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;
配置root用户互信
在 node1 节点生成互信文件，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 conf]# masterha_check_ssh --conf=/masterha_work/conf/mha_total.cnf
Sun Oct 1 19:07:20 2017 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Sun Oct 1 19:07:20 2017 - [info] Reading application default configuration from /masterha_work/conf/mha_total.cnf..
Sun Oct 1 19:07:20 2017 - [info] Reading server configuration from /masterha_work/conf/mha_total.cnf..
Sun Oct 1 19:07:20 2017 - [info] Starting SSH connection tests..
Sun Oct 1 19:07:21 2017 - [debug]
Sun Oct 1 19:07:20 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)..
Sun Oct 1 19:07:20 2017 - [debug] ok.
Sun Oct 1 19:07:20 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)..
Sun Oct 1 19:07:21 2017 - [debug] ok.
Sun Oct 1 19:07:21 2017 - [debug]
Sun Oct 1 19:07:20 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)..
Sun Oct 1 19:07:21 2017 - [debug] ok.
Sun Oct 1 19:07:21 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)..
Sun Oct 1 19:07:21 2017 - [debug] ok.
Sun Oct 1 19:07:22 2017 - [debug]
Sun Oct 1 19:07:21 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)..
Sun Oct 1 19:07:21 2017 - [debug] ok.
Sun Oct 1 19:07:21 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)..
Sun Oct 1 19:07:22 2017 - [debug] ok.
Sun Oct 1 19:07:22 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 13:28:22 2017 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Fri Oct 6 13:28:22 2017 - [info] Reading application default configuration from /masterha_work/conf/mha_total.cnf..
Fri Oct 6 13:28:22 2017 - [info] Reading server configuration from /masterha_work/conf/mha_total.cnf..
Fri Oct 6 13:28:22 2017 - [info] MHA::MasterMonitor version 0.56.
Fri Oct 6 13:28:22 2017 - [info] GTID failover mode = 0
Fri Oct 6 13:28:22 2017 - [info] Dead Servers:
Fri Oct 6 13:28:22 2017 - [info] Alive Servers:
Fri Oct 6 13:28:22 2017 - [info] 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 13:28:22 2017 - [info] 192.168.56.27(192.168.56.27:3307)
Fri Oct 6 13:28:22 2017 - [info] 192.168.56.28(192.168.56.28:3307)
Fri Oct 6 13:28:22 2017 - [info] Alive Slaves:
Fri Oct 6 13:28:22 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 13:28:22 2017 - [info] Replicating from 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 13:28:22 2017 - [info] Primary candidate for the new Master (candidate_master is set)
Fri Oct 6 13:28:22 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 13:28:22 2017 - [info] Replicating from 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 13:28:22 2017 - [info] Not candidate for the new Master (no_master is set)
Fri Oct 6 13:28:22 2017 - [info] Current Alive Master: 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 13:28:22 2017 - [info] Checking slave configurations..
Fri Oct 6 13:28:22 2017 - [info] read_only=1 is not set on slave 192.168.56.27(192.168.56.27:3307).
Fri Oct 6 13:28:22 2017 - [warning] relay_log_purge=0 is not set on slave 192.168.56.27(192.168.56.27:3307).
Fri Oct 6 13:28:22 2017 - [info] read_only=1 is not set on slave 192.168.56.28(192.168.56.28:3307).
Fri Oct 6 13:28:22 2017 - [warning] relay_log_purge=0 is not set on slave 192.168.56.28(192.168.56.28:3307).
Fri Oct 6 13:28:22 2017 - [info] Checking replication filtering settings..
Fri Oct 6 13:28:22 2017 - [info] binlog_do_db= , binlog_ignore_db=
Fri Oct 6 13:28:22 2017 - [info] Replication filtering check ok.
Fri Oct 6 13:28:22 2017 - [info] GTID (with auto-pos) is not supported
Fri Oct 6 13:28:22 2017 - [info] Starting SSH connection tests..
Fri Oct 6 13:28:25 2017 - [info] All SSH connection tests passed successfully.
Fri Oct 6 13:28:25 2017 - [info] Checking MHA Node version..
Fri Oct 6 13:28:25 2017 - [info] Version check ok.
Fri Oct 6 13:28:25 2017 - [info] Checking SSH publickey authentication settings on the current master..
Fri Oct 6 13:28:25 2017 - [info] HealthCheck: SSH to 192.168.56.26 is reachable.
Fri Oct 6 13:28:26 2017 - [info] Master MHA Node version is 0.56.
Fri Oct 6 13:28:26 2017 - [info] Checking recovery script configurations on 192.168.56.26(192.168.56.26:3307)..
