heartbeat3.0.5+drbd8.4.4+nfs 构建高可用nfs环境

环境：

master
eth0 192.168.253.140
eth1 192.168.254.140
slave
eth0 192.168.253.141eth1 192.168.254.141--------------------------------------在master和savle安装配置步骤一样。1）安装DRBD

[root@master ~]# mkdir /soft
[root@master ~]# cd /soft
[root@master soft]# yum -y install gcc kernel-devel kernel-headers flex perl
[root@master soft]# tar fzvx drbd-8.4.4.tar.gz
[root@master soft]# cd drbd-8.4.4
[root@master drbd-8.4.4]# ./configure --prefix=/usr/local/drbd-8.4 --with-km
[root@master drbd-8.4.4]# make KDIR=/usr/src/kernels/2.6.32-358.el6.x86_64/
[root@master drbd-8.4.4]# make install
[root@master drbd-8.4.4# mkdir -p /usr/local/drbd-8.4/var/run/drbd
[root@master drbd-8.4.4]# cp /usr/local/drbd-8.4/etc/rc.d/init.d/drbd /etc/init.d/
[root@master drbd-8.4.4]# chkconfig --add drbd
[root@master drbd-8.4.4]# chkconfig drbd on
[root@master drbd-8.4.4]# cd drbd
[root@master drbd]# make clean
[root@master drbd]# make KDIR=/usr/src/kernels/2.6.32-358.el6.x86_64/
[root@master drbd]# cp drbd.ko /lib/modules/2.6.32-358.el6.x86_64/kernel/lib/
[root@master drbd]# depmod

2）配置DRBD

[root@master drbd]# cd /usr/local/drbd-8.4/etc/drbd.d/
[root@master drbd.d]# cp global_common.conf global_common.conf.bak
[root@master drbd.d]# vi global_common.conf
global {
usage-count no;
}

common {
handlers {
pri-on-incon-degr "/usr/lib/drbd/notify-pri-on-incon-degr.sh; /usr/lib/drbd/notify-emergency-reboot.sh; echo b > /proc/sysrq-trigger ; reboot -f";
pri-lost-after-sb "/usr/lib/drbd/notify-pri-lost-after-sb.sh; /usr/lib/drbd/notify-emergency-reboot.sh; echo b > /proc/sysrq-trigger ; reboot -f";
local-io-error "/usr/lib/drbd/notify-io-error.sh; /usr/lib/drbd/notify-emergency-shutdown.sh; echo o > /proc/sysrq-trigger ; halt -f";
fence-peer "/usr/lib/drbd/crm-fence-peer.sh";
split-brain "/usr/lib/drbd/notify-split-brain.sh root";
out-of-sync "/usr/lib/drbd/notify-out-of-sync.sh root";
}

startup {
wfc-timeout 30;
degr-wfc-timeout 30;
outdated-wfc-timeout 30;
}

disk {
resync-rate     30M;
on-io-error     detach;
fencing         resource-only;
}

net {
protocol C;
cram-hmac-alg   sha1;
shared-secret   "mysql-ha";
csums-alg       sha1;
verify-alg crc32c;
}
}
#创建r0资源
[root@master drbd.d]# vi r0.res
resource r0{
on master{
device          /dev/drbd0; #逻辑设备的路径
disk            /dev/sdb1;  #物理设备
address         192.168.254.140:7788;
meta-disk       internal;
}
on slave{
device          /dev/drbd0;
disk            /dev/sb1;
address         192.168.254.141:7788;
meta-disk       internal;
}
}

3）创建设置DRBD

#创建 drbd resource
[root@master drbd.d]# modprobe drbd
[root@master drbd.d]# drbdadm create-md r0
[root@master drbd.d]# drbdadm up r0
#设置Primary [在master节点操作]
[root@master drbd.d]# drbdadm primary --force r0
#创建DRBD文件系统 [在Mysql主节点的master上执行]
[root@master drbd.d]# mkfs.ext4 /dev/drbd0
[root@master drbd.d]# mount /dev/drbd0 /drbd

