MHA 一主两从搭建-脚本VIP-自动切换

环境介绍：
主机名 IP MHA角色 MySQL角色
node1 192.168.56.26 Node MySQL Master
node2 192.168.56.27 Node MySQL Master behind
node3 192.168.56.28 Node MySQL slave
node4 192.168.56.36 Manager None

所有主机 /etc/hosts 添加信息
192.168.56.26 node1
192.168.56.27 node2
192.168.56.28 node3
192.168.56.36 node4

关闭selinux
永久生效：
/etc/selinux/config 文件修改如下参数
SELINUX=disabled

临时生效：
setenforce 0

关闭防火墙
chkconfig iptables off
chkconfig ip6tables off

/etc/init.d/iptables stop

安装MySQL：

解压软件
mkdir /opt/mysql
mv mysql-5.6.34-linux-glibc2.5-x86_64.tar.gz /opt/mysql
cd /opt/mysql
tar -zxvf mysql-5.6.34-linux-glibc2.5-x86_64.tar.gz

创建软连接
ln -s /opt/mysql/mysql-5.6.34-linux-glibc2.5-x86_64 /usr/local/mysql

创建运行用户
groupadd mysql
useradd -g mysql -d /usr/local/mysql -s /sbin/nologin -M -n mysql

创建所需的目录
mkdir -p /data/mysql/3307/{data,logs,tmp}
chown -R mysql:mysql /data/mysql/3307/
chown -R mysql:mysql /usr/local/mysql

配置文件内容
#my.cnf
[client]
port = 3307
socket = /data/mysql/3307/tmp/3307.sock

[mysql]
#pager="less -i -n -S"
#tee=/opt/mysql/query.log
no-auto-rehash

[mysqld]
#misc
user = mysql
basedir = /usr/local/mysql
datadir = /data/mysql/3307/data
port = 3307
socket = /data/mysql/3307/tmp/3307.sock
event_scheduler = 0

tmpdir = /data/mysql/3307/tmp
#timeout
interactive_timeout = 300
wait_timeout = 300

#character set
character-set-server = utf8

open_files_limit = 65535
max_connections = 100
max_connect_errors = 100000
lower_case_table_names =1

#symi replication

#rpl_semi_sync_master_enabled=1
#rpl_semi_sync_master_timeout=1000 # 1 second
#rpl_semi_sync_slave_enabled=1

#logs
log-output=file
slow_query_log = 1
slow_query_log_file = slow.log
log-error = error.log
log_warnings = 2
pid-file = mysql.pid
long_query_time = 1
#log-slow-admin-statements = 1
#log-queries-not-using-indexes = 1
log-slow-slave-statements = 1

#binlog
#binlog_format = STATEMENT
binlog_format = row
server-id = 330728
log-bin = /data/mysql/3307/logs/mysql-bin
binlog_cache_size = 4M
max_binlog_size = 256M
max_binlog_cache_size = 1M
sync_binlog = 0
expire_logs_days = 10
#procedure
log_bin_trust_function_creators=1

#
#gtid-mode = on
#enforce-gtid-consistency=1

#relay log
skip_slave_start = 1
max_relay_log_size = 128M
relay_log_purge = 1
relay_log_recovery = 1
relay-log=relay-bin
relay-log-index=relay-bin.index
log_slave_updates
#slave-skip-errors=1032,1053,1062
#skip-grant-tables

#buffers & cache
table_open_cache = 2048
table_definition_cache = 2048
table_open_cache = 2048
max_heap_table_size = 96M
sort_buffer_size = 128K
join_buffer_size = 128K
thread_cache_size = 200
query_cache_size = 0
query_cache_type = 0
query_cache_limit = 256K
query_cache_min_res_unit = 512
thread_stack = 192K
tmp_table_size = 96M
key_buffer_size = 8M
read_buffer_size = 2M
read_rnd_buffer_size = 16M
bulk_insert_buffer_size = 32M

#myisam
myisam_sort_buffer_size = 128M
myisam_max_sort_file_size = 10G
myisam_repair_threads = 1

#innodb
innodb_buffer_pool_size = 100M
innodb_buffer_pool_instances = 1
innodb_data_file_path = ibdata1:100M:autoextend
innodb_flush_log_at_trx_commit = 2
innodb_log_buffer_size = 8M
innodb_log_file_size = 100M
innodb_log_files_in_group = 3
innodb_max_dirty_pages_pct = 50
innodb_file_per_table = 1
innodb_rollback_on_timeout
innodb_status_file = 1
innodb_io_capacity = 100
transaction_isolation = READ-COMMITTED
innodb_flush_method = O_DIRECT

修改my3307.cnf权限
chown mysql:mysql /etc/my.cnf

初始化数据库
/usr/local/mysql/scripts/mysql_install_db --defaults-file=/etc/my.cnf --basedir=/usr/local/mysql --datadir=/data/mysql/3307/data --user=mysql

设置环境变量
echo "export PATH=$PATH:/usr/local/mysql/bin">> /etc/profile
source /etc/profile

cp /usr/local/mysql/support-files/mysql.server /etc/init.d/mysqld

启动MySQL
/etc/init.d/mysqld start

账号处理
grant all privileges on *.* to 'root'@'%' identified by 'chengce243' with grant option;
delete from mysql.user where password ='';
flush privileges;

搭建从库
主库创建复制账号
create user 'repl'@'192.168.56.%' identified by 'chengce243';
grant replication slave on *.* to 'repl'@'192.168.56.%';
flush privileges;

两个从库分别执行如下语句
MASTER_LOG_FILE 和 MASTER_LOG_POS 值，从主库 show master status;查看

CHANGE MASTER TO MASTER_HOST='192.168.56.26',MASTER_USER='repl',MASTER_PASSWORD='chengce243',MASTER_PORT=3307,MASTER_LOG_FILE='mysql-bin.000003',MASTER_LOG_POS=1718;

两个从库分别开启复制
start slave;

主库上创建
create user 'mhauser'@'192.168.56.%' identified by 'chengce243';
grant all privileges on *.* to 'mhauser'@'192.168.56.%';
flush privileges;

分别配置root用户和mysql用户互信

生成互信文件，输入如下命令，一路回车就行
ssh-keygen

cd ~/.ssh

cat id_rsa.pub > authorized_keys
chmod 600 *
cd ~/
scp -r .ssh 192.168.56.27:~/
scp -r .ssh 192.168.56.28:~/
scp -r .ssh 192.168.56.36:~/

最后每个节点都要验证
ssh node1 date
ssh node2 date
ssh node3 date
ssh node4 date

每个节点都要安装相关依赖包
yum install -y perl-devel
yum install -y perl-CPAN
yum install -y perl-Time-HiRes
yum install -y perl-DBD-MySQL
yum install -y perl-Params-Validate

yum install -y perl-Config-Tiny
yum install -y perl-Log-Dispatch
yum install -y perl-Parallel-ForkManager

MHA master节点，即node4安装
rpm -ivh mha4mysql-manager-0.56-0.el6.noarch.rpm
rpm -ivh mha4mysql-node-0.56-0.el6.noarch.rpm

