cd mha4mysql-node-0.58

perl Makefile.PL

make && make install

-r-xr-xr-x.  root root  Oct  : apply_diff_relay_logs

-r-xr-xr-x.  root root   Oct  : filter_mysqlbinlog

-r-xr-xr-x.  root root   Oct  : purge_relay_logs

-r-xr-xr-x.  root root   Oct  : save_binary_logs

Node脚本说明：(这些工具通常由MHA Manager的脚本触发，无需人为操作)

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）

cd mha4mysql-manager-0.58

perl Makefile.PL

make && make install

 echo "export PATH=${PATH}:/usr/local/bin">>/etc/profile source /etc/profile

[server default]

manager_workdir=/var/log/masterha/app1 #管理节点工作目录

manager_log=/var/log/masterha/app1/manager.log #管理节点日志

master_binlog_dir=/mysql/log/3306 #数据库Binlog所在日志

master_ip_failover_script=/usr/local/bin/master_ip_failover #自动故障转移的脚本

master_ip_online_change_script=/usr/local/bin/master_ip_online_change #手动在线切换主节点的脚本

password=   #mysql数据库监控密码

user=root #mysql数据库监控用户

ping_interval=   #发送ping间隔包的时间,默认3S,这里1是1S，如果3次没有响应则故障切换

remote_workdir=/tmp #mysql切换的时候binlog保存路径

repl_password= #mysql复制的mysql用户密码

repl_user=rpl #mysql复制的Mysql用户账户

report_script=/usr/local/bin/send_report #发生切换之后的报警报告脚本

secondary_check_script=/usr/local/bin/masterha_secondary_check  -s db2 -s db3 -s db4 -s db5 #检测哪个库是最新的，以便故障转移时为新主库

shutdown_script=""  #关闭的脚本

ssh_user=root #SSH通信的用户

[server1]

hostname=192.168.1.202

port=

[server2]

hostname=192.168.1.203

port=

candidate_master=  #设置为备用主库,当多个SERVER都有设置它,用最新的做主库

check_repl_delay= #切换的时候忽略复制延迟，

#默认情况下如果一个slave落后master 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]

port=

hostname=192.168.1.204

[server4]

hostname=192.168.1.205

port=

no_master= #不会成为主库

直接可用配置参数代码：

[server default]

manager_workdir=/var/log/masterha/app1

manager_log=/var/log/masterha/app1/manager.log

master_binlog_dir=/mysql/log/

master_ip_failover_script=/usr/local/bin/master_ip_failover

master_ip_online_change_script=/usr/local/bin/master_ip_online_change

password=

user=root

ping_interval=

remote_workdir=/tmp

repl_password=

repl_user=rpl

report_script=/usr/local/bin/send_report

secondary_check_script=/usr/local/bin/masterha_secondary_check  -s db2 -s db3 -s db4 -s db5

shutdown_script=""

ssh_user=root

[server1]

hostname=192.168.1.202

port=

candidate_master=

[server2]

hostname=192.168.1.203

port=

candidate_master=

check_repl_delay=

[server3]

port=

hostname=192.168.1.204

[server4]

hostname=192.168.1.205

port=

no_master=

#配置文件说明

MHA主要配置文件说明

manager_workdir=/var/log/masterha/app1.log：设置manager的工作目录

manager_log=/var/log/masterha/app1/manager.log：设置manager的日志文件

master_binlog_dir=/data/mysql：设置master 保存binlog的位置，以便MHA可以找到master的日志

master_ip_failover_script= /usr/local/bin/master_ip_failover：设置自动failover时候的切换脚本

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

user=root：设置监控mysql的用户

password=dayi123：设置监控mysql的用户，需要授权能够在manager节点远程登录

ping_interval=：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railover

remote_workdir=/tmp：设置远端mysql在发生切换时binlog的保存位置

repl_user=repl ：设置mysql中用于复制的用户密码

repl_password=replication：设置mysql中用于复制的用户

report_script=/usr/local/send_report：设置发生切换后发送的报警的脚本

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放在发生脑裂,这里没有使用）

ssh_user=root //设置ssh的登录用户名

candidate_master=：在节点下设置，设置当前节点为候选的master

slave check_repl_delay= :在节点配置下设置，默认情况下如果一个slave落后master 100M的relay logs的话，MHA将不会选择该slave作为一个新的master；这个选项对于对于设置了candidate_master=1的主机非常有用
secondary_check_script=/usr/local/bin/masterha_secondary_check  -s db2 -s db3 -s db4 -s db5 #检测哪个库是最新的，以便故障转移的时候确认信主库