Fri Oct 6 13:28:26 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 13:28:26 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 13:28:26 2017 - [info] Binlog setting check done.
Fri Oct 6 13:28:26 2017 - [info] Checking SSH publickey authentication and checking recovery script configurations on all alive slave servers..
Fri Oct 6 13:28:26 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 13:28:26 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 13:28:26 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 13:28:26 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 13:28:27 2017 - [info] Slaves settings check done.
Fri Oct 6 13:28:27 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 13:28:27 2017 - [info] Checking replication health on 192.168.56.27..
Fri Oct 6 13:28:27 2017 - [info] ok.
Fri Oct 6 13:28:27 2017 - [info] Checking replication health on 192.168.56.28..
Fri Oct 6 13:28:27 2017 - [info] ok.
Fri Oct 6 13:28:27 2017 - [warning] master_ip_failover_script is not defined.
Fri Oct 6 13:28:27 2017 - [warning] shutdown_script is not defined.
Fri Oct 6 13:28:27 2017 - [info] Got exit code 0 (Not master dead).
MySQL Replication Health is OK.
安装Keepalived：
在两台候选主机节点上安装，即：node1和node2
配置文件【/etc/keepalived/keepalived.conf】
该配置文件中包含LVS的配置，在当前的环境中，没有包含LVS，可以删除或者注释LVS部分的配置信息。
配置好的配置文件：
【node1】
[root@node1 ~]# cat /etc/keepalived/keepalived.conf
! Configuration File for keepalived
global_defs {
router_id LVS_node1
}
vrrp_instance VI_21 {
state MASTER
interface eth0
virtual_router_id 21
priority 93
advert_int 1
authentication {
auth_type PASS
auth_pass 1111
}
virtual_ipaddress {
192.168.56.206/24
}
}
【node2】
[root@node2 ~]# cat /etc/keepalived/keepalived.conf
! Configuration File for keepalived
global_defs {
router_id LVS_node2
}
vrrp_instance VI_21 {
state MASTER
interface eth0
virtual_router_id 21
priority 90
advert_int 1
authentication {
auth_type PASS
auth_pass 1111
}
virtual_ipaddress {
192.168.56.206/24
}
}
在上述配置文件中【priority】代表权重，数值最大的，才是Master。
启动keepalived
[root@node1 ~]# /etc/init.d/keepalived start
Starting keepalived: [ OK ]
观察IP情况：
[root@node1 ~]# ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 16436 qdisc noqueue state UNKNOWN
link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
inet 127.0.0.1/8 scope host lo
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000
link/ether 08:00:27:68:5f:50 brd ff:ff:ff:ff:ff:ff
inet 192.168.56.26/24 brd 192.168.56.255 scope global eth0
inet 192.168.56.206/24 scope global secondary eth0
inet6 fe80::a00:27ff:fe68:5f50/64 scope link
valid_lft forever preferred_lft forever
[root@node2 ~]# /etc/init.d/keepalived start
Starting keepalived: [ OK ]
[root@node2 ~]# ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 16436 qdisc noqueue state UNKNOWN
link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
inet 127.0.0.1/8 scope host lo
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000
link/ether 08:00:27:7c:8a:78 brd ff:ff:ff:ff:ff:ff
inet 192.168.56.27/24 brd 192.168.56.255 scope global eth0
inet6 fe80::a00:27ff:fe7c:8a78/64 scope link
valid_lft forever preferred_lft forever
node1把keepalived 停掉
[root@node1 ~]# /etc/init.d/keepalived stop
Stopping keepalived: [ OK ]
[root@node1 ~]# ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 16436 qdisc noqueue state UNKNOWN
link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
inet 127.0.0.1/8 scope host lo
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000
link/ether 08:00:27:68:5f:50 brd ff:ff:ff:ff:ff:ff
inet 192.168.56.26/24 brd 192.168.56.255 scope global eth0
inet6 fe80::a00:27ff:fe68:5f50/64 scope link
valid_lft forever preferred_lft forever
观察node2情况
[root@node2 ~]# ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 16436 qdisc noqueue state UNKNOWN
link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
inet 127.0.0.1/8 scope host lo
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000
link/ether 08:00:27:7c:8a:78 brd ff:ff:ff:ff:ff:ff
inet 192.168.56.27/24 brd 192.168.56.255 scope global eth0
inet 192.168.56.206/24 scope global secondary eth0
inet6 fe80::a00:27ff:fe7c:8a78/64 scope link
valid_lft forever preferred_lft forever
再启node1，再观察
[root@node1 ~]# ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 16436 qdisc noqueue state UNKNOWN
link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
inet 127.0.0.1/8 scope host lo
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000
link/ether 08:00:27:68:5f:50 brd ff:ff:ff:ff:ff:ff
inet 192.168.56.26/24 brd 192.168.56.255 scope global eth0
inet 192.168.56.206/24 scope global secondary eth0
inet6 fe80::a00:27ff:fe68:5f50/64 scope link
valid_lft forever preferred_lft forever
已达到预期效果。
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..
