corosync+pacemaker+crm实现drbd高可用

系统：Centos 7.2 内核3.10.0-327.el7.x86_64      # 内核需要高于2.6.32

Drbd  : 192.168.8.111：node1/dev/drdb0 /mydeta

  192.168.8.112 : node2

Mysql_vip: 192.168.8.200     #下章实现

# 需要的软件包：

mariadb-5.5.53-linux-i686.tar.gz

drbd84-utils-8.9.1-1.el7.elrepo.x86_64.rpm

kmod-drbd84-8.4.6-1.el7.elrepo.x86_64.rpm

yum 需要安装的软件 pcs, ansible, crmsh, libxslt

# drbd是基于主机名通信的在/etc/hosts中增加 

# 以本地ip地址如192.168.8.111 node1这样的方式添加一个地址一行、 127.0.0.1 不要填uname -n的名称

# 安装crmsh yum源如下 [root@node1 ~]# vim /etc/yum.repos.d/ha.repo

[network_ha-clustering_Stable]

name=Stable High Availability/Clustering packages (CentOS_CentOS-7)

type=rpm-md

baseurl=http://download.opensuse.org/repositories/network:/ha-clustering:/Stable/CentOS_CentOS-7/

gpgcheck=1

gpgkey=http://download.opensuse.org/repositories/network:/ha-clustering:/Stable/CentOS_CentOS-7//repodata/repomd.xml.key

enabled=1

# 安装crmsh  单台主机安装就行

yum -y install  crmsh libxslt ansible pcs

# 主机互信

 [root@node1 ~]# ssh-keygen

 [root@node1 ~]# cat .ssh/id_rsa.pub > .ssh/authorized_keys

 [root@node1 ~]# chmod go= .ssh/authorized_keys

 [root@node1 ~]# scp -p .ssh/id_rsa.pub .ssh/authorized_keys 192.168.8.112:/root/.ssh/

# 出现以下错误

scp: /root/.ssh/: No such file or directory

# 解决方案

 连接node2创建.ssh   mkdir /root/.ssh

# drbd配置段

# 安装drbd前先准备两块硬盘    node1 跟node2 同样配置

rpm -ivh http://elrepo.reloumirrors.net/elrepo/el7/x86_64/RPMS/drbd84-utils-8.9.1-1.el7.elrepo.x86_64.rpm

yum -y install http://elrepo.reloumirrors.net/elrepo/el7/x86_64/RPMS/kmod-drbd84-8.4.6-1.el7.elrepo.x86_64.rpm

[root@node1 drbd-8.4.8-1]# modprobe drbd

[root@node1 drbd-8.4.8-1]# lsmod | grep drbd

drbd                  405537  0 

libcrc32c              12644  2 xfs,drbd

# 将新建的磁盘分区

[root@node1 sbin]# fdisk /dev/sdb# 自己新建就成、两边大小保持一致跟raid1一样

# 配置drbd

[root@node1 sbin]#

# drbd配置: http://502245466.blog.51cto.com/7559397/1298945

# drbd常见错误: http://www.j3j5.com/post-128.html

[root@node1 drbd.d]# vim global_common.conf

global {

usage-count no;

}

common {

protocol C;

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";

}

startup {

}

options {

}

disk {

on-io-error detach;

}

net {

cram-hmac-alg "sha1";

shared-secret "xiong123";

}

syncer {

rate 1024M;

}

}

[root@node1 drbd.d]# vim mydrbd.res 

resource mydrbd {

 device /dev/drbd0;

 disk  /dev/sdb1;

 meta-disk internal;

   on node1{on为开启，node1为节点名称

      address 192.168.8.111:7789;

   }

   on node2{

      address 192.168.8.112:7789;

   }

}

[root@node1 drbd.d]# scp mydrbd.res global_common.conf node2:/usr/local/drbd/etc/drbd.d/

############测试drbd是否成功######

[root@node1 drbd.d]# drbdadm create-md mydrbd

initializing activity log

NOT initializing bitmap

Writing meta data...