#在202机器上执行

弄之前，先给主库，再加个IP网卡 ：/sbin/ifconfig ens34:1 192.168.1.210/24，然后作为VIP使用

mysql -uroot -p123456 -e"set global relay_log_purge=0;" #所有202~205都执行

vim /usr/local/bin/purge_relay_log.sh

#新建/修改如下

#!/bin/bash

user=root  #mysql的账户密码

password=

port=

socket=/mysql/data//mysql.sock

log_dir='/var/log/masterha/log'

work_dir='/mysql/log/3306/relaylog'

purge='/usr/local/bin/purge_relay_logs'

if [ ! -d $log_dir ]

then

   mkdir -p $log_dir

fi

$purge --user=${user} --password=${password} -S ${socket} --host=localhost --disable_relay_log_purge --port=${port}

#复制到202~205上的每一台机器上去

　　scp root@192.168.1.202:/usr/local/bin/purge_relay_log.sh /usr/local/bin

#添加到crontab,每4小时执行一次

　　chmod +x /usr/local/bin/purge_relay_log.sh

　　crontab -e

　　0 4 * * * /bin/bash /usr/local/bin/purge_relay_log.sh

　　#4个小时清理一次

#手工执行以下查看该脚本是否报错

#!/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

);

my $vip = '192.168.1.210/24';

my $key = '';

my $ssh_start_vip = "/sbin/ifconfig ens34:$key $vip";

my $ssh_stop_vip = "/sbin/ifconfig ens34:$key down";

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 = ;

        eval {

            print "Disabling the VIP on old master: $orig_master_host \n";

            &stop_vip();

            $exit_code = ;

        };

        if ($@) {

            warn "Got Error: $@\n";

            exit $exit_code;

        }

        exit $exit_code;

    }

    elsif ( $command eq "start" ) {

        my $exit_code = ;

        eval {

            print "Enabling the VIP - $vip on the new master - $new_master_host \n";

            &start_vip();

            $exit_code = ;

        };

        if ($@) {

            warn $@;

            exit $exit_code;

        }

        exit $exit_code;

    }

    elsif ( $command eq "status" ) {

        print "Checking the Status of the script.. OK \n";

        exit ;

    }

    else {

        &usage();

        exit ;

    }

}

sub start_vip() {

    `ssh $ssh_user\@$new_master_host \" $ssh_start_vip \"`;

}

sub stop_vip() {

     return   unless  ($ssh_user);

    `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";

}

#!/usr/bin/env perl

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_host, $orig_master_ip,

  $orig_master_port, $orig_master_user, 

  $new_master_host,  $new_master_ip,    $new_master_port,

  $new_master_user,  

);

my $vip = '192.168.1.210/24';  # Virtual IP 

my $key = "1"; 

my $ssh_start_vip = "/sbin/ifconfig ens34:$key $vip";

my $ssh_stop_vip = "/sbin/ifconfig ens34:$key down";

my $ssh_user = "root";

my $new_master_password='123456';

my $orig_master_password='123456';

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,

  'orig_master_user=s'     => \$orig_master_user,

  #'orig_master_password=s' => \$orig_master_password,

  '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 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;

  $running_time_threshold =  unless ($running_time_threshold);

  $type                   =  unless ($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};

    $info =~ s/^\s*(.*?)\s*$/$/ if defined($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 >=  );

    if ( $type >=  ) {

      next if ( defined($command) && $command eq "Sleep" );

      next if ( defined($command) && $command eq "Connect" );

    }

    if ( $type >=  ) {

      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

    # . Set read_only=  on the new master

    # . DROP USER so that no app user can establish new connections

    # . Set read_only=  on the current master

    # . Kill current queries

    # * Any database access failure will result in script die.

    my $exit_code = ;

    eval {

      ## Setting read_only= 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,

        $new_master_user, $new_master_password,  );

      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,  );

      ## 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 *  milliseconds so that current connections can exit

      my $time_until_read_only = ;

      $_tstart = [gettimeofday];

      my @threads = get_threads_util( $orig_master_handler->{dbh},

        $orig_master_handler->{connection_id} );

      while ( $time_until_read_only >  && $#threads >=  ) {

        if ( $time_until_read_only %  ==  ) {

          printf

"%s Waiting all running %d threads are disconnected.. (max %d milliseconds)\n",

            current_time_us(), $#threads + , $time_until_read_only * ;

          if ( $#threads <  ) {

            print Data::Dumper->new( [$_] )->Indent()->Terse()->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= 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 *  milliseconds so that current update queries can complete

      my $time_until_kill_threads = ;

