DRBD+Heartbeat+NFS高可用实战

时间:2021-11-20 22:27:20

实验环境:Centos 6.7_64位

服务器:

Master节点:dm1 IP地址:10.0.0.61(eth0) 192.168.3.150(eth1,心跳)

Slave节点:dm2 IP地址:10.0.0.62(eth0) 192.168.3.160(eth1,心跳)

VIP地址:192.168.0.180

一、DRBD环境搭建

1. host映射

# vi  /etc/hosts

127.0.0.1   localhostlocalhost.localdomain localhost4 localhost4.localdomain4

::1         localhostlocalhost.localdomain localhost6 localhost6.localdomain6

10.0.0.61 dm1

192.168.3.150 dm1

10.0.0.62 dm2

192.168.3.160 dm2

2. 时间同步

     # ntpdate 10.0.0.254

18 May 19:49:39 ntpdate[16332]: adjust time server 10.0.0.254 offset-0.023216 sec

3. 添加附加库

官方网站:http://elrepo.org/tiki/tiki-index.php

以下测试针对Centos6.7 版本:

aimport public key

#rpm --import https://www.elrepo.org/RPM-GPG-KEY-elrepo.org

b)安装库:

#rpm -Uvh http://www.elrepo.org/elrepo-release-6-6.el6.elrepo.noarch.rpm

4. 安装DRBD

DRBD官方网站:http://drbd.linbit.com/docs/install/

 # yum install drbd84 kmod-drbd84 -y

5. 两台服务器上的分区/dev/sdb1作为drbd的网络mirror分区

# fdisk /dev/sdb

//格式化分区

# mkfs.ext4 /dev/sdb1  //只在主机(dm1)上做

6. 开始配置NFS(两个节点都要执行)

# yum -y install rpcbind nfs-utils

# mkdir  /data

# vi /etc/exports

/data *(rw,no_root_squash,no_all_squash,sync)

# service rpcbind start

# chkconfig rpcbind on

# chkconfig nfs off  //NFS不需要启动,也不需要设置成开机启动,这些都将由后面的Heartbeat来完成。

# netstat -tunlp|grep rpc  //查看rpcbind是否启动成功

tcp        0      0 0.0.0.0:111                 0.0.0.0:*                   LISTEN      16537/rpcbind      

tcp        0      0 :::111                      :::*                        LISTEN      16537/rpcbind      

udp        0      0 0.0.0.0:600                 0.0.0.0:*                               16537/rpcbind      

udp        0      0 0.0.0.0:111                 0.0.0.0:*                               16537/rpcbind      

udp        0      0 :::600                      :::*                                   16537/rpcbind      

udp        0      0 :::111                      :::*                                   16537/rpcbind 

7. 开始配置DRBD

# modprobe drbd  //加载drbd模块到内核中(两个节点都要执行)

# lsmod | grep drbd  //查看drbd模块是否加载成功(两个节点都要执行)

drbd                 372759  3

libcrc32c              1246  1 drbd

说明:显示以上信息,说明drbd模块加载成功

# cat /etc/drbd.conf

# You can find an example in /usr/share/doc/drbd.../drbd.conf.example

 

include "drbd.d/global_common.conf";

include "drbd.d/*.res";

 

说明:主备节点两端配置文件完全一致

# cd /etc/drbd.d/

# vi nfs.res

//设定资源名称为: nfs

resource nfs {

            protocol C;

            net {

                 cram-hmac-algsha1;

                 shared-secret"abcd";

            }

            syncer {rate 30M;}

            on dm1 {

                 device    /dev/drbd1;

                 disk     /dev/sdb1; 

                 address   10.0.0.61:7788;

                 meta-disk internal;

            }

            on dm2 {

                 device    /dev/drbd1;

                 disk      /dev/sdb1;

                 address   10.0.0.62:7788;

                 meta-disk internal;

            }

}

8. 启动DRBD

# drbdadm create-md nfs  //激活前面配置的DRBD资源nfs(两个节点都要执行)

initializing activity log

NOT initializing bitmap

Writing meta data...