4）DRBD同步测试

#首先，在主服务器上先将设备卸载，同时将主服务器降为备用服务器：
[root@master drbd]# mkdir -p /drbd/mynode1
[root@master drbd]# cd /
[root@master /]# umount /dev/drbd0
[root@master /]# drbdadm secondary r0
#然后，登录备用服务器，将备用服务器升为主服务器，同时挂载drbd0设备到 /drbd目录：
[root@slave drbd]# drbdadm up r0
[root@slave drbd]# drbdadm primary r0
[root@slave drbd]# mount /dev/drbd0 /drbd/
[root@slave drbd]# cd /drbd/
[root@slave drbd]# ll
drwx------ 2 root root 16384 1月  29 10:15 lost+found
drwxr-xr-x 2 root root  4096 1月  29 10:16 mynode1

——安装heartbeat
1）添加用户和组

[root@master soft]# groupadd haclient
[root@master soft]# useradd -g haclient -M -s /sbin/nologin hacluster

2）安装依赖包

[root@master soft]# yum install libtool automake autoconf glib2-devel libxml2-devel bzip2-devel libtool-ltdl-devel libxslt-devel docbook* -y

3）安装glue

[root@master soft]# tar jfvx glue-1.0.9.tar.bz2
[root@master soft]# cd Reusable-Cluster-Components-glue--glue-1.0.9/
[root@master Reusable-Cluster-Components-glue--glue-1.0.9]# ./autogen.sh
[root@master Reusable-Cluster-Components-glue--glue-1.0.9]# ./configure LIBS='/lib64/libuuid.so.1'
[root@master Reusable-Cluster-Components-glue--glue-1.0.9]# make && mek install

4）安装agents

[root@master Reusable-Cluster-Components-glue--glue-1.0.9]# cd ..
[root@master soft]# tar zfvx ClusterLabs-resource-agents-v3.9.2-0-ge261943.tar.gz
[root@master soft]# cd ClusterLabs-resource-agents-b735277/
[root@master ClusterLabs-resource-agents-b735277]# ./autogen.sh
[root@master ClusterLabs-resource-agents-b735277]# ./configure LIBS='/lib64/libuuid.so.1'
[root@master ClusterLabs-resource-agents-b735277]# make && make install

5）安装heartbeat

[root@master soft]# tar jfvx heartbeat-3.0.5.tar.bz2
[root@master soft]# cd Heartbeat-3-0-7e3a82377fa8/
[root@master Heartbeat-3-0-7e3a82377fa8]# ./bootstrap
[root@master Heartbeat-3-0-7e3a82377fa8]# ./ConfigureMe configure LIBS='/lib64/libuuid.so.1'
[root@master Heartbeat-3-0-7e3a82377fa8]# make && mek install

6）配置heartbeat

[root@master Heartbeat-3-0-7e3a82377fa8]# cd doc
[root@master doc]# cp authkeys haresources ha.cf /etc/ha.d/
[root@master doc]# cp /usr/etc/ha.d/shellfuncs /etc/ha.d/
[root@master doc]# rm -rf /usr/etc/ha.d
[root@master doc]# vi /etc/ha.d/ha.cf
#开启日志
logfile /var/log/ha-log
#设置syslog()/logger 设备
logfacility local0
#心跳发送时间间隔/秒
keepalive 2
#15 秒没有收到主机心跳、确认主机故障
deadtime 15
#警告次数
warntime 5
#守护进程启动30 后启动服务资源
initdead 30
#监听端口
udpport 694
#另一个节点IP、通过检测来保证心跳的可用性
ucast eth0 192.168.1.11
ucast eth1 192.168.2.11
#两个节点的名字[uname -n 获取]
node master
node slave
#开启DPOD
respawn hacluster /usr/lib64/heartbeat/ipfail
respawn hacluster /usr/lib64/heartbeat/dopd
apiauth ipfail gid=haclient uid=hacluster
apiauth dopd gid=haclient uid=hacluster
[root@master doc]# vi /etc/ha.d/authkeys
auth 1
1 sha1 My_Passwd!
[root@master doc]# chmod 600 /etc/ha.d/authkeys
[root@master doc]# vi /etc/ha.d/haresources
master drbddisk::r0 Filesystem::/dev/drbd0::/raid10::ext4 nfs
IPaddr::192.168.254.200/24/eth1
[root@master doc]# cd /soft/drbd-8.4.4/scripts/
[root@master scripts]# cp drbddisk /etc/ha.d/resource.d/
[root@master scripts]# cp /etc/init.d/nfs /etc/ha.d/resource.d/
[root@master scripts]# cp /etc/init.d/rpcbind /etc/ha.d/resource.d/