New drbd meta data block successfully created

# 配置启动否则corosync ocf无法直接定义drbd启动

[root@node1 sbin]# systemctl enable drbd.service

# 此处为测试drbd是否完整  两边都得同时启动

[root@node1 sbin]# systemctl start drbd.service

[root@node1 drbd.d]# drbdadm primary --force mydrbd # 将主机强制成为主节点

[root@node73 drbd.d]# drbd-overview 

 0:mydrbd/0  Connected Primary/Secondary UpToDate/UpToDate# Primary/Secondary 主从，另一端是Secondary/Primary

#格式磁盘

[root@node1 drbd.d]# mkfs.ext4 /dev/drbd0

# 挂载     两个节点都需要创建 /mydata/

[root@node1 drbd.d]# mount /dev/drbd0 /mydata/

[root@node1 drbd.d]# df -Th

/dev/drbd0              ext4      4.8G   20M  4.6G    1% /mydata

复制一个文件至/mydata目录中，并将主drbd设置为从

[root@node1 ~]# umount /mydata/

[root@node1 ~]# drbdadm secondary mydrbd

[root@node1 ~]# drbd-overview 

 0:mydrbd/0  Connected Secondary/Secondary UpToDate/Diskless

# 节点2操作配置 无需格式化/dev/drbd0 

[root@node2 drbd.d]# drbdadm primary mydrbd

[root@node2 drbd.d]# mkdir /mydata

[root@node2 drbd.d]# mount /dev/drbd0 /mydata/

[root@node2 drbd.d]# cd /mydata/

[root@node2 mydata]# ls

issue  lost+found

# 最后将drbd服务都停止 

[root@node1 /]# umount /mydata/

[root@node1 /]# systemctl  stop drbd

[root@node2 /]# systemctl  stop drbd

############################测试结束########################################

# pcs配置drbd高可用

# 安装

# 安装pcs软件如果报/sbin/xxx命令的名字将crmsh.repo先改成crmsh.repo.bak 再安装

[root@node1 sbin]# ansible ha -m yum -a "name=pcs state=installed"

# pcs认证需要

[root@node1 sbin]# ansible ha -m shell -a 'echo "xiong" | passwd --stdin hacluster'

# 启动pcs服务

[root@node1 sbin]# ansible ha -m service -a "name=pcsd state=started enabled=yes"

# 认证集群服务

[root@node1 sbin]# pcs cluster auth node1 node2

Username: hacluster

Password: 

node1: Authorized

node2: Authorized

# 添加一个集群名为myha 并设置组播地址为235.35.32.24

[root@node1 sbin]# pcs cluster setup --name myha node1 node2 --mcast0 235.35.32.24

# 检查集群服务是否正常

[root@node1 sbin]# corosync-cmapctl | grep mem

runtime.totem.pg.mrp.srp.memb_commit_token_rx (u64) = 4

runtime.totem.pg.mrp.srp.memb_commit_token_tx (u64) = 4

runtime.totem.pg.mrp.srp.memb_join_rx (u64) = 5

runtime.totem.pg.mrp.srp.memb_join_tx (u64) = 3

runtime.totem.pg.mrp.srp.memb_merge_detect_rx (u64) = 332

runtime.totem.pg.mrp.srp.memb_merge_detect_tx (u64) = 332

runtime.totem.pg.mrp.srp.members.1.config_version (u64) = 0

runtime.totem.pg.mrp.srp.members.1.ip (str) = r(0) ip(192.168.8.111) 

runtime.totem.pg.mrp.srp.members.1.join_count (u32) = 1

runtime.totem.pg.mrp.srp.members.1.status (str) = joined

runtime.totem.pg.mrp.srp.members.2.config_version (u64) = 0

runtime.totem.pg.mrp.srp.members.2.ip (str) = r(0) ip(192.168.8.112) 

runtime.totem.pg.mrp.srp.members.2.join_count (u32) = 1

runtime.totem.pg.mrp.srp.members.2.status (str) = joined

# 检查状态

[root@node1 sbin]# pcs status

Cluster name: myha

WARNING: no stonith devices and stonith-enabled is not false

Stack: corosync

Current DC: node1 (version 1.1.13-10.el7-44eb2dd) - partition with quorum

2 nodes and 0 resources configured

Online: [ node1 node2 ]