MHA node节点，即node1/node2/node3安装
rpm -ivh mha4mysql-node-0.56-0.el6.noarch.rpm

为MHA的相关配置信息的存放规划目录结构（四台服务器均要操作）：
mkdir -p /masterha_work/{conf,manager_workdir,rmt_mysql_binlog_workdir,script_dir,log}

自定义规则：
conf，存放MHA的配置文件
log，存放于MHA有关的日志信息
script_dir，除了默认的存放脚本的位置外，另一个存放自定义的或者官方提供的脚本的位置
manager_workdir，Manager的工作目录
rmt_mysql_binlog_workdir，当发生切换的时候，MySQL的binlog的临时存放路径

修改配置目录权限：
chown -R mysql:mysql /masterha_work
[root@node4 conf]# cat /masterha_work/conf/mha_total.cnf
[server default]
manager_workdir=/masterha_work/manager_workdir
manager_log=/masterha_work/log/manager.log

master_binlog_dir=/data/mysql/3307/logs
user=mhauser
password=chengce243

#master_ip_failover_script=/usr/bin/master_ip_failover --command=status --ssh_user=root --orig_master_host=node1 --orig_master_ip=192.168.56.26 --orig_master_port=3307
master_ip_online_change_script=/usr/bin/master_ip_online_change

ping_interval=1

remote_workdir=/masterha_work/rmt_mysql_binlog_workdir

repl_user=repl
repl_password=chengce243
port=3307

report_script=/usr/bin/send_report

secondary_check_script=/usr/local/bin/masterha_secondary_check -s node2 -s node1 --user=mhame --master_host=node2 --master_ip=192.168.56.27 --master_port=3307
shutdown_script=""

ssh_user=root

[server1]
hostname=192.168.56.26
port=3307

[server2]
hostname=192.168.56.27
candidate_master=1
check_repl_delay=0
port=3307

[server3]
hostname=192.168.56.28
port=3307
no_master=1

测试SSH连通性：

[root@node4 ~]# masterha_check_ssh --conf=/masterha_work/conf/mha_total.cnf
Fri Oct 6 18:14:21 2017 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Fri Oct 6 18:14:21 2017 - [info] Reading application default configuration from /masterha_work/conf/mha_total.cnf..
Fri Oct 6 18:14:21 2017 - [info] Reading server configuration from /masterha_work/conf/mha_total.cnf..
Fri Oct 6 18:14:21 2017 - [info] Starting SSH connection tests..
Fri Oct 6 18:14:22 2017 - [debug]
Fri Oct 6 18:14:21 2017 - [debug] Connecting via SSH from root@192.168.56.26(192.168.56.26:22) to root@192.168.56.27(192.168.56.27:22)..
Fri Oct 6 18:14:21 2017 - [debug] ok.
Fri Oct 6 18:14:21 2017 - [debug] Connecting via SSH from root@192.168.56.26(192.168.56.26:22) to root@192.168.56.28(192.168.56.28:22)..
Fri Oct 6 18:14:22 2017 - [debug] ok.
Fri Oct 6 18:14:22 2017 - [debug]
Fri Oct 6 18:14:21 2017 - [debug] Connecting via SSH from root@192.168.56.27(192.168.56.27:22) to root@192.168.56.26(192.168.56.26:22)..
Fri Oct 6 18:14:22 2017 - [debug] ok.
Fri Oct 6 18:14:22 2017 - [debug] Connecting via SSH from root@192.168.56.27(192.168.56.27:22) to root@192.168.56.28(192.168.56.28:22)..
Fri Oct 6 18:14:22 2017 - [debug] ok.
Fri Oct 6 18:14:23 2017 - [debug]
Fri Oct 6 18:14:22 2017 - [debug] Connecting via SSH from root@192.168.56.28(192.168.56.28:22) to root@192.168.56.26(192.168.56.26:22)..
Fri Oct 6 18:14:22 2017 - [debug] ok.
Fri Oct 6 18:14:22 2017 - [debug] Connecting via SSH from root@192.168.56.28(192.168.56.28:22) to root@192.168.56.27(192.168.56.27:22)..
Fri Oct 6 18:14:23 2017 - [debug] ok.
Fri Oct 6 18:14:23 2017 - [info] All SSH connection tests passed successfully.