7）启动shellfuncs

[root@master scripts]# chkconfig --add heartbeat
[root@master scripts]# chkconfig heartbeat on
[root@master scripts]# /etc/init.d/heartbeat start
#输入以下信息，说明启动成功
[root@master scripts]# ps -ef |grep heartbeat
root      7302     1  0 13:15 ?        00:00:05 heartbeat: master control process
root      7305  7302  0 13:15 ?        00:00:00 heartbeat: FIFO reader
root      7306  7302  0 13:15 ?        00:00:01 heartbeat: write: bcast eth0
root      7307  7302  0 13:15 ?        00:00:00 heartbeat: read: bcast eth0
root      7308  7302  0 13:15 ?        00:00:01 heartbeat: write: bcast eth1
root      7309  7302  0 13:15 ?        00:00:00 heartbeat: read: bcast eth1
root      7310  7302  0 13:15 ?        00:00:00 heartbeat: write: ucast eth0
root      7311  7302  0 13:15 ?        00:00:00 heartbeat: read: ucast eth0
root      7312  7302  0 13:15 ?        00:00:00 heartbeat: write: ucast eth1
root      7313  7302  0 13:15 ?        00:00:00 heartbeat: read: ucast eth1
root      7314  7302  0 13:16 ?        00:00:01 heartbeat: write: ping 192.168.254.141
root      7315  7302  0 13:16 ?        00:00:00 heartbeat: read: ping 192.168.254.141
500       7335  7302  0 13:16 ?        00:00:00 /usr/lib64/heartbeat/ipfail
500       7336  7302  0 13:16 ?        00:00:00 /usr/lib64/heartbeat/dopd
root      8311  7214  0 14:13 pts/0    00:00:00 grep heartbeat

——安装nfs
1）安装nfs

[root@master ~]# yum -y install nfs-utils rpcbind

2）配置nfs实例

[root@master ~]# vi /etc/exports
/drbd/mynode1 192.168.254.0/24(rw,no_root_squash,no_all_squash,sync)

3）启动nfs [不需要设置开机启动]

[root@master ~]# exportfs -r
[root@master ~]# service rpcbind restart
[root@master ~]# service nfs restart

——客户端挂载

[root@Client ~]# mount -t nfs 192.168.254.200:/drbd/mynode1 /nfs/

——测试heartbeat故障转移
1）在master停止heartbeat

[root@master ~]# /etc/init.d/heartbeat stop
Stopping High-Availability services: 已终止

