类型为多态（Multi-state）clone类型，即主机节点有Master和Slave之分，且要求服务刚启动时两个节点都处于slave状态。

[root@node1 ~]# crm
crm(live)# configure
crm(live)configure# primitive webdrbd ocf:linbit:drbd params drbd_resource=web op monitor role=Master interval=50s timeout=30s op monitor role=Slave interval=60s timeout=30s
crm(live)configure# master MS_Webdrbd webdrbd meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true"

crm(live)configure# show webdrbd
primitive webdrbd ocf:linbit:drbd  params drbd_resource="web"  op monitor interval="15s"
crm(live)configure# show MS_Webdrbd
ms MS_Webdrbd webdrbd  meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true"
crm(live)configure# verify
crm(live)configure# commit


查看当前集群运行状态：
# crm status
============
Last updated: Fri Jun 17 06:24:03 2011
Stack: openais
Current DC: node2.a.org - partition with quorum
Version: 1.0.11-1554a83db0d3c3e546cfd3aaff6af1184f79ee87
2 Nodes configured, 2 expected votes
1 Resources configured.
============

Online: [ node2.a.org node1.a.org ]

 Master/Slave Set: MS_Webdrbd
 Masters: [ node2.a.org ]
 Slaves: [ node1.a.org ]

由上面的信息可以看出此时的drbd服务的Primary节点为node2.a.org，Secondary节点为node1.a.org。当然，也可以在node2上使用如下命令验正当前主机是否已经成为web资源的Primary节点：
# drbdadm role web
Primary/Secondary

3）为Primary节点上的web资源创建自动挂载的集群服务

MS_Webdrbd的Master节点即为drbd服务web资源的Primary节点，此节点的设备/dev/drbd0可以挂载使用，且在某集群服务的应用当中也需要能够实现自动挂载。假设我们这里的web资源是为Web服务器集群提供网页文件的共享文件系统，其需要挂载至/www（此目录需要在两个节点都已经建立完成）目录。

此外，此自动挂载的集群资源需要运行于drbd服务的Master节点上，并且只能在drbd服务将某节点设置为Primary以后方可启动。因此，还需要为这两个资源建立排列约束和顺序约束。

# crm
crm(live)# configure
crm(live)configure# primitive WebFS ocf:heartbeat:Filesystem params device="/dev/drbd0" directory="/www" fstype="ext3"
crm(live)configure# colocation WebFS_on_MS_webdrbd inf: WebFS MS_Webdrbd:Master
crm(live)configure# order WebFS_after_MS_Webdrbd inf: MS_Webdrbd:promote WebFS:start
crm(live)configure# verify
crm(live)configure# commit

查看集群中资源的运行状态：
 crm status
============
Last updated: Fri Jun 17 06:26:03 2011
Stack: openais
Current DC: node2.a.org - partition with quorum
Version: 1.0.11-1554a83db0d3c3e546cfd3aaff6af1184f79ee87
2 Nodes configured, 2 expected votes
2 Resources configured.
============

Online: [ node2.a.org node1.a.org ]

 Master/Slave Set: MS_Webdrbd
 Masters: [ node2.a.org ]
 Slaves: [ node1.a.org ]
 WebFS (ocf::heartbeat:Filesystem): Started node2.a.org

由上面的信息可以发现，此时WebFS运行的节点和drbd服务的Primary节点均为node2.a.org；我们在node2上复制一些文件至/www目录（挂载点），而后在故障故障转移后查看node1的/www目录下是否存在这些文件。
# cp /etc/rc./rc.sysinit /www

下面我们模拟node2节点故障，看此些资源可否正确转移至node1。

以下命令在Node2上执行：
# crm node standby
# crm status
============
Last updated: Fri Jun 17 06:27:03 2011
Stack: openais
Current DC: node2.a.org - partition with quorum
Version: 1.0.11-1554a83db0d3c3e546cfd3aaff6af1184f79ee87
2 Nodes configured, 2 expected votes
2 Resources configured.
============

Node node2.a.org: standby
Online: [ node1.a.org ]

