systemctl stop firewalld systemctl disable firewalld setenforce 0
hostnamectl set-hostname Mysql1 hostnamectl set-hostname Mysql2 hostnamectl set-hostname Mysql3
##Master 节点## vim /etc/my.cnf [mysqld] server-id = 1 log_bin = master-bin log-slave-updates = true systemctl restart mysqld ##Slave1、Slave2 节点## vim /etc/my.cnf server-id = 2 #三台服务器的 server-id 不能一样 log_bin = master-bin relay-log = relay-log-bin relay-log-index = slave-relay-bin.index systemctl restart mysqld
ln -s /usr/local/mysql/bin/mysql /usr/sbin/ ln -s /usr/local/mysql/bin/mysqlbinlog /usr/sbin/
mysql -uroot -p grant replication slave on *.* to 'myslave'@'192.168.73.%' identified by '123'; #从数据库同步使用 grant all privileges on *.* to 'mha'@'192.168.73.%' identified by 'manager'; #manager 使用 grant all privileges on *.* to 'mha'@'Mysql1' identified by 'manager'; #防止从库通过主机名连接不上主库 grant all privileges on *.* to 'mha'@'Mysql2' identified by 'manager'; grant all privileges on *.* to 'mha'@'Mysql3' identified by 'manager'; flush privileges;
show master status; +-------------------+----------+--------------+------------------+-------------------+ | File | Position | Binlog_Do_DB | Binlog_Ignore_DB | Executed_Gtid_Set | +-------------------+----------+--------------+------------------+-------------------+ | master-bin.000001 | 1745 | | | | +-------------------+----------+--------------+------------------+-------------------+
change master to master_host='192.168.73.10',master_user='myslave',master_password='123',master_log_file='master-bin.000001',master_log_pos=1745; start slave;
show slave status\G; //确保 IO 和 SQL 线程都是 Yes,代表同步正常。 Slave_IO_Running: Yes Slave_SQL_Running: Yes
set global read_only=1;
##在 Master 主库插入条数据,测试是否同步## create database test_db; use test_db; create table test(id int); insert into test(id) values (1);
yum install epel-release --nogpgcheck -y yum install -y perl-DBD-MySQL \ perl-Config-Tiny \ perl-Log-Dispatch \ perl-Parallel-ForkManager \ perl-ExtUtils-CBuilder \ perl-ExtUtils-MakeMaker \ perl-CPAN
cd /opt tar zxvf mha4mysql-node-0.57.tar.gz cd mha4mysql-node-0.57 perl Makefile.PL make && make install
cd /opt tar zxvf mha4mysql-manager-0.57.tar.gz cd mha4mysql-manager-0.57 perl Makefile.PL make && make install
---------------------------------------------------------------------------------------------------------- #manager 组件安装后在/usr/local/bin 下面会生成几个工具,主要包括以下几个: masterha_check_ssh 检查 MHA 的 SSH 配置状况 masterha_check_repl 检查 MySQL 复制状况 masterha_manger 启动 manager的脚本 masterha_check_status 检测当前 MHA 运行状态 masterha_master_monitor 检测 master 是否宕机 masterha_master_switch 控制故障转移(自动或者手动) masterha_conf_host 添加或删除配置的 server 信息 masterha_stop 关闭manager #node 组件安装后也会在/usr/local/bin 下面会生成几个脚本(这些工具通常由 MHAManager 的脚本触发,无需人为操作)主要如下: save_binary_logs 保存和复制 master 的二进制日志 apply_diff_relay_logs 识别差异的中继日志事件并将其差异的事件应用于其他的 slave filter_mysqlbinlog 去除不必要的 ROLLBACK 事件(MHA 已不再使用这个工具) purge_relay_logs 清除中继日志(不会阻塞 SQL 线程) ----------------------------------------------------------------------------------------------------------