";
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..
";
#FIXME_xxx_create_user( $new_master_handler->{dbh} );
$new_master_handler->enable_log_bin_local();
$new_master_handler->disconnect();
## Update master ip on the catalog database, etc
#FIXME_xxx;
在 FIXME_xxx 后面增加对keepalived 停止命令的调用：
`/usr/bin/ssh -t root@${orig_master_ip} "/etc/init.d/keepalived stop"`;
注意，一定要用【;】结尾，否则脚本执行会出错。
修改 new_master_handler ：
# 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 );
数据库中 mhauser 的用户名与密码。
修改后 master_ip_failover 脚本如下：
[root@node4 bin]# 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: $@
";
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,
# $new_master_user, $new_master_password, 1 );
$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.
";
$new_master_handler->disable_read_only();
## Creating an app user on the new master
print "Creating app user on the new master..
";
#FIXME_xxx_create_user( $new_master_handler->{dbh} );
$new_master_handler->enable_log_bin_local();
$new_master_handler->disconnect();
## Update master ip on the catalog database, etc
#FIXME_xxx;
`/usr/bin/ssh -t root@${orig_master_ip} "/etc/init.d/keepalived stop"`;
$exit_code = 0;
};
if ($@) {
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
";
}
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
$orig_master_handler->disable_log_bin_local();
print current_time_us() . " Drpping app user on the orig master..
";
FIXME_xxx_drop_app_user($orig_master_handler);
修改如下：
## Drop application user so that nobody can connect. Disabling per-session binlog beforehand
$orig_master_handler->disable_log_bin_local();
print current_time_us() . " Drpping app user on the orig master..
";
#FIXME_xxx_drop_app_user($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..
";
FIXME_xxx_create_app_user($new_master_handler);
$new_master_handler->enable_log_bin_local();
$new_master_handler->disconnect();
修改如下：
## Creating an app user on the new master
print current_time_us() . " Creating app user on the new master..
";
#FIXME_xxx_create_app_user($new_master_handler);
$new_master_handler->enable_log_bin_local();
$new_master_handler->disconnect();
需要注册发 mhauser 用户的位置：
位置一：
# args: hostname, port, user, password, raise_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(die_on_error)_or_not
$new_master_handler->connect( $new_master_ip, $new_master_port,
'mhauser', 'chengce243', 1 );
位置三：
$orig_master_handler->connect( $orig_master_ip, $orig_master_port,
'mhauser', 'chengce243', 1 );
增加对keepalived的调用：
`/usr/bin/ssh -t root@${orig_master_ip} "/etc/init.d/keepalived stop"`;
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.
";
}
else {
die "Failed!
";
}
$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,
'mhauser', 'chengce243', 1 );
## Drop application user so that nobody can connect. Disabling per-session binlog beforehand
$orig_master_handler->disable_log_bin_local();
print current_time_us() . " Drpping app user on the orig master..
";
#FIXME_xxx_drop_app_user($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)
",
current_time_us(), $#threads + 1, $time_until_read_only * 100;
if ( $#threads < 5 ) {
print Data::Dumper->new( [$_] )->Indent(0)->Terse(1)->Dump . "
"
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.
";
}
else {
die "Failed!
";
}
## 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)
",
current_time_us(), $#threads + 1, $time_until_kill_threads * 100;
if ( $#threads < 5 ) {
print Data::Dumper->new( [$_] )->Indent(0)->Terse(1)->Dump . "
"
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..
";
$orig_master_handler->kill_threads(@threads) if ( $#threads >= 0 );
print current_time_us() . " done.
";
$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: $@
";
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.
";
$new_master_handler->disable_read_only();
## Creating an app user on the new master
print current_time_us() . " Creating app user on the new master..
";
#FIXME_xxx_create_app_user($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} "/etc/init.d/keepalived stop"`;
$exit_code = 0;
};
if ($@) {
warn "Got Error: $@
";
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
";
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/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
测试一下：
[root@node4 ~]# masterha_check_repl --conf=/masterha_work/conf/mha_total.cnf
Fri Oct 6 16:05:03 2017 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Fri Oct 6 16:05:03 2017 - [info] Reading application default configuration from /masterha_work/conf/mha_total.cnf..