 Master/Slave Set: MS_Webdrbd
 Masters: [ node1.a.org ]
 Stopped: [ webdrbd:0 ]
 WebFS (ocf::heartbeat:Filesystem): Started node1.a.org

由上面的信息可以推断出，node2已经转入standby模式，其drbd服务已经停止，但故障转移已经完成，所有资源已经正常转移至node1。

在node1可以看到在node2作为primary节点时产生的保存至/www目录中的数据，在node1上均存在一份拷贝。

让node2重新上线：
# crm node online
[root@node2 ~]# crm status
============
Last updated: Fri Jun 17 06:30:05 2011
Stack: openais
Current DC: node2.a.org - partition with quorum
Version: 1.0.11-1554a83db0d3c3e546cfd3aaff6af1184f79ee87
2 Nodes configured, 2 expected votes
2 Resources configured.
============

Online: [ node2.a.org node1.a.org ]

 Master/Slave Set: MS_Webdrbd
 Masters: [ node1.a.org ]
 Slaves: [ node2.a.org ]
 WebFS (ocf::heartbeat:Filesystem): Started node1.a.org
 
 
 
 
 
 
mysql+drbd+corosync
 
 
node node1.magedu.com
node node2.magedu.com
primitive mysqldrbd ocf:linbit:drbd     params drbd_resource="mysqlres"     op monitor interval="30s" role="Master" timeout="30s"     op monitor interval="40s" role="Slave" timeout="30s"     op start interval="0" timeout="240"     op stop interval="0" timeout="100"
primitive mysqlfs ocf:heartbeat:Filesystem     params device="/dev/drbd0" directory="/data/mydata" fstype="ext3"     op start interval="0" timeout="60s"     op stop interval="0" timeout="60s"
primitive mysqlserver lsb:mysqld
primitive mysqlvip ocf:heartbeat:IPaddr     params ip="172.16.100.1"
ms ms_mysqldrbd mysqldrbd     meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true"
colocation mysqlfs_with_ms_mysqldrbd inf: mysqlfs ms_mysqldrbd:Master
colocation mysqlserver_with_mysqlfs inf: mysqlfs mysqlserver
colocation mysqlvip_with_mysqlserver inf: mysqlvip mysqlserver
order mysqlfs_after_ms_mysqldrbd inf: ms_mysqldrbd:promote mysqlfs:start
order mysqlserver_after_mysqlfs inf: mysqlfs mysqlserver
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"


版本2：
crm(live)# configure 
crm(live)configure# SHOW
node node1.magedu.com     attributes standby="off"
node node2.magedu.com     attributes standby="off"
primitive myip ocf:heartbeat:IPaddr     params ip="172.16.100.1" nic="eth0" cidr_netmask="255.255.0.0"
primitive mysqld lsb:mysqld
primitive mysqldrbd ocf:heartbeat:drbd     params drbd_resource="mydrbd"     op start interval="0" timeout="240"     op stop interval="0" timeout="100"     op monitor interval="20" role="Master" timeout="30"     op monitor interval="30" role="Slave" timeout="30"
primitive mystore ocf:heartbeat:Filesystem     params device="/dev/drbd0" directory="/mydata" fstype="ext3"     op start interval="0" timeout="60"     op stop interval="0" timeout="60"
ms ms_mysqldrbd mysqldrbd     meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true"
colocation myip_with_ms_mysqldrbd inf: ms_mysqldrbd:Master myip
colocation mysqld_with_mystore inf: mysqld mystore
colocation mystore_with_ms_mysqldrbd inf: mystore ms_mysqldrbd:Master
order mysqld_after_mystore inf: mystore mysqld
order mystore_after_ms_mysqldrbd inf: ms_mysqldrbd:promote mystore:start
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"     last-lrm-refresh="1368438416"
rsc_defaults $id="rsc-options"     resource-stickiness="100"