ssh-keygen -t rsa #一路按回车键 ssh-copy-id 192.168.73.10 ssh-copy-id 192.168.73.20 ssh-copy-id 192.168.73.30
ssh-keygen -t rsa ssh-copy-id 192.168.73.20 ssh-copy-id 192.168.73.30
ssh-keygen -t rsa ssh-copy-id 192.168.73.10 ssh-copy-id 192.168.73.30
ssh-keygen -t rsa ssh-copy-id 192.168.73.10 ssh-copy-id 192.168.73.20
cp -rp /opt/mha4mysql-manager-0.57/samples/scripts /usr/local/bin //拷贝后会有四个执行文件 ll /usr/local/bin/scripts/
---------------------------------------------------------------------------------------------------------- master_ip_failover #自动切换时 VIP 管理的脚本 master_ip_online_change #在线切换时 vip 的管理 power_manager #故障发生后关闭主机的脚本 send_report #因故障切换后发送报警的脚本 ----------------------------------------------------------------------------------------------------------
cp /usr/local/bin/scripts/master_ip_failover /usr/local/bin
vim /usr/local/bin/master_ip_failover #!/usr/bin/env perl use strict; use warnings FATAL => 'all'; use Getopt::Long; my ( $command, $ssh_user, $orig_master_host, $orig_master_ip, $orig_master_port, $new_master_host, $new_master_ip, $new_master_port ); #############################添加内容部分######################################### my $vip = '192.168.73.200'; #指定vip的地址 my $brdc = '192.168.73.255'; #指定vip的广播地址 my $ifdev = 'ens33'; #指定vip绑定的网卡 my $key = '1'; #指定vip绑定的虚拟网卡序列号 my $ssh_start_vip = "/sbin/ifconfig ens33:$key $vip"; #代表此变量值为ifconfig ens33:1 192.168.73.200 my $ssh_stop_vip = "/sbin/ifconfig ens33:$key down"; #代表此变量值为ifconfig ens33:1 192.168.73.200 down my $exit_code = 0; #指定退出状态码为0 #my $ssh_start_vip = "/usr/sbin/ip addr add $vip/24 brd $brdc dev $ifdev label $ifdev:$key;/usr/sbin/arping -q -A -c 1 -I $ifdev $vip;iptables -F;"; #my $ssh_stop_vip = "/usr/sbin/ip addr del $vip/24 dev $ifdev label $ifdev:$key"; ################################################################################## 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, ); exit &main(); sub main { print "\n\nIN SCRIPT TEST====$ssh_stop_vip==$ssh_start_vip===\n\n"; if ( $command eq "stop" || $command eq "stopssh" ) { my $exit_code = 1; eval { print "Disabling the VIP on old master: $orig_master_host \n"; &stop_vip(); $exit_code = 0; }; if ($@) { warn "Got Error: $@\n"; exit $exit_code; } exit $exit_code; } elsif ( $command eq "start" ) { my $exit_code = 10; eval { print "Enabling the VIP - $vip on the new master - $new_master_host \n"; &start_vip(); $exit_code = 0; }; if ($@) { warn $@; exit $exit_code; } exit $exit_code; } elsif ( $command eq "status" ) { print "Checking the Status of the script.. OK \n"; exit 0; } else { &usage(); exit 1; } } sub start_vip() { `ssh $ssh_user\@$new_master_host \" $ssh_start_vip \"`; } ## A simple system call that disable the VIP on the old_master sub stop_vip() { `ssh $ssh_user\@$orig_master_host \" $ssh_stop_vip \"`; } 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"; }
mkdir /etc/masterha cp /opt/mha4mysql-manager-0.57/samples/conf/app1.cnf /etc/masterha