# 配置高可用 

crm(live)configure# primitive mydrbd ocf:linbit:drbd params drbd_resource="mystore" op monitor role="Master" interval=30s timeout=30s op monitor role="Slave" timeout=30s op start timeout=240s op stop timeout=100s

####################正确模板##########################################

primitive mydatas ocf:linbit:drbd \

params drbd_resource=mystore \

op monitor role=Master interval=10s timeout=20s \

op monitor role=Slave interval=20s timeout=20s \

op start timeout=240s interval=0 \

op stop timeout=100s interval=0

######################################################################

crm(live)configure# ms mydrbd_master mydrbd meta clone-max=2 clone-node-max=1 master-max=1 master-node-max=1 

crm(live)configure#  verify     #检查是否成功

crm(live)# status

Online: [ node73 node74 ]

 Master/Slave Set: ms_mydatas [mydatas]

     Masters: [ node73 ]

     Slaves: [ node74 ]

# 配置文件挂载目录

crm(live)configure# primitive mount ocf:heartbeat:Filesystem params device="/dev/drbd0" directory="/mydata" fstype="ext4" op start timeout=60s op stop timeout=60s

# 定义排序约束 让mount一直跟着ms_mydatas的主

crm(live)configure# colocation mount_with_ms_mydatas inf: mount ms_mydatas:Master

# 检查是否成功

[root@node73 ~]# df -Th

/dev/drbd0              ext4       16G   45M   15G    1% /mydata

[root@node73 ~]# drbd-overview 

 0:mystore/0  Connected Primary/Secondary UpToDate/UpToDate /mydata ext4 16G 45M 15G 1% 

####################### drbd主从配置文件###############################

primitive mount Filesystem \

params device="/dev/drbd0" directory="/mydata" fstype=ext4 \

op start timeout=60s interval=0 \

op stop timeout=60s interval=0

primitive mydatas ocf:linbit:drbd \

params drbd_resource=mystore \

op monitor role=Master interval=10s timeout=20s \

op monitor role=Slave interval=20s timeout=20s \

op start timeout=240s interval=0 \

op stop timeout=100s interval=0

ms ms_mydatas mydatas \

meta clone-max=2 clone-node-max=1 master-max=1 master-node-max=1 notify=true

colocation mount_with_ms_mydatas inf: mount ms_mydatas:Master

#########################################################################

# 错误整理

1、ERROR: error: unpack_resources:Resource start-up disabled since no STONITH resources have been defined

   error: unpack_resources:Either configure some or disable STONITH with the stonith-enabled option

   error: unpack_resources:NOTE: Clusters with shared data need STONITH to ensure data integrity

解决：crm(live)configure# property stonith-enabled=false

# 错误 

[root@node1 drbd.d]# drbdadm primary mystore

0: State change failed: (-2) Need access to UpToDate data

Command 'drbdsetup-84 primary 0' terminated with exit code 17

# 解决方案

[root@node1 drbd.d]# drbdadm primary mystore --force

# 错误 

[root@node1 drbd.d]# pcs status

Error: cluster is not currently running on this node

# 解决方案

[root@node1 drbd.d]# pcs cluster start --all

# 启动主从失败

Failed Actions:

* mydrbd_stop_0 on node74 'not configured' (6): call=8, status=complete, exitreason='none',

    last-rc-change='Wed May 24 15:27:42 2017', queued=0ms, exec=138ms

* mydrbd_stop_0 on node73 'not configured' (6): call=8, status=complete, exitreason='none',

    last-rc-change='Wed May 24 15:27:41 2017', queued=0ms, exec=134ms

# 解决方案

设置各种超时时长都加上"s"  primitive mydrbd ocf:linbit:drbd params drbd_resource="mystore" op monitor role="Master" interval=30s timeout=30s op monitor role="Slave" timeout=30s op start timeout=240s op stop timeout=100s

drbd yum包下载地址：http://elrepo.reloumirrors.net/elrepo/el7/x86_64/RPMS/

配置参阅链接： http://blog.csdn.net/qq_21127313/article/details/68210977

     本文转自812374156 51CTO博客，原文链接：http://blog.51cto.com/xiong51/1929054，如需转载请自行联系原作者