测试MySQL复制的情况：
[root@node4 ~]# masterha_check_repl --conf=/masterha_work/conf/mha_total.cnf
Fri Oct 6 18:16:53 2017 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Fri Oct 6 18:16:53 2017 - [info] Reading application default configuration from /masterha_work/conf/mha_total.cnf..
Fri Oct 6 18:16:53 2017 - [info] Reading server configuration from /masterha_work/conf/mha_total.cnf..
Fri Oct 6 18:16:53 2017 - [info] MHA::MasterMonitor version 0.56.
Fri Oct 6 18:16:53 2017 - [info] GTID failover mode = 0
Fri Oct 6 18:16:53 2017 - [info] Dead Servers:
Fri Oct 6 18:16:53 2017 - [info] Alive Servers:
Fri Oct 6 18:16:53 2017 - [info] 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 18:16:53 2017 - [info] 192.168.56.27(192.168.56.27:3307)
Fri Oct 6 18:16:53 2017 - [info] 192.168.56.28(192.168.56.28:3307)
Fri Oct 6 18:16:53 2017 - [info] Alive Slaves:
Fri Oct 6 18:16:53 2017 - [info] 192.168.56.27(192.168.56.27:3307) Version=5.6.34-log (oldest major version between slaves) log-bin:enabled
Fri Oct 6 18:16:53 2017 - [info] Replicating from 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 18:16:53 2017 - [info] Primary candidate for the new Master (candidate_master is set)
Fri Oct 6 18:16:53 2017 - [info] 192.168.56.28(192.168.56.28:3307) Version=5.6.34-log (oldest major version between slaves) log-bin:enabled
Fri Oct 6 18:16:53 2017 - [info] Replicating from 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 18:16:53 2017 - [info] Not candidate for the new Master (no_master is set)
Fri Oct 6 18:16:53 2017 - [info] Current Alive Master: 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 18:16:53 2017 - [info] Checking slave configurations..
Fri Oct 6 18:16:53 2017 - [info] read_only=1 is not set on slave 192.168.56.27(192.168.56.27:3307).
Fri Oct 6 18:16:53 2017 - [warning] relay_log_purge=0 is not set on slave 192.168.56.27(192.168.56.27:3307).
Fri Oct 6 18:16:53 2017 - [info] read_only=1 is not set on slave 192.168.56.28(192.168.56.28:3307).
Fri Oct 6 18:16:53 2017 - [warning] relay_log_purge=0 is not set on slave 192.168.56.28(192.168.56.28:3307).
Fri Oct 6 18:16:53 2017 - [info] Checking replication filtering settings..
Fri Oct 6 18:16:53 2017 - [info] binlog_do_db= , binlog_ignore_db=
Fri Oct 6 18:16:53 2017 - [info] Replication filtering check ok.
Fri Oct 6 18:16:53 2017 - [info] GTID (with auto-pos) is not supported
Fri Oct 6 18:16:53 2017 - [info] Starting SSH connection tests..
Fri Oct 6 18:16:56 2017 - [info] All SSH connection tests passed successfully.
Fri Oct 6 18:16:56 2017 - [info] Checking MHA Node version..
Fri Oct 6 18:16:56 2017 - [info] Version check ok.
Fri Oct 6 18:16:56 2017 - [info] Checking SSH publickey authentication settings on the current master..
Fri Oct 6 18:16:56 2017 - [info] HealthCheck: SSH to 192.168.56.26 is reachable.
Fri Oct 6 18:16:57 2017 - [info] Master MHA Node version is 0.56.
Fri Oct 6 18:16:57 2017 - [info] Checking recovery script configurations on 192.168.56.26(192.168.56.26:3307)..
Fri Oct 6 18:16:57 2017 - [info] Executing command: save_binary_logs --command=test --start_pos=4 --binlog_dir=/data/mysql/3307/logs --output_file=/masterha_work/rmt_mysql_binlog_workdir/save_binary_logs_test --manager_version=0.56 --start_file=mysql-bin.000003
Fri Oct 6 18:16:57 2017 - [info] Connecting to root@192.168.56.26(192.168.56.26:22)..
Creating /masterha_work/rmt_mysql_binlog_workdir if not exists.. ok.
Checking output directory is accessible or not..
ok.
Binlog found at /data/mysql/3307/logs, up to mysql-bin.000003
Fri Oct 6 18:16:57 2017 - [info] Binlog setting check done.
Fri Oct 6 18:16:57 2017 - [info] Checking SSH publickey authentication and checking recovery script configurations on all alive slave servers..
Fri Oct 6 18:16:57 2017 - [info] Executing command : apply_diff_relay_logs --command=test --slave_user='mhauser' --slave_host=192.168.56.27 --slave_ip=192.168.56.27 --slave_port=3307 --workdir=/masterha_work/rmt_mysql_binlog_workdir --target_version=5.6.34-log --manager_version=0.56 --relay_log_info=/data/mysql/3307/data/relay-log.info --relay_dir=/data/mysql/3307/data/ --slave_pass=xxx
Fri Oct 6 18:16:57 2017 - [info] Connecting to root@192.168.56.27(192.168.56.27:22)..
Checking slave recovery environment settings..
Opening /data/mysql/3307/data/relay-log.info ... ok.
Relay log found at /data/mysql/3307/data, up to relay-bin.000002
Temporary relay log file is /data/mysql/3307/data/relay-bin.000002
Testing mysql connection and privileges..Warning: Using a password on the command line interface can be insecure.
done.
Testing mysqlbinlog output.. done.
Cleaning up test file(s).. done.
Fri Oct 6 18:16:58 2017 - [info] Executing command : apply_diff_relay_logs --command=test --slave_user='mhauser' --slave_host=192.168.56.28 --slave_ip=192.168.56.28 --slave_port=3307 --workdir=/masterha_work/rmt_mysql_binlog_workdir --target_version=5.6.34-log --manager_version=0.56 --relay_log_info=/data/mysql/3307/data/relay-log.info --relay_dir=/data/mysql/3307/data/ --slave_pass=xxx
Fri Oct 6 18:16:58 2017 - [info] Connecting to root@192.168.56.28(192.168.56.28:22)..
Checking slave recovery environment settings..
Opening /data/mysql/3307/data/relay-log.info ... ok.
Relay log found at /data/mysql/3307/data, up to relay-bin.000002
Temporary relay log file is /data/mysql/3307/data/relay-bin.000002
Testing mysql connection and privileges..Warning: Using a password on the command line interface can be insecure.
done.
Testing mysqlbinlog output.. done.
Cleaning up test file(s).. done.
Fri Oct 6 18:16:58 2017 - [info] Slaves settings check done.
Fri Oct 6 18:16:58 2017 - [info]
192.168.56.26(192.168.56.26:3307) (current master)
+--192.168.56.27(192.168.56.27:3307)
+--192.168.56.28(192.168.56.28:3307)

Fri Oct 6 18:16:58 2017 - [info] Checking replication health on 192.168.56.27..
Fri Oct 6 18:16:58 2017 - [info] ok.
Fri Oct 6 18:16:58 2017 - [info] Checking replication health on 192.168.56.28..
Fri Oct 6 18:16:58 2017 - [info] ok.
Fri Oct 6 18:16:58 2017 - [warning] master_ip_failover_script is not defined.
Fri Oct 6 18:16:58 2017 - [warning] shutdown_script is not defined.
Fri Oct 6 18:16:58 2017 - [info] Got exit code 0 (Not master dead).

MySQL Replication Health is OK.

配置VIP

str_vip="192.168.56.206"
str_mask="255.255.255.0"
str_nic_name="eth0:0"

ifconfig $str_nic_name $str_vip netmask $str_mask up
ifconfig $str_nic_name $str_vip netmask $str_mask down

master_ip_failover脚本修改

注释掉 FIXME，

原：
## Creating an app user on the new master
print "Creating app user on the new master..\n";
FIXME_xxx_create_user( $new_master_handler->{dbh} );
$new_master_handler->enable_log_bin_local();
$new_master_handler->disconnect();
## Update master ip on the catalog database, etc
FIXME_xxx;

修改如下：

## Creating an app user on the new master
print "Creating app user on the new master..\n";
#FIXME_xxx_create_user( $new_master_handler->{dbh} );
$new_master_handler->enable_log_bin_local();
$new_master_handler->disconnect();
## Update master ip on the catalog database, etc
#FIXME_xxx;

在 FIXME_xxx 后面增加对do_vip_crontab.sh 脚本的调用：

`/usr/bin/ssh -t root\@${orig_master_ip} "sh /data/script/do_vip_crontab.sh 1 0"`;
`/usr/bin/ssh -t root\@${new_master_ip} "sh /data/script/do_vip_crontab.sh 0 1"`;
`sh /script/shell/do_mha.sh > /work_dir/mha_manager/test_me/do_mha.log`;

注意，一定要用【;】结尾，否则脚本执行会出错。

修改 new_master_handler 中 mhamhauser用户与密码 ：

# args: hostname, port, user, password, raise_error_or_not
#$new_master_handler->connect( $new_master_ip, $new_master_port,
# $new_master_user, $new_master_password, 1 );
$new_master_handler->connect( $new_master_ip, $new_master_port,
'mhauser', 'chengce243', 1 );

修改后 master_ip_failover 脚本如下：

[root@node4 ~]# cat /usr/bin/master_ip_failover
#!/usr/bin/env perl

# Copyright (C) 2011 DeNA Co.,Ltd.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA

## Note: This is a sample script and is not complete. Modify the script based on your environment.

use strict;
use warnings FATAL => 'all';

use Getopt::Long;
use MHA::DBHelper;

my (
$command, $ssh_user, $orig_master_host,
$orig_master_ip, $orig_master_port, $new_master_host,
$new_master_ip, $new_master_port, $new_master_user,
$new_master_password
);
GetOptions(
'command=s' => \$command,
'ssh_user=s' => \$ssh_user,
'orig_master_host=s' => \$orig_master_host,
'orig_master_ip=s' => \$orig_master_ip,
'orig_master_port=i' => \$orig_master_port,
'new_master_host=s' => \$new_master_host,
'new_master_ip=s' => \$new_master_ip,
'new_master_port=i' => \$new_master_port,
'new_master_user=s' => \$new_master_user,
'new_master_password=s' => \$new_master_password,
);

exit &main();

sub main {
if ( $command eq "stop" || $command eq "stopssh" ) {

# $orig_master_host, $orig_master_ip, $orig_master_port are passed.
# If you manage master ip address at global catalog database,
# invalidate orig_master_ip here.
my $exit_code = 1;
eval {