vim /etc/masterha/app1.cnf #删除原有内容,直接复制并修改节点服务器的IP地址 [server default] manager_log=/var/log/masterha/app1/manager.log manager_workdir=/var/log/masterha/app1 master_binlog_dir=/usr/local/mysql/data master_ip_failover_script=/usr/local/bin/master_ip_failover master_ip_online_change_script=/usr/local/bin/master_ip_online_change password=manager ping_interval=1 remote_workdir=/tmp repl_password=123 repl_user=myslave secondary_check_script=/usr/local/bin/masterha_secondary_check -s 192.168.73.20 -s 192.168.73.30 shutdown_script="" ssh_user=root user=mha [server1] hostname=192.168.73.10 port=3306 [server2] candidate_master=1 check_repl_delay=0 hostname=192.168.73.20 port=3306 [server3] hostname=192.168.73.30 port=3306
---------------------------------------------------------------------------------------------------------- [server default] manager_log=/var/log/masterha/app1/manager.log #manager日志 manager_workdir=/var/log/masterha/app1.log #manager工作目录 master_binlog_dir=/usr/local/mysql/data/ #master保存binlog的位置,这里的路径要与master里配置的binlog的路径一致,以便MHA能找到 master_ip_failover_script=/usr/local/bin/master_ip_failover #设置自动failover时候的切换脚本,也就是上面的那个脚本 master_ip_online_change_script=/usr/local/bin/master_ip_online_change #设置手动切换时候的切换脚本 password=manager #设置mysql中root用户的密码,这个密码是前文中创建监控用户的那个密码 ping_interval=1 #设置监控主库,发送ping包的时间间隔,默认是3秒,尝试三次没有回应的时候自动进行failover remote_workdir=/tmp #设置远端mysql在发生切换时binlog的保存位置 repl_password=123 #设置复制用户的密码 repl_user=myslave #设置复制用户的用户 report_script=/usr/local/send_report #设置发生切换后发送的报警的脚本 secondary_check_script=/usr/local/bin/masterha_secondary_check -s 192.168.73.20 -s 192.168.73.30 #指定检查的从服务器IP地址 shutdown_script="" #设置故障发生后关闭故障主机脚本(该脚本的主要作用是关闭主机防止发生脑裂,这里没有使用) ssh_user=root #设置ssh的登录用户名 user=mha #设置监控用户root [server1] hostname=192.168.73.10 port=3306 [server2] hostname=192.168.73.20 port=3306 candidate_master=1 #设置为候选master,设置该参数以后,发生主从切换以后将会将此从库提升为主库,即使这个从库不是集群中最新的slave check_repl_delay=0 #默认情况下如果一个slave落后master 超过100M的relay logs的话,MHA将不会选择该slave作为一个新的master, 因为对于这个slave的恢复需要花费很长时间;通过设置check_repl_delay=0,MHA触发切换在选择一个新的master的时候将会忽略复制延时,这个参数对于设置了candidate_master=1的主机非常有用,因为这个候选主在切换的过程中一定是新的master [server3] hostname=192.168.73.30 port=3306 ----------------------------------------------------------------------------------------------------------
/sbin/ifconfig ens33:1 192.168.73.200/24
masterha_check_ssh -conf=/etc/masterha/app1.cnf Tue Nov 26 23:09:45 2020 - [warning] Global configuration file /etc/masterha_default.cnf not found. Skipping. Tue Nov 26 23:09:45 2020 - [info] Reading application default configuration from /etc/masterha/app1.cnf.. Tue Nov 26 23:09:45 2020 - [info] Reading server configuration from /etc/masterha/app1.cnf.. Tue Nov 26 23:09:45 2020 - [info] Starting SSH connection tests.. Tue Nov 26 23:09:46 2020 - [debug] Tue Nov 26 23:09:45 2020 - [debug] Connecting via SSH from root@192.168.73.20(192.168.73.20:22) to root@192.168.73.30(192.168.73.30:22).. Tue Nov 26 23:09:46 2020 - [debug] ok. Tue Nov 26 23:09:47 2020 - [debug] Tue Nov 26 23:09:46 2020 - [debug] Connecting via SSH from root@192.168.73.30(192.168.73.30:22) to root@192.168.73.20(192.168.73.20:22).. Tue Nov 26 23:09:47 2020 - [debug] ok. Tue Nov 26 23:09:47 2020 - [info] All SSH connection tests passed successfully.