      @threads = get_threads_util( $orig_master_handler->{dbh},

        $orig_master_handler->{connection_id} );

      while ( $time_until_kill_threads >  && $#threads >=  ) {

        if ( $time_until_kill_threads %  ==  ) {

          printf

"%s Waiting all running %d queries are disconnected.. (max %d milliseconds)\n",

            current_time_us(), $#threads + , $time_until_kill_threads * ;

          if ( $#threads <  ) {

            print Data::Dumper->new( [$_] )->Indent()->Terse()->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} );

      }

                print "Disabling the VIP on old master: $orig_master_host \n";

                &stop_vip();     

      ## Terminating all threads

      print current_time_us() . " Killing all application threads..\n";

      $orig_master_handler->kill_threads(@threads) if ( $#threads >=  );

      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 = ;

    };

    if ($@) {

      warn "Got Error: $@\n";

      exit $exit_code;

    }

    exit $exit_code;

  }

  elsif ( $command eq "start" ) {

    ## Activating master ip on the new master

    # . Create app user with write privileges

    # . Moving backup script if needed

    # . 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  or , MHA does not abort

    my $exit_code = ;

    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,  );

      ## Set read_only= 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

                print "Enabling the VIP - $vip on the new master - $new_master_host \n";

                &start_vip();

                $exit_code = ;

    };

    if ($@) {

      warn "Got Error: $@\n";

      exit $exit_code;

    }

    exit $exit_code;

  }

  elsif ( $command eq "status" ) {

    # do nothing

    exit ;

  }

  else {

    &usage();

    exit ;

  }

}

# A simple system call that enable the VIP on the new master 

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_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;

}

#!/bin/bash

source /root/.bash_profile

vip=`echo '192.168.1.210/24'`  #设置VIP

key=`echo ''`

command=`echo "$1" | awk -F = '{print $2}'`

orig_master_host=`echo "$2" | awk -F = '{print $2}'`

new_master_host=`echo "$7" | awk -F = '{print $2}'`

orig_master_ssh_user=`echo "${12}" | awk -F = '{print $2}'`

new_master_ssh_user=`echo "${13}" | awk -F = '{print $2}'`

#要求服务的网卡识别名一样

stop_vip=`echo "ssh root@$orig_master_host /usr/sbin/ifconfig bond0:$key down"`

start_vip=`echo "ssh root@$new_master_host /usr/sbin/ifconfig bond0:$key $vip"`

if [ $command = 'stop' ]

  then

    echo -e "\n\n\n****************************\n"

    echo -e "Disabled thi VIP - $vip on old master: $orig_master_host \n"

    $stop_vip

    if [ $? -eq  ]

      then

    echo "Disabled the VIP successfully"

      else

    echo "Disabled the VIP failed"

    fi

    echo -e "***************************\n\n\n"

  fi

if [ $command = 'start' -o $command = 'status' ]

  then

    echo -e "\n\n\n*************************\n"

    echo -e "Enabling the VIP - $vip on new master: $new_master_host \n"

    $start_vip

    if [ $? -eq  ]

      then

    echo "Enabled the VIP successfully"

      else

    echo "Enabled the VIP failed"

    fi

    echo -e "***************************\n\n\n"

fi

#检查mha manager 到所有的 MHA Node 的SSH链接状态

masterha_check_ssh --conf=/etc/masterha/app1.cnf

#通过 masterha_check_repl 脚本查看整个集群的状态

masterha_check_repl --conf=/etc/masterha/app1.cnf

masterha_check_status --conf=/etc/masterha/app1.cnf

mkdir -p /var/log/masterha/app1

chmod -R 777 /var/log/masterha/app1

#启动MHA监控

nohup masterha_manager --conf=/etc/masterha/app1.cnf --ignore_laster_failover &
#--remove_dead_master_conf &

(1)--remove_dead_master_conf #当发生故障切换后，老的主库配置会从配置文件中移除掉（比如发生故障切换了，202主库切换到了203，那么在app1.cnf配置文件中，[server1]描述的ip为192.168.1.202内容会被清除）
(2)--manger_log #管理节点的日志位置
(3)--ignore_last_failover
　　#在默认情况下，如果mha检查到主库连续发现宕机，且两次宕机间隔不超过8小时，则不会发生继续切换。（会生成一个文件，判断文件存在就不允许继续故障转移切换）
　　#加了这个参数的话，就是来避免上述情况的，以便可以无限制的故障切换。

# 停止MHA监控
masterha_stop --conf=/etc/masterha/app1.cnf