mysqlbinlog闪回数据

mysql利用binlog恢复误操作数据
在人工手动进行一些数据库写操作的时候(比方说数据订正),尤其是一些不可控的批量更新或删除,通常都建议备份后操作。不过不怕万一,就怕一万,有备无患总是好的。在线上或者测试环境误操作导致数据被删除或者更新后,想要恢复,一般有两种方法。
方法一、利用最近的全量备份+增量binlog备份,恢复到误操作之前的状态,但是随着数据量的增大,binlog的增多,恢复起来很费时。
方法二、如果binlog的格式为row,那么就可以将binlog解析出来生成反向的原始sql
以下是利用方法二写的一个python脚本binlog_rollback.py,可利用此脚本生成反向的原始sql。
说明:
0、前提是binlog的格式为row
1、要恢复的表操作前后表结构没有发生变更,否则脚本无法解析
2、只生成dml(insert/update/delete)的rollback语句
3、最终生成的sql是逆序的,所以最新的dml会生成在输入文件的最前面,并且带上了时间戳和偏移点,方便查找目标
4、需要提供一个连接mysql的只读用户,主要是为了获取表结构
5、如果binlog过大,建议带上时间范围,也可以指定只恢复某个库的sql
6、sql生成后,请务必在测试环境上测试恢复后再应用到线上
脚本代码
#!/bin/env python
# -*- coding:utf-8 -*-
import os,sys,re,getopt
import mysqldb
host = ‘127.0.0.1’
user = ‘’
password = ‘’
port = 3306
start_datetime = ‘1971-01-01 00:00:00’
stop_datetime = ‘2037-01-01 00:00:00’
start_position = ‘4’
stop_position = ‘18446744073709551615’
database = ‘’
mysqlbinlog_bin = ‘mysqlbinlog -v’
binlog = ‘’
filecontent = ‘’
output=‘rollback.sql’
only_primary = 0
# ----------------------------------------------------------------------------------------
# 功能:获取参数,生成相应的binlog解析文件
# ----------------------------------------------------------------------------------------
def getopts_parse_binlog():
global host
global user
global password
global port
global filecontent
global output
global binlog
global start_datetime
global stop_datetime
global start_position
global stop_position
global database
global only_primary
try:
options, args = getopt.getopt(sys.argv[1:], “f:o:h:u:p:p:d:”, [“help”,“binlog=”,“output=”,“host=”,“user=”,“password=”,“port=”,“start-datetime=”, \
“stop-datetime=”,“start-position=”,“stop-position=”,“database=”,“only-primary=”])
except getopt.getopterror:
print “参数输入有误!!!!!”
options = []
if options == [] or options[0][0] in (“--help”):
usage()
sys.exit()
print “正在获取参数。..。.”
for name, value in options:
if name == “-f” or name == “--binlog”:
binlog = value
if name == “-o” or name == “--output”:
output = value
if name == “-h” or name == “--host”:
host = value
if name == “-u” or name == “--user”:
user = value
if name == “-p” or name == “--password”:
password = value
if name == “-p” or name == “--port”:
port = value
if name == “--start-datetime”:
start_datetime = value
if name == “--stop-datetime”:
stop_datetime = value
if name == “--start-position”:
start_position = value
if name == “--stop-position”:
stop_position = value
if name == “-d” or name == “--database”:
database = value
if name == “--only-primary” :
only_primary = value
if binlog == ‘’ :
print “错误:请指定binlog文件名!”
usage()
if user == ‘’ :
print “错误:请指定用户名!”
usage()
if password == ‘’ :
print “错误:请指定密码!”
usage()
if database 《》 ‘’ :
condition_database = “--database=” + “‘” + database + “’”
else:
condition_database = ‘’
print “正在解析binlog.。..。”
filecontent=os.popen(“%s %s --base64-output=decode-rows --start-datetime=‘%s’ --stop-datetime=‘%s’ --start-position=‘%s’ --stop-position=‘%s’ %s\
|grep ‘###’ -b 2|sed -e ‘s/### //g’ -e ‘s/^insert/##insert/g’ -e ‘s/^update/##update/g’ -e ‘s/^delete/##delete/g’ ” \
%(mysqlbinlog_bin,binlog,start_datetime,stop_datetime,start_position,stop_position,condition_database)).read()
#print filecontent
# ----------------------------------------------------------------------------------------
# 功能:初始化binlog里的所有表名和列名,用全局字典result_dict来储存每个表有哪些列
# ----------------------------------------------------------------------------------------
def init_col_name():
global result_dict
global pri_dict
global filecontent
result_dict = {}
pri_dict = {}
table_list = re.findall(‘`.*`\\。`.*`’,filecontent)
table_list = list(set(table_list))
#table_list 为所有在这段binlog里出现过的表
print “正在初始化列名。..。.”