Fri Oct 6 16:05:03 2017 - [info] Reading server configuration from /masterha_work/conf/mha_total.cnf..
Fri Oct 6 16:05:03 2017 - [info] MHA::MasterMonitor version 0.56.
Fri Oct 6 16:05:03 2017 - [info] GTID failover mode = 0
Fri Oct 6 16:05:03 2017 - [info] Dead Servers:
Fri Oct 6 16:05:03 2017 - [info] Alive Servers:
Fri Oct 6 16:05:03 2017 - [info] 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 16:05:03 2017 - [info] 192.168.56.27(192.168.56.27:3307)
Fri Oct 6 16:05:03 2017 - [info] 192.168.56.28(192.168.56.28:3307)
Fri Oct 6 16:05:03 2017 - [info] Alive Slaves:
Fri Oct 6 16:05:03 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 16:05:03 2017 - [info] Replicating from 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 16:05:03 2017 - [info] Primary candidate for the new Master (candidate_master is set)
Fri Oct 6 16:05:03 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 16:05:03 2017 - [info] Replicating from 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 16:05:03 2017 - [info] Not candidate for the new Master (no_master is set)
Fri Oct 6 16:05:03 2017 - [info] Current Alive Master: 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 16:05:03 2017 - [info] Checking slave configurations..
Fri Oct 6 16:05:03 2017 - [info] read_only=1 is not set on slave 192.168.56.27(192.168.56.27:3307).
Fri Oct 6 16:05:03 2017 - [warning] relay_log_purge=0 is not set on slave 192.168.56.27(192.168.56.27:3307).
Fri Oct 6 16:05:03 2017 - [info] read_only=1 is not set on slave 192.168.56.28(192.168.56.28:3307).
Fri Oct 6 16:05:03 2017 - [warning] relay_log_purge=0 is not set on slave 192.168.56.28(192.168.56.28:3307).
Fri Oct 6 16:05:03 2017 - [info] Checking replication filtering settings..
Fri Oct 6 16:05:03 2017 - [info] binlog_do_db= , binlog_ignore_db=
Fri Oct 6 16:05:03 2017 - [info] Replication filtering check ok.
Fri Oct 6 16:05:03 2017 - [info] GTID (with auto-pos) is not supported
Fri Oct 6 16:05:03 2017 - [info] Starting SSH connection tests..
Fri Oct 6 16:05:05 2017 - [info] All SSH connection tests passed successfully.
Fri Oct 6 16:05:05 2017 - [info] Checking MHA Node version..
Fri Oct 6 16:05:06 2017 - [info] Version check ok.
Fri Oct 6 16:05:06 2017 - [info] Checking SSH publickey authentication settings on the current master..
Fri Oct 6 16:05:06 2017 - [info] HealthCheck: SSH to 192.168.56.26 is reachable.
Fri Oct 6 16:05:06 2017 - [info] Master MHA Node version is 0.56.
Fri Oct 6 16:05:06 2017 - [info] Checking recovery script configurations on 192.168.56.26(192.168.56.26:3307)..
Fri Oct 6 16:05:06 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 16:05:06 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 16:05:07 2017 - [info] Binlog setting check done.
Fri Oct 6 16:05:07 2017 - [info] Checking SSH publickey authentication and checking recovery script configurations on all alive slave servers..
Fri Oct 6 16:05:07 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 16:05:07 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 16:05:07 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 16:05:07 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 16:05:08 2017 - [info] Slaves settings check done.
Fri Oct 6 16:05:08 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 16:05:08 2017 - [info] Checking replication health on 192.168.56.27..
Fri Oct 6 16:05:08 2017 - [info] ok.
Fri Oct 6 16:05:08 2017 - [info] Checking replication health on 192.168.56.28..
Fri Oct 6 16:05:08 2017 - [info] ok.
Fri Oct 6 16:05:08 2017 - [info] Checking master_ip_failover_script status:
Fri Oct 6 16:05:08 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 16:05:08 2017 - [info] OK.
Fri Oct 6 16:05:08 2017 - [warning] shutdown_script is not defined.
Fri Oct 6 16:05:08 2017 - [info] Got exit code 0 (Not master dead).
MySQL Replication Health is OK.
手动执行在线切换：
切换前：
node1的IP：
[root@node1 ~]# ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 16436 qdisc noqueue state UNKNOWN
link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
inet 127.0.0.1/8 scope host lo
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000
link/ether 08:00:27:68:5f:50 brd ff:ff:ff:ff:ff:ff
inet 192.168.56.26/24 brd 192.168.56.255 scope global eth0
inet 192.168.56.206/24 scope global secondary eth0
inet6 fe80::a00:27ff:fe68:5f50/64 scope link
valid_lft forever preferred_lft forever
node3的从库状态：
[root@node3 ~]# mysql -uroot -pchengce243 -P3307
Warning: Using a password on the command line interface can be insecure.