# updating global catalog, etc
$exit_code = 0;
};
if ($@) {
warn "Got Error: $@\n";
exit $exit_code;
}
exit $exit_code;
}
elsif ( $command eq "start" ) {

# all arguments are passed.
# If you manage master ip address at global catalog database,
# activate new_master_ip here.
# You can also grant write access (create user, set read_only=0, etc) here.
my $exit_code = 10;
eval {
my $new_master_handler = new MHA::DBHelper();

# args: hostname, port, user, password, raise_error_or_not
$new_master_handler->connect( $new_master_ip, $new_master_port,
"mhauser", "chengce243", 1 );

## Set read_only=0 on the new master
$new_master_handler->disable_log_bin_local();
print "Set read_only=0 on the new master.\n";
$new_master_handler->disable_read_only();

## Creating an app user on the new master
print "Creating app user on the new master..\n";
#FIXME_xxx_create_user( $new_master_handler->{dbh} );
$new_master_handler->enable_log_bin_local();
$new_master_handler->disconnect();

## Update master ip on the catalog database, etc
#FIXME_xxx;

`echo "script begin running..." > /masterha_work/manager_workdir/master_ip_failover_run_shell`;

#`/usr/bin/ssh -t root\@${orig_master_ip} "service keepalived stop" > /work_dir/mha_manager/test_me/orig_master.log`;
#`/usr/bin/ssh -t root\@${new_master_ip} "service keepalived start" > /work_dir/mha_manager/test_me/new_master.log`;
`/usr/bin/ssh -t root\@${orig_master_ip} "sh /data/script/do_vip_crontab.sh 1 0"`;
`/usr/bin/ssh -t root\@${new_master_ip} "sh /data/script/do_vip_crontab.sh 0 1"`;
`sh /script/shell/do_mha.sh > /work_dir/mha_manager/test_me/do_mha.log`;

$exit_code = 0;
};
if ($@) {
warn $@;

# If you want to continue failover, exit 10.
exit $exit_code;
}
exit $exit_code;
}
elsif ( $command eq "status" ) {

# do nothing
exit 0;
}
else {
&usage();
exit 1;
}
}

sub usage {
print
"Usage: master_ip_failover --command=start|stop|stopssh|status --orig_master_host=host --orig_master_ip=ip --orig_master_port=port --new_master_host=host --new_master_ip=ip --new_master_port=port\n";
}

最后修改脚本权限：
chmod 755 /usr/bin/master_ip_failover

master_ip_online_change 脚本修改：

注释 FIXME_xxx_drop_app_user
原来：
## Drop application user so that nobody can connect. Disabling per-session binlog beforehand
$orig_master_handler->disable_log_bin_local();
print current_time_us() . " Drpping app user on the orig master..\n";
FIXME_xxx_drop_app_user($orig_master_handler);

修改如下：
## Drop application user so that nobody can connect. Disabling per-session binlog beforehand
$orig_master_handler->disable_log_bin_local();
print current_time_us() . " Drpping app user on the orig master..\n";
#FIXME_xxx_drop_app_user($orig_master_handler);

注释 FIXME_xxx_create_app_user
原来：
## Creating an app user on the new master
print current_time_us() . " Creating app user on the new master..\n";
FIXME_xxx_create_app_user($new_master_handler);
$new_master_handler->enable_log_bin_local();
$new_master_handler->disconnect();

修改如下：
## Creating an app user on the new master
print current_time_us() . " Creating app user on the new master..\n";
#FIXME_xxx_create_app_user($new_master_handler);
$new_master_handler->enable_log_bin_local();
$new_master_handler->disconnect();

修改 mhauser 用户的位置：
位置一：
# args: hostname, port, user, password, raise_error(die_on_error)_or_not
$new_master_handler->connect( $new_master_ip, $new_master_port,
"mhauser", "chengce243", 1 );

位置二：
# args: hostname, port, user, password, raise_error_or_not
$new_master_handler->connect( $new_master_ip, $new_master_port,
"mhauser", "chengce243", 1 );

增加do_vip_crontab.sh 脚本的调用：
`/usr/bin/ssh -t root\@${orig_master_ip} "sh /data/script/do_vip_crontab.sh 1 0"`;
`/usr/bin/ssh -t root\@${new_master_ip} "sh /data/script/do_vip_crontab.sh 0 1"`;

/masterha_work/manager_workdir/master_ip_failover_run_shell

修改后的脚本如下：
[root@node4 ~]# cat /usr/bin/master_ip_online_change
#!/usr/bin/env perl

# Copyright (C) 2011 DeNA Co.,Ltd.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA

## Note: This is a sample script and is not complete. Modify the script based on your environment.

use strict;
use warnings FATAL => 'all';

use Getopt::Long;
use MHA::DBHelper;
use MHA::NodeUtil;
use Time::HiRes qw( sleep gettimeofday tv_interval );
use Data::Dumper;

my $_tstart;
my $_running_interval = 0.1;
my (
$command, $orig_master_is_new_slave, $orig_master_host,
$orig_master_ip, $orig_master_port, $orig_master_user,
$orig_master_password, $orig_master_ssh_user, $new_master_host,
$new_master_ip, $new_master_port, $new_master_user,
$new_master_password, $new_master_ssh_user,
);
GetOptions(
'command=s' => \$command,
'orig_master_is_new_slave' => \$orig_master_is_new_slave,
'orig_master_host=s' => \$orig_master_host,
'orig_master_ip=s' => \$orig_master_ip,
'orig_master_port=i' => \$orig_master_port,
'orig_master_user=s' => \$orig_master_user,
'orig_master_password=s' => \$orig_master_password,
'orig_master_ssh_user=s' => \$orig_master_ssh_user,
'new_master_host=s' => \$new_master_host,
'new_master_ip=s' => \$new_master_ip,
'new_master_port=i' => \$new_master_port,
'new_master_user=s' => \$new_master_user,
'new_master_password=s' => \$new_master_password,
'new_master_ssh_user=s' => \$new_master_ssh_user,
);

exit &main();

sub current_time_us {
my ( $sec, $microsec ) = gettimeofday();
my $curdate = localtime($sec);
return $curdate . " " . sprintf( "%06d", $microsec );
}

sub sleep_until {
my $elapsed = tv_interval($_tstart);
if ( $_running_interval > $elapsed ) {
sleep( $_running_interval - $elapsed );
}
}

sub get_threads_util {
my $dbh = shift;
my $my_connection_id = shift;
my $running_time_threshold = shift;
my $type = shift;
$running_time_threshold = 0 unless ($running_time_threshold);
$type = 0 unless ($type);
my @threads;