New drbd meta data block successfully created.

Success

# service drbd start  //(两个节点都要执行)

# chkconfig drbd on  //(两个节点都要执行)

# cat /proc/drbd

version: 8.4.7-1 (api:1/proto:86-101)

GIT-hash: 3a6a769340ef93b1ba2792c6461250790795db49 build bymockbuild@Build64R6, 2016-01-12 13:27:11

 

 1: cs:Connectedro:Secondary/Secondary ds:Inconsistent/Inconsistent C r-----

    ns:0 nr:0 dw:0 dr:0 al:8bm:0 lo:0 pe:0 ua:0 ap:0 ep:1 wo:f oos:6827344

# drbdsetup /dev/drbd1 primary //初始化一个主机(这几步只在主节点上操作)

# drbdadm primary nfs

# drbdadm -- --overwrite-data-of-peer primary nfs

# cat /proc/drbd                      

version: 8.4.7-1 (api:1/proto:86-101)

GIT-hash: 3a6a769340ef93b1ba2792c6461250790795db49 build bymockbuild@Build64R6, 2016-01-12 13:27:11

 

 1: cs:SyncSourcero:Primary/Secondary ds:UpToDate/Inconsistent C r-----

    ns:1624064 nr:0 dw:0dr:1624728 al:8 bm:0 lo:0 pe:0 ua:0 ap:0 ep:1 wo:f oos:5203280

       [===>................] sync'ed: 23.9% (5080/6664)M

        finish: 0:02:03 speed:42,116 (36,088) K/sec

9. DRBD的使用

# mkfs.ext4 /dev/drbd1

# mount /dev/drbd1 /data  //现在就可以使用DRBD分区了

注意:secondary节点上不允许对DRBD设备进行任何操作,包括只读。所有的读写操作只能在主节点上进行,只有当主节点挂掉时,secondary节点才能提升为主节点,继续进行读写操作。

二、Heartbeat环境搭建

   Heartbeat具体的安装配置:http://linuxzkq.blog.51cto.com/9379412/1771152

   以下仅提供配置文件供参考:

   # vi authkeys //打开下面两项:一共有三种认证方式供选择,第一种是CRC循环冗余校验,第二种是SHA1哈希算法,第三种是MD3哈希算法,其中他们的密码可以任意设置,但是两边密码必须保持一致。  

auth 3 

3 md5 Hello!

chmod 600 authkeys  //给认证文件授权为600

# cd /etc/ha.d/

# cat ha.cf  //dm1

debugfile /var/log/ha-debug

logfile /var/log/ha-log

logfacility  local0

keepalive 2

deadtime 30

warntime 10

initdead 120

udpport 694

ucast eth1 192.168.3.160

auto_failback off

node    dm1

node    dm2

ping 10.0.0.254

respawn hacluster /usr/lib64/heartbeat/ipfail

# cat ha.cf  //dm2

debugfile /var/log/ha-debug

logfile /var/log/ha-log

logfacility  local0

keepalive 2

deadtime 30

warntime 10

initdead 120

udpport 694

ucast eth1 192.168.3.150

auto_failback off

node    dm1

node    dm2

ping 10.0.0.254

respawn hacluster /usr/lib64/heartbeat/ipfail

#tail haresources  //两台主、备机器上的配置是一样的

#node1 10.0.0.170 Filesystem::/dev/sda1::/data1::ext2

#

#      Regarding the node-names in this file:

#

#      They must match the names of the nodes listed in ha.cf, which in turn

#      must match the `uname -n` of some node in the cluster.  So they aren't

#      virtual in any sense of the word.

#

#dm1 IPaddr::192.168.0.180/32/eth0 drbddisk::nfs Filesystem::/dev/drbd1::/data::ext4 nfs

dm1 IPaddr::192.168.0.180/24/eth0 drbd_primary

说明:

drbddisk::data  <==启动drbd data资源,相当于执行/etc/ha.d/resource.d/drbddiskdata stop/start操作