Welcome to the MySQL monitor. Commands end with ; or g.
Your MySQL connection id is 21
Server version: 5.6.34-log MySQL Community Server (GPL)
Copyright (c) 2000, 2016, Oracle and/or its affiliates. All rights reserved.
Oracle is a registered trademark of Oracle Corporation and/or its
affiliates. Other names may be trademarks of their respective
owners.
Type 'help;' or 'h' for help. Type 'c' to clear the current input statement.
mysql> show slave status G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 192.168.56.26
Master_User: repl
Master_Port: 3307
Connect_Retry: 60
Master_Log_File: mysql-bin.000003
Read_Master_Log_Pos: 2759
Relay_Log_File: relay-bin.000002
Relay_Log_Pos: 1324
Relay_Master_Log_File: mysql-bin.000003
Slave_IO_Running: Yes
Slave_SQL_Running: Yes
Replicate_Do_DB:
Replicate_Ignore_DB:
Replicate_Do_Table:
Replicate_Ignore_Table:
Replicate_Wild_Do_Table:
Replicate_Wild_Ignore_Table:
Last_Errno: 0
Last_Error:
Skip_Counter: 0
Exec_Master_Log_Pos: 2759
Relay_Log_Space: 1491
Until_Condition: None
Until_Log_File:
Until_Log_Pos: 0
Master_SSL_Allowed: No
Master_SSL_CA_File:
Master_SSL_CA_Path:
Master_SSL_Cert:
Master_SSL_Cipher:
Master_SSL_Key:
Seconds_Behind_Master: 0
Master_SSL_Verify_Server_Cert: No
Last_IO_Errno: 0
Last_IO_Error:
Last_SQL_Errno: 0
Last_SQL_Error:
Replicate_Ignore_Server_Ids:
Master_Server_Id: 330726
Master_UUID: 336d78f5-a9d1-11e7-ab8a-080027685f50
Master_Info_File: /data/mysql/3307/data/master.info
SQL_Delay: 0
SQL_Remaining_Delay: NULL
Slave_SQL_Running_State: Slave has read all relay log; waiting for the slave I/O thread to update it
Master_Retry_Count: 86400
Master_Bind:
Last_IO_Error_Timestamp:
Last_SQL_Error_Timestamp:
Master_SSL_Crl:
Master_SSL_Crlpath:
Retrieved_Gtid_Set:
Executed_Gtid_Set:
Auto_Position: 0
1 row in set (0.00 sec)
执行切换命令：
首先应该停止MHA：
[root@node4 ~]# masterha_stop --conf=/masterha_work/conf/mha_total.cnf
[root@node4 ~]# masterha_master_switch --master_state=alive --conf=/masterha_work/conf/mha_total.cnf
Fri Oct 6 16:09:39 2017 - [info] MHA::MasterRotate version 0.56.
Fri Oct 6 16:09:39 2017 - [info] Starting online master switch..
Fri Oct 6 16:09:39 2017 - [info]
Fri Oct 6 16:09:39 2017 - [info] * Phase 1: Configuration Check Phase..
Fri Oct 6 16:09:39 2017 - [info]
Fri Oct 6 16:09:39 2017 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping.
Fri Oct 6 16:09:39 2017 - [info] Reading application default configuration from /masterha_work/conf/mha_total.cnf..
Fri Oct 6 16:09:39 2017 - [info] Reading server configuration from /masterha_work/conf/mha_total.cnf..
Fri Oct 6 16:09:39 2017 - [info] GTID failover mode = 0
Fri Oct 6 16:09:39 2017 - [info] Current Alive Master: 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 16:09:39 2017 - [info] Alive Slaves:
Fri Oct 6 16:09:39 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 16:09:39 2017 - [info] Replicating from 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 16:09:39 2017 - [info] Primary candidate for the new Master (candidate_master is set)
Fri Oct 6 16:09:39 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 16:09:39 2017 - [info] Replicating from 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 16:09:39 2017 - [info] Not candidate for the new Master (no_master is set)
It is better to execute FLUSH NO_WRITE_TO_BINLOG TABLES on the master before switching. Is it ok to execute on 192.168.56.26(192.168.56.26:3307)? (YES/no): yes
Fri Oct 6 16:10:08 2017 - [info] Executing FLUSH NO_WRITE_TO_BINLOG TABLES. This may take long time..
Fri Oct 6 16:10:08 2017 - [info] ok.