my $sth = $dbh->prepare("SHOW PROCESSLIST");
$sth->execute();

while ( my $ref = $sth->fetchrow_hashref() ) {
my $id = $ref->{Id};
my $user = $ref->{User};
my $host = $ref->{Host};
my $command = $ref->{Command};
my $state = $ref->{State};
my $query_time = $ref->{Time};
my $info = $ref->{Info};
$info =~ s/^\s*(.*?)\s*$/$1/ if defined($info);
next if ( $my_connection_id == $id );
next if ( defined($query_time) && $query_time < $running_time_threshold );
next if ( defined($command) && $command eq "Binlog Dump" );
next if ( defined($user) && $user eq "system user" );
next
if ( defined($command)
&& $command eq "Sleep"
&& defined($query_time)
&& $query_time >= 1 );

if ( $type >= 1 ) {
next if ( defined($command) && $command eq "Sleep" );
next if ( defined($command) && $command eq "Connect" );
}

if ( $type >= 2 ) {
next if ( defined($info) && $info =~ m/^select/i );
next if ( defined($info) && $info =~ m/^show/i );
}

push @threads, $ref;
}
return @threads;
}

sub main {
if ( $command eq "stop" ) {
## Gracefully killing connections on the current master
# 1. Set read_only= 1 on the new master
# 2. DROP USER so that no app user can establish new connections
# 3. Set read_only= 1 on the current master
# 4. Kill current queries
# * Any database access failure will result in script die.
my $exit_code = 1;
eval {
## Setting read_only=1 on the new master (to avoid accident)
my $new_master_handler = new MHA::DBHelper();

# args: hostname, port, user, password, raise_error(die_on_error)_or_not
$new_master_handler->connect( $new_master_ip, $new_master_port,
"mhauser", "chengce243", 1 );
print current_time_us() . " Set read_only on the new master.. ";
$new_master_handler->enable_read_only();
if ( $new_master_handler->is_read_only() ) {
print "ok.\n";
}
else {
die "Failed!\n";
}
$new_master_handler->disconnect();

# Connecting to the orig master, die if any database error happens
my $orig_master_handler = new MHA::DBHelper();
$orig_master_handler->connect( $orig_master_ip, $orig_master_port,
$orig_master_user, $orig_master_password, 1 );

## Drop application user so that nobody can connect. Disabling per-session binlog beforehand
$orig_master_handler->disable_log_bin_local();
print current_time_us() . " Drpping app user on the orig master..\n";
#FIXME_xxx_drop_app_user($orig_master_handler);

## Waiting for N * 100 milliseconds so that current connections can exit
my $time_until_read_only = 15;
$_tstart = [gettimeofday];
my @threads = get_threads_util( $orig_master_handler->{dbh},
$orig_master_handler->{connection_id} );
while ( $time_until_read_only > 0 && $#threads >= 0 ) {
if ( $time_until_read_only % 5 == 0 ) {
printf
"%s Waiting all running %d threads are disconnected.. (max %d milliseconds)\n",
current_time_us(), $#threads + 1, $time_until_read_only * 100;
if ( $#threads < 5 ) {
print Data::Dumper->new( [$_] )->Indent(0)->Terse(1)->Dump . "\n"
foreach (@threads);
}
}
sleep_until();
$_tstart = [gettimeofday];
$time_until_read_only--;
@threads = get_threads_util( $orig_master_handler->{dbh},
$orig_master_handler->{connection_id} );
}

## Setting read_only=1 on the current master so that nobody(except SUPER) can write
print current_time_us() . " Set read_only=1 on the orig master.. ";
$orig_master_handler->enable_read_only();
if ( $orig_master_handler->is_read_only() ) {
print "ok.\n";
}
else {
die "Failed!\n";
}

## Waiting for M * 100 milliseconds so that current update queries can complete
my $time_until_kill_threads = 5;
@threads = get_threads_util( $orig_master_handler->{dbh},
$orig_master_handler->{connection_id} );
while ( $time_until_kill_threads > 0 && $#threads >= 0 ) {
if ( $time_until_kill_threads % 5 == 0 ) {
printf
"%s Waiting all running %d queries are disconnected.. (max %d milliseconds)\n",
current_time_us(), $#threads + 1, $time_until_kill_threads * 100;
if ( $#threads < 5 ) {
print Data::Dumper->new( [$_] )->Indent(0)->Terse(1)->Dump . "\n"
foreach (@threads);
}
}
sleep_until();
$_tstart = [gettimeofday];
$time_until_kill_threads--;
@threads = get_threads_util( $orig_master_handler->{dbh},
$orig_master_handler->{connection_id} );
}

## Terminating all threads
print current_time_us() . " Killing all application threads..\n";
$orig_master_handler->kill_threads(@threads) if ( $#threads >= 0 );
print current_time_us() . " done.\n";
$orig_master_handler->enable_log_bin_local();
$orig_master_handler->disconnect();

## After finishing the script, MHA executes FLUSH TABLES WITH READ LOCK
$exit_code = 0;
};
if ($@) {
warn "Got Error: $@\n";
exit $exit_code;
}
exit $exit_code;
}
elsif ( $command eq "start" ) {
## Activating master ip on the new master
# 1. Create app user with write privileges
# 2. Moving backup script if needed
# 3. Register new master's ip to the catalog database

# We don't return error even though activating updatable accounts/ip failed so that we don't interrupt slaves' recovery.
# If exit code is 0 or 10, MHA does not abort
my $exit_code = 10;
eval {
my $new_master_handler = new MHA::DBHelper();

# args: hostname, port, user, password, raise_error_or_not
$new_master_handler->connect( $new_master_ip, $new_master_port,
"mhauser", "chengce243", 1 );

## Set read_only=0 on the new master
$new_master_handler->disable_log_bin_local();
print current_time_us() . " Set read_only=0 on the new master.\n";
$new_master_handler->disable_read_only();

## Creating an app user on the new master
print current_time_us() . " Creating app user on the new master..\n";
#FIXME_xxx_create_app_user($new_master_handler);
$new_master_handler->enable_log_bin_local();
$new_master_handler->disconnect();

## Update master ip on the catalog database, etc
#`/usr/bin/ssh -t root\@${orig_master_ip} "service keepalived stop"`;
#`/usr/bin/ssh -t root\@${new_master_ip} "service keepalived start"`;
`/usr/bin/ssh -t root\@${orig_master_ip} "sh /data/script/do_vip_crontab.sh 1 0"`;
`/usr/bin/ssh -t root\@${new_master_ip} "sh /data/script/do_vip_crontab.sh 0 1"`;

$exit_code = 0;
};
if ($@) {
warn "Got Error: $@\n";
exit $exit_code;
}
exit $exit_code;
}
elsif ( $command eq "status" ) {

# do nothing
exit 0;
}
else {
&usage();
exit 1;
}
}

sub usage {
print
"Usage: master_ip_online_change --command=start|stop|status --orig_master_host=host --orig_master_ip=ip --orig_master_port=port --new_master_host=host --new_master_ip=ip --new_master_port=port\n";
die;
}