版本3(第11期用)
[root@node1 ~]# crm configure show
node node1.magedu.com     attributes standby="off"
node node2.magedu.com     attributes standby="off"
primitive myip ocf:heartbeat:IPaddr     params ip="172.16.100.101"     op monitor interval="20" timeout="20" on-fail="restart"
primitive myserver lsb:mysqld     op monitor interval="20" timeout="20" on-fail="restart"
primitive mysql_drbd ocf:linbit:drbd     params drbd_resource="mydata"     op monitor role="Master" interval="10" timeout="20"     op monitor role="Slave" interval="20" timeout="20"     op start timeout="240" interval="0"     op stop timeout="100" interval="0"
primitive mystore ocf:heartbeat:Filesystem     params device="/dev/drbd0" directory="/mydata" fstype="ext4"     op monitor interval="40" timeout="40"     op start timeout="60" interval="0"     op stop timeout="60" interval="0"
ms ms_mysql_drbd mysql_drbd     meta master-max="1" master-node-max="1" clone-max="2" clone-node-max="1" notify="true"
colocation myip_with_myserver inf: myip myserver
colocation myserver_with_mystore inf: myserver mystore
colocation mystore_with_ms_mysql_drbd_master inf: mystore ms_mysql_drbd:Master
order ms_mysql_drbd_before_mystore inf: ms_mysql_drbd:promote mystore:start
order myip_before_myserver inf: myip myserver
order mystore_before_myserver inf: mystore:start myserver:start
property $id="cib-bootstrap-options"     dc-version="1.1.8-7.el6-394e906"     cluster-infrastructure="classic openais (with plugin)"     expected-quorum-votes="2"     stonith-enabled="false"     last-lrm-refresh="1379316850"     no-quorum-policy="ignore"




    
    
    
使用双主模型：

一、设定资源启用双主模型
resource <resource> {
  startup {
    become-primary-on both;
    ...
  }
  net {
    allow-two-primaries yes;
    after-sb-0pri discard-zero-changes;
    after-sb-1pri discard-secondary;
    after-sb-2pri disconnect;
    ...
  }
  ...
}

同时，包括双主drbd模型中的任何集群文件系统都需要fencing功能，且要求其不仅要在资源级别实现，也要在节点级别实现STONITH功能。

disk {
        fencing resource-and-stonith;
}
handlers {
        outdate-peer "/sbin/make-sure-the-other-node-is-confirmed-dead.sh"
}



二、使用GFS2文件系统




三、结合RHCS时的资源定义示例
<rm>
  <resources />
  <service autostart="1" name="mysql">
    <drbd name="drbd-mysql" resource="mydrbd">
      <fs device="/dev/drbd0"
          mountpoint="/var/lib/mysql"
          fstype="ext3"
          name="mydrbd"
          options="noatime"/>
    </drbd>
    <ip address="172.16.100.8" monitor_link="1"/>
    <mysql config_file="/etc/my.cnf"
           listen_address="172.16.100.8"
           name="mysqld"/>
  </service>
</rm>



多节点同时启动一个IP
node node1.magedu.com     attributes standby="off"
node node2.magedu.com
node node3.magedu.com     attributes standby="off"
primitive DLM ocf:pacemaker:controld     params daemon="/usr/sbin/dlm_controld"     op start interval="0" timeout="90"     op stop interval="0" timeout="100"
primitive clusterip ocf:heartbeat:IPaddr2     params ip="172.16.200.7" cidr_netmask="32" clusterip_hash="sourceip"
clone WebIP clusterip     meta globally-unique="true" clone-max="3" clone-node-max="3" target-role="Stopped"
clone dlm_clone DLM     meta clone-max="3" clone-node-max="1" target-role="Started"
property $id="cib-bootstrap-options"     dc-version="1.1.7-6.el6-148fccfd5985c5590cc601123c6c16e966b85d14"     cluster-infrastructure="openais"     expected-quorum-votes="3"     stonith-enabled="false"     last-lrm-refresh="1354024090"



 primitive mysql_drbd ocf:linbit:drbd params drbd_resource="mydata" op monitor role=Master interval=10 timeout=20 op monitor role=Slave interval=20 timeout=20 op start timeout=240 op stop timeout=100