Fri Oct 6 16:10:08 2017 - [info] Checking MHA is not monitoring or doing failover..
Fri Oct 6 16:10:09 2017 - [info] Checking replication health on 192.168.56.27..
Fri Oct 6 16:10:09 2017 - [info] ok.
Fri Oct 6 16:10:09 2017 - [info] Checking replication health on 192.168.56.28..
Fri Oct 6 16:10:09 2017 - [info] ok.
Fri Oct 6 16:10:09 2017 - [info] Searching new master from slaves..
Fri Oct 6 16:10:09 2017 - [info] Candidate masters from the configuration file:
Fri Oct 6 16:10:09 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 16:10:09 2017 - [info] Replicating from 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 16:10:09 2017 - [info] Primary candidate for the new Master (candidate_master is set)
Fri Oct 6 16:10:09 2017 - [info] Non-candidate masters:
Fri Oct 6 16:10:09 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 16:10:09 2017 - [info] Replicating from 192.168.56.26(192.168.56.26:3307)
Fri Oct 6 16:10:09 2017 - [info] Not candidate for the new Master (no_master is set)
Fri Oct 6 16:10:09 2017 - [info] Searching from candidate_master slaves which have received the latest relay log events..
Fri Oct 6 16:10:09 2017 - [info]
From:
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)
To:
192.168.56.27(192.168.56.27:3307) (new master)
+--192.168.56.28(192.168.56.28:3307)
Starting master switch from 192.168.56.26(192.168.56.26:3307) to 192.168.56.27(192.168.56.27:3307)? (yes/NO): yes
Fri Oct 6 16:10:10 2017 - [info] Checking whether 192.168.56.27(192.168.56.27:3307) is ok for the new master..
Fri Oct 6 16:10:10 2017 - [info] ok.
Fri Oct 6 16:10:10 2017 - [info] ** Phase 1: Configuration Check Phase completed.
Fri Oct 6 16:10:10 2017 - [info]
Fri Oct 6 16:10:10 2017 - [info] * Phase 2: Rejecting updates Phase..
Fri Oct 6 16:10:10 2017 - [info]
Fri Oct 6 16:10:10 2017 - [info] Executing master ip online change script to disable write on the current master:
Fri Oct 6 16:10:10 2017 - [info] /usr/bin/master_ip_online_change --command=stop --orig_master_host=192.168.56.26 --orig_master_ip=192.168.56.26 --orig_master_port=3307 --orig_master_user='mhauser' --orig_master_password='chengce243' --new_master_host=192.168.56.27 --new_master_ip=192.168.56.27 --new_master_port=3307 --new_master_user='mhauser' --new_master_password='chengce243' --orig_master_ssh_user=root --new_master_ssh_user=root
Fri Oct 6 16:10:10 2017 856828 Set read_only on the new master.. ok.
Fri Oct 6 16:10:10 2017 898583 Drpping app user on the orig master..
Fri Oct 6 16:10:10 2017 900126 Set read_only=1 on the orig master.. ok.
Fri Oct 6 16:10:10 2017 923958 Killing all application threads..
Fri Oct 6 16:10:10 2017 924002 done.
Fri Oct 6 16:10:10 2017 - [info] ok.
Fri Oct 6 16:10:10 2017 - [info] Locking all tables on the orig master to reject updates from everybody (including root):
Fri Oct 6 16:10:10 2017 - [info] Executing FLUSH TABLES WITH READ LOCK..
Fri Oct 6 16:10:10 2017 - [info] ok.
Fri Oct 6 16:10:10 2017 - [info] Orig master binlog:pos is mysql-bin.000003:2759.
Fri Oct 6 16:10:10 2017 - [info] Waiting to execute all relay logs on 192.168.56.27(192.168.56.27:3307)..
Fri Oct 6 16:10:10 2017 - [info] master_pos_wait(mysql-bin.000003:2759) completed on 192.168.56.27(192.168.56.27:3307). Executed 0 events.
Fri Oct 6 16:10:10 2017 - [info] done.
Fri Oct 6 16:10:11 2017 - [info] Getting new master's binlog name and position..