修改文件的权限：
chmod 755 /usr/bin/master_ip_online_change

MHA配置文件中打开对FAILOVER脚本的引用

[root@node4 ~]# cat /masterha_work/conf/masterha_consumer.cnf
[server default]
user=root
password=chengce243

ssh_user=root

master_binlog_dir=/data/mysql/3307/logs
remote_workdir=/masterha_work/rmt_mysql_binlog_workdir

repl_user=repl
repl_password=chengce243

master_ip_failover_script=/usr/bin/master_ip_failover
master_ip_online_change_script=/usr/bin/master_ip_online_change

ping_interval=30

manager_log=/masterha_work/log/manager_consumer.log

[server1]
hostname=192.168.56.26
port=3307

[server2]
hostname=192.168.56.27
candidate_master=1
check_repl_delay=0
port=3307

[server3]
hostname=192.168.56.28
port=3307
no_master=1

测试一下：
[root@node4 ~]# masterha_check_repl --conf=/masterha_work/conf/masterha_consumer.cnf
Fri Oct 6 22:16:34 2017 - [info] Reading default configuration from /etc/masterha_default.cnf..
Fri Oct 6 22:16:34 2017 - [info] Reading application default configuration from /masterha_work/conf/masterha_consumer.cnf..
Fri Oct 6 22:16:34 2017 - [info] Reading server configuration from /masterha_work/conf/masterha_consumer.cnf..
Fri Oct 6 22:16:34 2017 - [info] MHA::MasterMonitor version 0.56.
Fri Oct 6 22:16:34 2017 - [info] GTID failover mode = 0
Fri Oct 6 22:16:34 2017 - [info] Dead Servers:
Fri Oct 6 22:16:34 2017 - [info] Alive Servers:
Fri Oct 6 22:16:34 2017 - [info] 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 22:16:34 2017 - [info] 192.168.56.27(192.168.56.27:3307)
Fri Oct 6 22:16:34 2017 - [info] 192.168.56.28(192.168.56.28:3307)
Fri Oct 6 22:16:34 2017 - [info] Alive Slaves:
Fri Oct 6 22:16:34 2017 - [info] 192.168.56.27(192.168.56.27:3307) Version=5.6.34-log (oldest major version between slaves) log-bin:enabled
Fri Oct 6 22:16:34 2017 - [info] Replicating from 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 22:16:34 2017 - [info] Primary candidate for the new Master (candidate_master is set)
Fri Oct 6 22:16:34 2017 - [info] 192.168.56.28(192.168.56.28:3307) Version=5.6.34-log (oldest major version between slaves) log-bin:enabled
Fri Oct 6 22:16:34 2017 - [info] Replicating from 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 22:16:34 2017 - [info] Not candidate for the new Master (no_master is set)
Fri Oct 6 22:16:34 2017 - [info] Current Alive Master: 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 22:16:34 2017 - [info] Checking slave configurations..
Fri Oct 6 22:16:34 2017 - [info] read_only=1 is not set on slave 192.168.56.27(192.168.56.27:3307).
Fri Oct 6 22:16:34 2017 - [warning] relay_log_purge=0 is not set on slave 192.168.56.27(192.168.56.27:3307).
Fri Oct 6 22:16:34 2017 - [info] read_only=1 is not set on slave 192.168.56.28(192.168.56.28:3307).
Fri Oct 6 22:16:34 2017 - [warning] relay_log_purge=0 is not set on slave 192.168.56.28(192.168.56.28:3307).
Fri Oct 6 22:16:34 2017 - [info] Checking replication filtering settings..
Fri Oct 6 22:16:34 2017 - [info] binlog_do_db= , binlog_ignore_db=
Fri Oct 6 22:16:34 2017 - [info] Replication filtering check ok.
Fri Oct 6 22:16:34 2017 - [info] GTID (with auto-pos) is not supported
Fri Oct 6 22:16:34 2017 - [info] Starting SSH connection tests..
Fri Oct 6 22:16:36 2017 - [info] All SSH connection tests passed successfully.
Fri Oct 6 22:16:36 2017 - [info] Checking MHA Node version..
Fri Oct 6 22:16:37 2017 - [info] Version check ok.
Fri Oct 6 22:16:37 2017 - [info] Checking SSH publickey authentication settings on the current master..
Fri Oct 6 22:16:37 2017 - [info] HealthCheck: SSH to 192.168.56.26 is reachable.
Fri Oct 6 22:16:37 2017 - [info] Master MHA Node version is 0.56.
Fri Oct 6 22:16:37 2017 - [info] Checking recovery script configurations on 192.168.56.26(192.168.56.26:3307)..
Fri Oct 6 22:16:37 2017 - [info] Executing command: save_binary_logs --command=test --start_pos=4 --binlog_dir=/data/mysql/3307/logs --output_file=/masterha_work/rmt_mysql_binlog_workdir/save_binary_logs_test --manager_version=0.56 --start_file=mysql-bin.000003
Fri Oct 6 22:16:37 2017 - [info] Connecting to root@192.168.56.26(192.168.56.26:22)..
Creating /masterha_work/rmt_mysql_binlog_workdir if not exists.. ok.
Checking output directory is accessible or not..
ok.
Binlog found at /data/mysql/3307/logs, up to mysql-bin.000003
Fri Oct 6 22:16:37 2017 - [info] Binlog setting check done.
Fri Oct 6 22:16:37 2017 - [info] Checking SSH publickey authentication and checking recovery script configurations on all alive slave servers..
Fri Oct 6 22:16:37 2017 - [info] Executing command : apply_diff_relay_logs --command=test --slave_user='mhauser' --slave_host=192.168.56.27 --slave_ip=192.168.56.27 --slave_port=3307 --workdir=/masterha_work/rmt_mysql_binlog_workdir --target_version=5.6.34-log --manager_version=0.56 --relay_log_info=/data/mysql/3307/data/relay-log.info --relay_dir=/data/mysql/3307/data/ --slave_pass=xxx
Fri Oct 6 22:16:37 2017 - [info] Connecting to root@192.168.56.27(192.168.56.27:22)..
Checking slave recovery environment settings..
Opening /data/mysql/3307/data/relay-log.info ... ok.
Relay log found at /data/mysql/3307/data, up to relay-bin.000002
Temporary relay log file is /data/mysql/3307/data/relay-bin.000002
Testing mysql connection and privileges..Warning: Using a password on the command line interface can be insecure.
done.
Testing mysqlbinlog output.. done.
Cleaning up test file(s).. done.
Fri Oct 6 22:16:38 2017 - [info] Executing command : apply_diff_relay_logs --command=test --slave_user='mhauser' --slave_host=192.168.56.28 --slave_ip=192.168.56.28 --slave_port=3307 --workdir=/masterha_work/rmt_mysql_binlog_workdir --target_version=5.6.34-log --manager_version=0.56 --relay_log_info=/data/mysql/3307/data/relay-log.info --relay_dir=/data/mysql/3307/data/ --slave_pass=xxx
Fri Oct 6 22:16:38 2017 - [info] Connecting to root@192.168.56.28(192.168.56.28:22)..
Checking slave recovery environment settings..
Opening /data/mysql/3307/data/relay-log.info ... ok.
Relay log found at /data/mysql/3307/data, up to relay-bin.000002
Temporary relay log file is /data/mysql/3307/data/relay-bin.000002
Testing mysql connection and privileges..Warning: Using a password on the command line interface can be insecure.
done.
Testing mysqlbinlog output.. done.
Cleaning up test file(s).. done.
Fri Oct 6 22:16:38 2017 - [info] Slaves settings check done.
Fri Oct 6 22:16:38 2017 - [info]
192.168.56.26(192.168.56.26:3307) (current master)
+--192.168.56.27(192.168.56.27:3307)
+--192.168.56.28(192.168.56.28:3307)