Filesystem::/dev/drbd1::/data::ext4 <==drbd分区挂载到/data目录,相当于执行/etc/ha.d/resource.d/Filesystem /dev/drbd1 /data ext4stop/start <==相当于系统中执行mount /dev/drbd1 /data

nfs  <==启动nfs服务脚本,相当于/etc/init.d/nfsstop/start

资源切换脚本:

drbd_primary  resource-group用来指定需要Heartbeat托管的服务,也就是这些 服务可以由Heartbeat来启动和关闭。如果要托管这些服务,就必须将服务写成可以通过start/stop来启动和关闭的脚步,然后放到/etc/init.d/或者/etc/ha.d/resource.d/目录下,Heartbeat会根据脚本的名称自动去/etc/init.d或者/etc/ha.d/resource.d/目录下找到相应脚本进行启动或关闭操作。

本脚本复制drbd的切换:

# cd /etc/init.d

# cat drbd_primary  //两台机器上的脚本一模一样
#!/bin/sh
case "$1" in
start)
    drbdadm primary nfs
    mount /dev/drbd1 /data
   /etc/init.d/nfs start
;;
stop)
   /etc/init.d/nfs stop
   umount /dev/drbd1
   drbdadm secondary nfs
;;
esac
exit 0

# chmod 755 drbd_primary

 

启动Heartbeat(先主后从):

# /etc/init.d/heartbeat start

# chkconfig heartbeat on

# netstat -tunlp|grep hear

udp        0     0 0.0.0.0:694                0.0.0.0:*                              2447/heartbeat: wri

udp        0     0 0.0.0.0:58330              0.0.0.0:*                              2447/heartbeat: wri

# ip a|grep eth0  //dm1

2: eth0:<BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen1000

   inet 10.0.0.61/24 brd 10.0.0.255 scope global eth0

inet 192.168.0.180/32 scope global eth0

# df-h

Filesystem      Size Used Avail Use% Mounted on

/dev/sda3        14G 2.9G   10G  23% /

tmpfs           238M     0 238M   0% /dev/shm

/dev/sda1       190M  52M  129M  29% /boot

/dev/drbd1      6.3G  15M  6.0G   1% /data

# df-h  //dm2

Filesystem      Size Used Avail Use% Mounted on

/dev/sda3        14G 2.5G   11G  19% /

tmpfs           238M     0 238M   0% /dev/shm

/dev/sda1       190M  52M  129M  29% /boot

# ip a|grep eth0

2: eth0:<BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen1000

inet10.0.0.62/24 brd 10.0.0.255 scope global eth0

# netstat -tunlp|grep hear

udp        0     0 0.0.0.0:694                0.0.0.0:*                              1789/heartbeat: wri

udp        0     0 0.0.0.0:18128              0.0.0.0:*                               1789/heartbeat: wri

 

三、测试

1. 测试NFS客户端读写共享目录是否正常

# cd/data

# mkdirtest  //dm1

[root@lb_stmp]# ls  //NFS客户端

[root@lb_stmp]# df -h

Filesystem      Size Used Avail Use% Mounted on

/dev/sda3        14G 1.6G   12G  12% /

tmpfs           238M     0 238M   0% /dev/shm

/dev/sda1       190M  51M  129M  29% /boot

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

[root@lb_stmp]# service rpcbind start

[root@lb_stmp]# chkconfig rpcbind on

[root@lb_stmp]# ping 192.168.0.180       

PING192.168.0.180 (192.168.0.180) 56(84) bytes of data.

64 bytesfrom 192.168.0.180: icmp_seq=52 ttl=64 time=0.242 ms

64 bytesfrom 192.168.0.180: icmp_seq=53 ttl=64 time=0.434 ms

64 bytesfrom 192.168.0.180: icmp_seq=54 ttl=64 time=0.364 ms

64 bytesfrom 192.168.0.180: icmp_seq=55 ttl=64 time=0.310 ms

64 bytesfrom 192.168.0.180: icmp_seq=56 ttl=64 time=0.308 ms

[root@lb_stmp]# showmount -e 192.168.0.180

Exportlist for 192.168.0.180:

/data(everyone)