masterha_check_repl -conf=/etc/masterha/app1.cnf Tue Nov 26 23:10:29 2020 - [info] Slaves settings check done. Tue Nov 26 23:10:29 2020 - [info] 192.168.73.20(192.168.73.20:3306) (current master) +--192.168.73.30(192.168.73.30:3306) Tue Nov 26 23:10:29 2020 - [info] Checking replication health on 192.168.73.30.. Tue Nov 26 23:10:29 2020 - [info] ok. Tue Nov 26 23:10:29 2020 - [info] Checking master_ip_failover_script status: Tue Nov 26 23:10:29 2020 - [info] /usr/local/bin/master_ip_failover --command=status --ssh_user=root --orig_master_host=192.168.73.20 --orig_master_ip=192.168.73.20 --orig_master_port=3306 IN SCRIPT TEST====/sbin/ifconfig ens33:1 down==/sbin/ifconfig ens33:1 192.168.80.200=== Checking the Status of the script.. OK Tue Nov 26 23:10:29 2020 - [info] OK. Tue Nov 26 23:10:29 2020 - [warning] shutdown_script is not defined. Tue Nov 26 23:10:29 2020 - [info] Got exit code 0 (Not master dead). MySQL Replication Health is OK.
nohup masterha_manager --conf=/etc/masterha/app1.cnf --remove_dead_master_conf --ignore_last_failover < /dev/null > /var/log/masterha/app1/manager.log 2>&1 &
---------------------------------------------------------------------------------------------------------- --remove_dead_master_conf:该参数代表当发生主从切换后,老的主库的 ip 将会从配置文件中移除。 --manger_log:日志存放位置。 --ignore_last_failover:在缺省情况下,如果 MHA 检测到连续发生宕机,且两次宕机间隔不足 8 小时的话,则不会进行 Failover, 之所以这样限制是为了避免 ping-pong 效应。该参数代表忽略上次 MHA 触发切换产生的文件,默认情况下,MHA 发生切换后会在日志记目录,也就是上面设置的日志app1.failover.complete文件,下次再次切换的时候如果发现该目录下存在该文件将不允许触发切换,除非在第一次切换后收到删除该文件,为了方便,这里设置为--ignore_last_failover。 ----------------------------------------------------------------------------------------------------------
masterha_check_status --conf=/etc/masterha/app1.cnf
cat /var/log/masterha/app1/manager.log | grep "current master"
ifconfig //若要关闭 manager 服务,可以使用如下命令。 masterha_stop --conf=/etc/masterha/app1.cnf 或者可以直接采用 kill 进程 ID 的方式关闭。
tail -f /var/log/masterha/app1/manager.log
systemctl stop mysqld 或 pkill -9 mysql
ifconfig
systemctl restart mysqld
#在现主库服务器 Mysql2 查看二进制文件和同步点 show master status; #在原主库服务器 mysql1 执行同步操作 change master to master_host='192.168.73.20',master_user='myslave',master_password='123',master_log_file='master-bin.000001',master_log_pos=1745; start slave;
vi /etc/masterha/app1.cnf ...... secondary_check_script=/usr/local/bin/masterha_secondary_check -s 192.168.73.10 -s 192.168.73.30 ...... [server1] hostname=192.168.73.20 port=3306 [server2] candidate_master=1 check_repl_delay=0 hostname=192.168.73.10 port=3306 [server3] hostname=192.168.73.30 port=3306
nohup masterha_manager --conf=/etc/masterha/app1.cnf --remove_dead_master_conf --ignore_last_failover < /dev/null > /var/log/masterha/app1/manager.log 2>&1 & #解决中英字不兼容报错的问题 dos2unix /usr/local/bin/master_ip_failover