Fri Oct 6 22:16:38 2017 - [info] Checking replication health on 192.168.56.27..
Fri Oct 6 22:16:38 2017 - [info] ok.
Fri Oct 6 22:16:38 2017 - [info] Checking replication health on 192.168.56.28..
Fri Oct 6 22:16:38 2017 - [info] ok.
Fri Oct 6 22:16:38 2017 - [info] Checking master_ip_failover_script status:
Fri Oct 6 22:16:38 2017 - [info] /usr/bin/master_ip_failover --command=status --ssh_user=root --orig_master_host=node1 --orig_master_ip=192.168.56.26 --orig_master_port=3307 --command=status --ssh_user=root --orig_master_host=192.168.56.26 --orig_master_ip=192.168.56.26 --orig_master_port=3307
Fri Oct 6 22:16:38 2017 - [info] OK.
Fri Oct 6 22:16:38 2017 - [warning] shutdown_script is not defined.
Fri Oct 6 22:16:38 2017 - [info] Got exit code 0 (Not master dead).

MySQL Replication Health is OK.

启动 mha守护进程

nohup masterha_manager --conf=/masterha_work/conf/masterha_consumer.cnf --ignore_last_failover > /tmp/mha_manager.log 2>&1&

node1、node2 上部署 do_vip_and_crontab.sh 脚本

[root@node1 ~]# cat /data/script/do_vip_crontab.sh
# file: do_vip_and_crontab.sh

# 职能：
# --> 1. 启动或停止：虚拟IP
# --> 2. 启用或禁用：crontab策略

# variable

# ---> 信号量
# 对于所有信号而言：
# 0，启用
# 1，禁用

#是否启用：VIP
#sign_vip=0
sign_vip="$1"

# 是否启用：crontab
#sign_crontab=0
sign_crontab="$2"

# 对于VIP而言
str_vip="192.168.56.206"
str_mask="255.255.255.0"
str_nic_name="eth0:0"

# 对于CRONTAB而言

# for RHEL6
# 如果是root用户，就会在：/var/spool/cron/root
file_crontab_dir="/var/spool/cron"
file_crontab_conf="$file_crontab_dir/mysql"

str_crontab_command="/bin/bash -x /data/script/run_commander.sh /data/script/backup.sh /data/script/mysql_auto_manage_binlog.sh > /dbbackup_idc/xtrabackup/consumer06/log/mysqlbackup.log 2>&1"
str_crontab_date="10 02 * * *"

str_crontab_command_sed=`echo "$str_crontab_command" | sed 's/\//\\\//g'`
str_crontab_date_sed=`echo "$str_crontab_date" | sed 's/*/\\\*/g'`

str_crontab_full="$str_crontab_date $str_crontab_command"
str_crontab_full_sed="$str_crontab_date_sed $str_crontab_command_sed"

str_block_crontab_content=`cat $file_crontab_conf | grep -v '#'`

# disable

echo "Crontab content:"
echo "$str_block_crontab_content"
echo ""

echo "var: str_crontab_date --> $str_crontab_date"
echo "var: str_crontab_command --> $str_crontab_command"
echo "--------------------------------------------"
echo "var: str_crontab_full --> $str_crontab_full"

echo ""

echo "var: str_crontab_date_sed --> $str_crontab_date_sed"
echo "var: str_crontab_command_sed --> $str_crontab_command_sed"
echo "--------------------------------------------"
echo "var: str_crontab_full_sed --> $str_crontab_full_sed"

echo ""

# running

if [ $sign_vip -eq "0" ]
then
echo "------------"
echo "VIP:: enable."
ifconfig $str_nic_name $str_vip netmask $str_mask up
echo ""
else
echo "------------"
echo "VIP:: disable."
ifconfig $str_nic_name $str_vip netmask $str_mask down
echo ""
fi

if [ $sign_crontab -eq "0" ]
then
echo "------------"
echo "CRONTAB:: enable."

if [[ $str_block_crontab_content =~ "$str_crontab_full" ]]
then
echo "CRONTAB Policy is in [$file_crontab_conf]"

else
echo "CRONTAB Policy is not in [$file_crontab_conf]"
echo "Put it in, ..."
echo "$str_crontab_full" >> $file_crontab_conf
echo "Done."
fi

echo ""
else
echo "------------"
echo "CRONTAB:: disable."

if [[ $str_block_crontab_content =~"$str_crontab_full" ]]
then
echo "CRONTAB Policy is in [$file_crontab_conf]"
echo "change it, ..."
sed -i "s/$str_crontab_full_sed/#$str_crontab_full_sed/g" $file_crontab_conf
echo "Done."

else
echo "CRONTAB Policy is not in [$file_crontab_conf]"

fi

echo ""
fi

# Finished

在node4上部署 call_do_mha.sh 脚本

[root@node4 script_dir]# cat /masterha_work/script_dir/call_do_mha.sh
# name: call_do_mha.sh

#variables

str_mha_app=$1

while [ true ]
do
sh /masterha_work/script_dir/do_mha.sh $str_mha_app
sleep 5
done

在node4上部署 do_mha.sh 脚本

[root@node4 ~]# cat /masterha_work/script_dir/do_mha.sh
#!/bin/bash
# Script
# Name: do_mha.sh
# APP vendor: MHA
# Linux vendor: RHEL / CentOS

# Author: leochen

# --------------------------
# variable and file path

# Part:: this script
str_mha_application=$1

# Part:: Linux
# Account info
str_linux_username="root"

# Part:: MySQL
# Account info
str_mysql_username="root"
str_mysql_password="chengce243"

str_repl_username="repl"
str_repl_password="chengce243"

# Part:: MHA
# pid
#str_pid_masterha_manager=`ps -ef | grep masterha_manager | grep perl | awk '{print $2}'`

str_pid_masterha_manager=`ps -ef | grep masterha_manager | grep "$str_mha_application" | grep perl | awk '{print $2}'`

# file
file_conf_mha_application="/masterha_work/conf/$str_mha_application.cnf"

# file: relation / by computed
file_log_mha_manager=`cat $file_conf_mha_application | grep --color manager_log | cut -d'=' -f2`