[root@lb_stmp]# mount -t nfs 192.168.0.180:/data /media

[root@lb_s~]# df -h

Filesystem           Size Used Avail Use% Mounted on

/dev/sda3             14G  1.6G  12G  12% /

tmpfs                238M     0 238M   0% /dev/shm

/dev/sda1            190M   51M 129M  29% /boot

192.168.0.180:/data  6.3G  15M  6.0G   1% /media

[root@lb_s~]# ll /media/

0

drwxrwxrwx2 root root 16384 518 22:21 lost+found

drwxrwxrwx2 root root  4096 518 23:18 test

[root@lb_s~]# cd /media/

[root@lb_smedia]# ls

lost+found  test

[root@lb_smedia]# touch 333  //NFS客户端在共享目录上读写数据成功

[root@lb_smedia]# ls

333  lost+found test

[root@dm1~]# ll /data

0

-rw-r--r--1 root root     0 520 20:35 333 

drwxrwxrwx2 root root 16384 518 22:21 lost+found

drwxrwxrwx2 root root  4096 518 23:18 test

2.  测试高可用

[root@dm1~]# /etc/init.d/heartbeat stop

StoppingHigh-Availability services: Done.

[root@dm1~]# ip a|grep eth0

2:eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast stateUP qlen 1000

inet 10.0.0.61/24 brd 10.0.0.255 scope global eth0

[root@dm1~]# df -h  //可以看到DRBD资源已释放

Filesystem      Size Used Avail Use% Mounted on

/dev/sda3        14G 2.9G   10G  23% /

tmpfs           238M     0 238M   0% /dev/shm

/dev/sda1       190M  52M  129M  29% /boot

[root@dm1~]# cat /proc/drbd  //我们看到dm1上的DRBD角色由原来的主,已转换成备

version:8.4.7-1 (api:1/proto:86-101)

GIT-hash:3a6a769340ef93b1ba2792c6461250790795db49 build by mockbuild@Build64R6,2016-01-12 13:27:11

 

 1: cs:Connected ro:Secondary/Primaryds:UpToDate/UpToDate C r-----

ns:88 nr:16 dw:104 dr:1366 al:3 bm:0 lo:0 pe:0 ua:0 ap:0 ep:1wo:f oos:0

[root@dm2~]# ip a|grep eth0  //已看到VIP飘移成功

2:eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast stateUP qlen 1000

    inet 10.0.0.62/24 brd 10.0.0.255 scopeglobal eth0

inet 192.168.0.180/24 scope global eth0

[root@dm2~]# df -h  //DRBD资源切换成功,并挂载.

Filesystem      Size Used Avail Use% Mounted on

/dev/sda3        14G 2.5G   11G  19% /

tmpfs           238M     0 238M   0% /dev/shm

/dev/sda1       190M  52M  129M  29% /boot

/dev/drbd1      6.3G  15M  6.0G   1% /data

[root@dm2~]# cat /proc/drbd  //我们看到dm2上的DRBD角色由原来的备,已转换成主.

version:8.4.7-1 (api:1/proto:86-101)

GIT-hash:3a6a769340ef93b1ba2792c6461250790795db49 build by mockbuild@Build64R6,2016-01-12 13:27:11

 

 1: cs:Connected ro:Primary/Secondary ds:UpToDate/UpToDateC r-----

ns:40 nr:112 dw:152 dr:1366 al:2 bm:0 lo:0 pe:0 ua:0 ap:0 ep:1wo:f oos:0

[root@dm2~]# ll /data  //我们看到数据也同步成功

0

-rw-r--r--1 root root     0 520 20:35 333

drwxrwxrwx2 root root 16384 518 22:21 lost+found

drwxrwxrwx2 root root  4096 518 23:18 test

 

DRBD+Heartbeat+NFS的高可用至此结束,对高可用的测试,我们上面只是测试了一种情况,当然还有其它几种情况,留给大家去测试吧!


本文出自 “云计算与大数据” 博客,请务必保留此出处http://linuxzkq.blog.51cto.com/9379412/1775552