Fri Oct 6 16:10:11 2017 - [info] mysql-bin.000003:2743
Fri Oct 6 16:10:11 2017 - [info] All other slaves should start replication from here. Statement should be: CHANGE MASTER TO MASTER_HOST='192.168.56.27', MASTER_PORT=3307, MASTER_LOG_FILE='mysql-bin.000003', MASTER_LOG_POS=2743, MASTER_USER='repl', MASTER_PASSWORD='xxx';
Fri Oct 6 16:10:11 2017 - [info] Executing master ip online change script to allow write on the new master:
Fri Oct 6 16:10:11 2017 - [info] /usr/bin/master_ip_online_change --command=start --orig_master_host=192.168.56.26 --orig_master_ip=192.168.56.26 --orig_master_port=3307 --orig_master_user='mhauser' --orig_master_password='chengce243' --new_master_host=192.168.56.27 --new_master_ip=192.168.56.27 --new_master_port=3307 --new_master_user='mhauser' --new_master_password='chengce243' --orig_master_ssh_user=root --new_master_ssh_user=root
Fri Oct 6 16:10:11 2017 117572 Set read_only=0 on the new master.
Fri Oct 6 16:10:11 2017 121387 Creating app user on the new master..
Connection to 192.168.56.26 closed.
Fri Oct 6 16:10:11 2017 - [info] ok.
Fri Oct 6 16:10:11 2017 - [info]
Fri Oct 6 16:10:11 2017 - [info] * Switching slaves in parallel..
Fri Oct 6 16:10:11 2017 - [info]
Fri Oct 6 16:10:11 2017 - [info] -- Slave switch on host 192.168.56.28(192.168.56.28:3307) started, pid: 1871
Fri Oct 6 16:10:11 2017 - [info]
Fri Oct 6 16:10:11 2017 - [info] Log messages from 192.168.56.28 ...
Fri Oct 6 16:10:11 2017 - [info]
Fri Oct 6 16:10:11 2017 - [info] Waiting to execute all relay logs on 192.168.56.28(192.168.56.28:3307)..
Fri Oct 6 16:10:11 2017 - [info] master_pos_wait(mysql-bin.000003:2759) completed on 192.168.56.28(192.168.56.28:3307). Executed 0 events.
Fri Oct 6 16:10:11 2017 - [info] done.
Fri Oct 6 16:10:11 2017 - [info] Resetting slave 192.168.56.28(192.168.56.28:3307) and starting replication from the new master 192.168.56.27(192.168.56.27:3307)..
Fri Oct 6 16:10:11 2017 - [info] Executed CHANGE MASTER.
Fri Oct 6 16:10:11 2017 - [info] Slave started.
Fri Oct 6 16:10:11 2017 - [info] End of log messages from 192.168.56.28 ...
Fri Oct 6 16:10:11 2017 - [info]
Fri Oct 6 16:10:11 2017 - [info] -- Slave switch on host 192.168.56.28(192.168.56.28:3307) succeeded.
Fri Oct 6 16:10:11 2017 - [info] Unlocking all tables on the orig master:
Fri Oct 6 16:10:11 2017 - [info] Executing UNLOCK TABLES..
Fri Oct 6 16:10:11 2017 - [info] ok.
Fri Oct 6 16:10:11 2017 - [info] All new slave servers switched successfully.
Fri Oct 6 16:10:11 2017 - [info]
Fri Oct 6 16:10:11 2017 - [info] * Phase 5: New master cleanup phase..
Fri Oct 6 16:10:11 2017 - [info]
Fri Oct 6 16:10:12 2017 - [info] 192.168.56.27: Resetting slave info succeeded.
Fri Oct 6 16:10:12 2017 - [info] Switching master to 192.168.56.27(192.168.56.27:3307) completed successfully.