# variable: ip info
# 如果MHA中MySQL主库的候选服务器数量超过了两台，也许下面这个list参数，就会排上用场
list_ip_candicate=`cat $file_conf_mha_application | grep -B 2 "^candidate" | grep "hostname" | cut -d'=' -f2`

str_ip_orig_master=`cat $file_log_mha_manager | grep --color "MySQL Master failover" | cut -d'(' -f2 | cut -d':' -f1 | tail -n 1`
str_ip_new_master=`cat $file_log_mha_manager | grep --color "MySQL Master failover" | cut -d'(' -f3 | cut -d':' -f1 | tail -n 1`

str_ip_mha_manager="10.158.1.94"

# 为[change master]准备的参数
str_log_file_new_master=""
str_log_pos_new_master=""

# Part:: String SQL
str_sql_mysql_change_master=""

# --------------------------
# function

function do_sql() {
# variable
func_str_ip="$1"
func_str_sql="$2"

# action
# 本场景中不涉及到对MySQL某个库的操作，所以没有选择[db]
# mysql -u $user -p"$password" $db -N -e "$f_sql_str"
mysql -u $str_mysql_username -h $func_str_ip -p"$str_mysql_password" -N -e "$func_str_sql" -P3307
}

# 获取主库状态信息
#function get_info_mysql_master_new_master() {
# version ONE
#str_log_file_new_master=`do_sql "$str_ip_new_master" "show master status" | awk '{print $1}'`
#str_log_pos_new_master=`do_sql "$str_ip_new_master" "show master status" | awk '{print $2}'`

#}

# 生成orig_master作为slave加入new_master的[change master]SQL命令
function gen_sql_mysql_change_master() {
#if [[ "$str_log_file_new_master" == "" || $str_log_pos_new_master == "" ]]
#then
# get_info_mysql_master_new_master
#fi
#str_sql_mysql_change_master="CHANGE MASTER TO MASTER_HOST='$str_ip_new_master',MASTER_USER='$str_repl_username',MASTER_PASSWORD='$str_repl_password',MASTER_LOG_FILE='$str_log_file_new_master',MASTER_LOG_POS=$str_log_pos_new_master;"

# version TWO
func_temp_master_host_sed=`cat $file_log_mha_manager | grep --color "All other slaves should start" | tail -n 1 | cut -d',' -f1 | cut -d'=' -f2 | cut -d\' -f2`
func_temp_repl_password_sed=`cat $file_log_mha_manager | grep --color "All other slaves should start" | tail -n 1 | rev | cut -d\' -f2`

echo "======================"
echo "@@ func variable: func_temp_repl_password_sed = $func_temp_repl_password_sed"
echo "======================"
str_sql_mysql_change_master=`cat $file_log_mha_manager | grep --color "All other slaves should start" | tail -n 1 | sed "s#${func_temp_repl_password_sed}#${str_repl_password}#g" | cut -d':' -f4`
str_sql_mysql_change_master=`echo $str_sql_mysql_change_master | sed "s#${func_temp_master_host_sed}#${str_ip_new_master}#g"`
}

# 对指定主机执行Linux命令
# 前提：
# 1. IP可达
# 2. SSH等价关系
function do_linux_by_ssh() {
# variable
func_str_ip="$1"
func_str_user="$2"
func_str_command="$3"

# action
# ssh -t $func_str_user@$func_str_ip "$func_str_command"
ssh -t -t $func_str_user@$func_str_ip "$func_str_command"
}

# 处理VIP的事宜
function do_part_vip() {
do_linux_by_ssh "$str_ip_new_master" "root" "service keepalived start"
do_linux_by_ssh "$str_ip_orig_master" "root" "service keepalived stop"
}

function do_part_orig_master_is_new_slave() {
do_linux_by_ssh "$str_ip_orig_master" "root" "service mysqld start"
do_sql "$str_ip_orig_master" "set global read_only=1;"
do_sql "$str_ip_orig_master" "$str_sql_mysql_change_master"
do_sql "$str_ip_orig_master" "start slave;"
}

function do_part_mha_master_manager_start() {
do_linux_by_ssh "$str_ip_mha_manager" "root" "nohup masterha_manager --conf=$file_conf_mha_application --ignore_last_failover &"
}

# 如果PID不存在，则执行该脚本，否则，退出
function runable_by_mha_manager_pid() {
echo "-----------------"
echo "Script for MySQL Master HA"
echo "-----------------"
echo "Begin:: "`date "+|%Y-%m-%d|%H:%M:%S|"`

if [[ "$str_pid_masterha_manager" == "" ]]
then
echo "## masterha_manager is [NOT ALIVED]."
else
echo "## masterha_manager is [ALIVED]."
echo "[masterha_manager] PID is:: $str_pid_masterha_manager"

# do something.
echo "## Exit Script"
exit 0
fi
}

# --------------------------
# action

# 如果PID不存在，则执行该脚本，否则，退出
echo "------------------"
echo "app: runable_by_mha_manager_pid"
runable_by_mha_manager_pid
echo ""

echo "------------------"
echo "app: gen_sql_mysql_change_master"
gen_sql_mysql_change_master
echo ""
#echo "------------------"
#echo "app: do_part_vip"
#do_part_vip
#echo ""

echo "------------------"
echo "app: do_part_orig_master_is_new_slave"
do_part_orig_master_is_new_slave
echo ""

echo "------------------"
echo "app: do_part_mha_master_manager_start"
#do_part_mha_master_manager_start
nohup masterha_manager --conf=$file_conf_mha_application --ignore_last_failover &
echo ""

# --------------------------
# Show time

# ---------
# version one
# ---------
#echo "new master is:: $str_ip_new_master"
#echo "Master log file is:: $str_log_file_new_master"
#echo "Master log POS is:: $str_log_pos_new_master"
#echo "orig master --> new master ## SQL: CHANGE MASTER ## is:: $str_sql_mysql_change_master"

# ---------
# version two
# ---------
echo "================="
echo "MySQL info:"

echo "## Account and Password"
echo "username @ $str_mysql_username"
echo "password @ $str_mysql_password"
echo "--- for REPLICATION ---"
echo "repl @ username ## $str_repl_username"
echo "repl @ password ## $str_repl_password"
echo "## Master Server info"
echo "log file @ Master ## $str_log_file_new_master"
echo "log pos @ Master ## $str_log_pos_new_master"
echo ""

echo "================="
echo "SQL statement:"
echo "[CHANGE MASTER] -->"
echo "$str_sql_mysql_change_master"
echo ""

echo "================="
echo "MasterHA info:"

echo "## File and Path"
echo "MHA Global config file @ $file_conf_mha_global"
echo "MHA Application config file @ $file_conf_mha_application"
echo "MHA Log file:: masterha_manager @ $file_log_mha_manager"

echo "## Architecture"
echo "Candicate Server list::"
echo "$list_ip_candicate"

echo "## IP"
echo "MHA Manager Server:: $str_ip_mha_manager"
echo "Last:: new master:: $str_ip_new_master"
echo "Last:: orig master:: $str_ip_orig_master"
echo ""

# --------------------------
echo "-----------------"
echo "Finished:: "`date "+|%Y-%m-%d|%H:%M:%S|"`
# Done

启动 call_do_mha.sh 脚本

nohup sh /masterha_work/script_dir/call_do_mha.sh masterha_consumer &