2）在slave上面查看日志是否切换成功

[root@slave ~]# tail -f /var/log/ha-log
Jan 29 14:42:24 slave heartbeat: [7263]: info: Local status now set to: 'active'
Jan 29 14:42:24 slave heartbeat: [7263]: info: Starting child client "/usr/lib64/heartbeat/ipfail" (500,500)
Jan 29 14:42:24 slave heartbeat: [7263]: info: Starting child client "/usr/lib64/heartbeat/dopd" (500,500)
Jan 29 14:42:24 slave heartbeat: [7294]: info: Starting "/usr/lib64/heartbeat/dopd" as uid 500  gid 500 (pid 7294)
Jan 29 14:42:24 slave heartbeat: [7293]: info: Starting "/usr/lib64/heartbeat/ipfail" as uid 500  gid 500 (pid 7293)
Jan 29 14:42:25 slave heartbeat: [7263]: info: remote resource transition completed.
Jan 29 14:42:25 slave heartbeat: [7263]: info: remote resource transition completed.
Jan 29 14:42:25 slave heartbeat: [7263]: info: Local Resource acquisition completed. (none)
Jan 29 14:42:25 slave heartbeat: [7263]: info: Initial resource acquisition complete (T_RESOURCES(them))
Jan 29 14:42:25 slave heartbeat: [7263]: info: Link master:eth0 up.
Jan 29 14:42:30 slave ipfail: [7293]: info: Link Status update: Link master/eth0 now has status up
Jan 29 14:42:31 slave ipfail: [7293]: info: Ping node count is balanced.
Jan 29 14:42:54 slave heartbeat: [7263]: info: Received shutdown notice from 'master'.
Jan 29 14:42:54 slave heartbeat: [7263]: info: Resources being acquired from master.
Jan 29 14:42:54 slave heartbeat: [7298]: info: acquire all HA resources (standby).
Jan 29 14:42:54 slave heartbeat: [7299]: info: No local resources [/usr/share/heartbeat/ResourceManager listkeys slave] to acquire.
ResourceManager[7324]:  2015/01/29_14:42:54 info: Acquiring resource group: master drbddisk::r0 Filesystem::/dev/drbd0::/drbd::ext4 rpcbind nfs IPaddr::192.168.254.200/24/eth1
ResourceManager[7324]:  2015/01/29_14:42:54 info: Running /etc/ha.d/resource.d/drbddisk r0 start
Filesystem[7393]:       2015/01/29_14:42:54 INFO:  Resource is stopped
#说明成功
ResourceManager[7324]:  2015/01/29_14:42:54 info: Running /etc/ha.d/resource.d/Filesystem /dev/drbd0 /drbd ext4 start
Filesystem[7473]:       2015/01/29_14:42:54 INFO: Running start for /dev/drbd0 on /drbd
Filesystem[7465]:       2015/01/29_14:42:54 INFO:  Success
ResourceManager[7324]:  2015/01/29_14:42:54 info: Running /etc/ha.d/resource.d/rpcbind  start
ResourceManager[7324]:  2015/01/29_14:42:55 info: Running /etc/ha.d/resource.d/nfs  start
IPaddr[7716]:   2015/01/29_14:43:05 INFO:  Resource is stopped
ResourceManager[7324]:  2015/01/29_14:43:05 info: Running /etc/ha.d/resource.d/IPaddr 192.168.254.200/24/eth1 start
IPaddr[7801]:   2015/01/29_14:43:05 INFO: Using calculated netmask for 192.168.254.200: 255.255.255.0
#获取IP
IPaddr[7801]:   2015/01/29_14:43:05 INFO: eval ifconfig eth1:0 192.168.254.200 netmask 255.255.255.0 broadcast 192.168.254.255
IPaddr[7775]:   2015/01/29_14:43:05 INFO:  Success
Jan 29 14:43:05 slave heartbeat: [7298]: info: all HA resource acquisition completed (standby).
Jan 29 14:43:05 slave heartbeat: [7263]: info: Standby resource acquisition done [all].
harc[7888]:     2015/01/29_14:43:05 info: Running /usr/etc/ha.d//rc.d/status status
mach_down[7905]:        2015/01/29_14:43:05 info: Taking over resource group drbddisk::r0
ResourceManager[7932]:  2015/01/29_14:43:05 info: Acquiring resource group: master drbddisk::r0 Filesystem::/dev/drbd0::/drbd::ext4 rpcbind nfs IPaddr::192.168.254.200/24/eth1
Filesystem[7974]:       2015/01/29_14:43:05 INFO:  Running OK
IPaddr[8085]:   2015/01/29_14:43:06 INFO:  Running OK
mach_down[7905]:        2015/01/29_14:43:06 info: /usr/share/heartbeat/mach_down: nice_failback: foreign resources acquired
mach_down[7905]:        2015/01/29_14:43:06 info: mach_down takeover complete for node master.