node1的IP：
[root@node1 ~]# ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 16436 qdisc noqueue state UNKNOWN
link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
inet 127.0.0.1/8 scope host lo
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000
link/ether 08:00:27:68:5f:50 brd ff:ff:ff:ff:ff:ff
inet 192.168.56.26/24 brd 192.168.56.255 scope global eth0
inet6 fe80::a00:27ff:fe68:5f50/64 scope link
valid_lft forever preferred_lft forever
node1的状态：
mysql> show master status ;
+------------------+----------+--------------+------------------+-------------------+
| File | Position | Binlog_Do_DB | Binlog_Ignore_DB | Executed_Gtid_Set |
+------------------+----------+--------------+------------------+-------------------+
| mysql-bin.000003 | 2759 | | | |
+------------------+----------+--------------+------------------+-------------------+
1 row in set (0.00 sec)
mysql> show slave status G
Empty set (0.00 sec)
可以看到node1现在已经不是从库了。原master可能已经废弃掉了。
node2的IP：
[root@node2 ~]# ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 16436 qdisc noqueue state UNKNOWN
link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
inet 127.0.0.1/8 scope host lo
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000
link/ether 08:00:27:7c:8a:78 brd ff:ff:ff:ff:ff:ff
inet 192.168.56.27/24 brd 192.168.56.255 scope global eth0
inet 192.168.56.206/24 scope global secondary eth0
inet6 fe80::a00:27ff:fe7c:8a78/64 scope link
valid_lft forever preferred_lft forever
node3的从库状态：
mysql> show slave status G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 192.168.56.27
Master_User: repl
Master_Port: 3307
Connect_Retry: 60
Master_Log_File: mysql-bin.000003
Read_Master_Log_Pos: 2743
Relay_Log_File: relay-bin.000002
Relay_Log_Pos: 283
Relay_Master_Log_File: mysql-bin.000003
Slave_IO_Running: Yes
Slave_SQL_Running: Yes
Replicate_Do_DB:
Replicate_Ignore_DB:
Replicate_Do_Table:
Replicate_Ignore_Table:
Replicate_Wild_Do_Table:
Replicate_Wild_Ignore_Table:
Last_Errno: 0
Last_Error:
Skip_Counter: 0
Exec_Master_Log_Pos: 2743
Relay_Log_Space: 450
Until_Condition: None
Until_Log_File:
Until_Log_Pos: 0
Master_SSL_Allowed: No
Master_SSL_CA_File:
Master_SSL_CA_Path:
Master_SSL_Cert:
Master_SSL_Cipher:
Master_SSL_Key:
Seconds_Behind_Master: 0
Master_SSL_Verify_Server_Cert: No
Last_IO_Errno: 0
Last_IO_Error:
Last_SQL_Errno: 0
Last_SQL_Error:
Replicate_Ignore_Server_Ids:
Master_Server_Id: 330727
Master_UUID: 8a12a46e-a9e0-11e7-abee-0800277c8a78
Master_Info_File: /data/mysql/3307/data/master.info
SQL_Delay: 0
SQL_Remaining_Delay: NULL
Slave_SQL_Running_State: Slave has read all relay log; waiting for the slave I/O thread to update it
Master_Retry_Count: 86400
Master_Bind:
Last_IO_Error_Timestamp:
Last_SQL_Error_Timestamp:
Master_SSL_Crl:
Master_SSL_Crlpath:
Retrieved_Gtid_Set:
Executed_Gtid_Set:
Auto_Position: 0
1 row in set (0.00 sec)
可以看到现在主库已经是node2了。
自此，切换成功。
根据上面输出的日志，找出如下内容，然后在node1上执行。
CHANGE MASTER TO MASTER_HOST='192.168.56.27', MASTER_PORT=3307, MASTER_LOG_FILE='mysql-bin.000003', MASTER_LOG_POS=2743, MASTER_USER='repl', MASTER_PASSWORD='chengce243';
mysql> start slave ;
Query OK, 0 rows affected (0.06 sec)
mysql> show slave status G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 192.168.56.27
Master_User: repl
Master_Port: 3307
Connect_Retry: 60
Master_Log_File: mysql-bin.000003
Read_Master_Log_Pos: 2743
Relay_Log_File: relay-bin.000002
Relay_Log_Pos: 283
Relay_Master_Log_File: mysql-bin.000003
Slave_IO_Running: Yes
Slave_SQL_Running: Yes
Replicate_Do_DB:
Replicate_Ignore_DB:
Replicate_Do_Table:
Replicate_Ignore_Table:
Replicate_Wild_Do_Table:
Replicate_Wild_Ignore_Table:
Last_Errno: 0
Last_Error:
Skip_Counter: 0
Exec_Master_Log_Pos: 2743
Relay_Log_Space: 450
Until_Condition: None
Until_Log_File:
Until_Log_Pos: 0
Master_SSL_Allowed: No
Master_SSL_CA_File:
Master_SSL_CA_Path:
Master_SSL_Cert:
Master_SSL_Cipher:
Master_SSL_Key:
Seconds_Behind_Master: 0
Master_SSL_Verify_Server_Cert: No
Last_IO_Errno: 0
Last_IO_Error:
Last_SQL_Errno: 0
Last_SQL_Error:
Replicate_Ignore_Server_Ids:
Master_Server_Id: 330727
Master_UUID: 8a12a46e-a9e0-11e7-abee-0800277c8a78
Master_Info_File: /data/mysql/3307/data/master.info
SQL_Delay: 0
SQL_Remaining_Delay: NULL
Slave_SQL_Running_State: Slave has read all relay log; waiting for the slave I/O thread to update it
Master_Retry_Count: 86400
Master_Bind:
Last_IO_Error_Timestamp:
Last_SQL_Error_Timestamp:
Master_SSL_Crl:
Master_SSL_Crlpath:
Retrieved_Gtid_Set:
Executed_Gtid_Set:
Auto_Position: 0
1 row in set (0.00 sec)
自此，node1已经是node2的从库