for table in table_list:
sname = table.split(‘。’)[0].replace(‘`’,‘’)
tname = table.split(‘。’)[1].replace(‘`’,‘’)
#连接数据库获取列和列id
try:
conn = mysqldb.connect(host=host,user=user,passwd=password,port=int(port))
cursor = conn.cursor()
cursor.execute(“select ordinal_position,column_name \
from information_schema.columns \
where table_schema=‘%s’ and table_name=‘%s’ ” %(sname,tname))
result=cursor.fetchall()
if result == () :
print ‘warning:’+sname+‘。’+tname+‘已删除’
#sys.exit()
result_dict[sname+‘。’+tname]=result
cursor.execute(“select ordinal_position,column_name \
from information_schema.columns \
where table_schema=‘%s’ and table_name=‘%s’ and column_key=‘pri’ ” %(sname,tname))
pri=cursor.fetchall()
#print pri
pri_dict[sname+‘。’+tname]=pri
cursor.close()
conn.close()
except mysqldb.error, e:
try:
print “error %d:%s” % (e.args[0], e.args[1])
except indexerror:
print “mysql error:%s” % str(e)
sys.exit()
#print result_dict
#print pri_dict
# ----------------------------------------------------------------------------------------
# 功能:拼凑回滚sql,逆序
# ----------------------------------------------------------------------------------------
def gen_rollback_sql():
global only_primary
fileoutput = open(output, ‘w’)
#先将文件根据‘--’分块,每块代表一个sql
area_list=filecontent.split(‘--\n’)
#逆序读取分块
print “正在开始拼凑sql.。..。”
for area in area_list[::-1]:
#由于一条sql可能影响多行,每个sql又可以分成多个逐条执行的sql
sql_list = area.split(‘##’)
#先将pos点和timestamp传入输出文件中
for sql_head in sql_list[0].splitlines():
sql_head = ‘#’+sql_head+‘\n’
fileoutput.write(sql_head)
#逐条sql进行替换更新,逆序
for sql in sql_list[::-1][0:-1]:
try:
if sql.split()[0] == ‘insert’:
rollback_sql = re.sub(‘^insert into’, ‘delete from’, sql, 1)
rollback_sql = re.sub(‘set\n’, ‘where\n’, rollback_sql, 1)
tablename_pos = 2
table_name = rollback_sql.split()[tablename_pos].replace(‘`’, ‘’)
# 获取该sql中的所有列
col_list = sorted(list(set(re.findall(‘@\d+’, rollback_sql))))
# 因为第一个列前面没有逗号或者and,所以单独替换
rollback_sql = rollback_sql.replace(‘@1=’, result_dict[table_name][0][1]+‘=’)
for col in col_list[1:]:
i = int(col[1:]) - 1
rollback_sql = rollback_sql.replace(col+‘=’, ‘and ’ + result_dict[table_name][i][1]+‘=’,1)
# 如果only_primary开启且存在主键,where条件里就只列出主键字段
if int(only_primary) == 1 and pri_dict[table_name] 《》 ():
sub_where = ‘’
for primary in pri_dict[table_name]:
primary_name = primary[1]
for condition in rollback_sql.split(‘where’, 1)[1].splitlines():
if re.compile(‘^\s*’+primary_name).match(condition) or re.compile(‘^\s*and\s*’+primary_name).match(condition):
sub_where = sub_where + condition + ‘\n’
sub_where = re.sub(‘^\s*and’, ‘’, sub_where, 1)
rollback_sql = rollback_sql.split(‘where’, 1)[0] + ‘where\n’ + sub_where
if sql.split()[0] == ‘update’:
rollback_sql = re.sub(‘set\n’, ‘#set#\n’, sql, 1)
rollback_sql = re.sub(‘where\n’, ‘set\n’, rollback_sql, 1)
rollback_sql = re.sub(‘#set#\n’, ‘where\n’, rollback_sql, 1)
tablename_pos = 1
table_name = rollback_sql.split()[tablename_pos].replace(‘`’, ‘’)
# 获取该sql中的所有列
col_list = sorted(list(set(re.findall(‘@\d+’, rollback_sql))))
# 因为第一个列前面没有逗号或者and,所以单独替换
rollback_sql = rollback_sql.replace(‘@1=’, result_dict[table_name][0][1] + ‘=’)
for col in col_list[1:]:
i = int(col[1:]) - 1
rollback_sql = rollback_sql.replace(col+‘=’, ‘,’ + result_dict[table_name][i][1]+‘=’, 1).replace(col+‘=’,‘and ’ +result_dict[table_name][i][1]+‘=’)
# 如果only_primary开启且存在主键,where条件里就只列出主键字段
if int(only_primary) == 1 and pri_dict[table_name] 《》 ():
sub_where = ‘’
for primary in pri_dict[table_name]:
primary_name = primary[1]
for condition in rollback_sql.split(‘where’, 1)[1].splitlines():
if re.compile(‘^\s*’ + primary_name).match(condition) or re.compile(‘^\s*and\s*’+primary_name).match(condition):
sub_where = sub_where + condition + ‘\n’
sub_where = re.sub(‘^\s*and’, ‘’, sub_where, 1)
rollback_sql = rollback_sql.split(‘where’, 1)[0] + ‘where\n’ + sub_where
if sql.split()[0] == ‘delete’:
rollback_sql = re.sub(‘^delete from’, ‘insert into’, sql, 1)
rollback_sql = re.sub(‘where\n’, ‘set\n’, rollback_sql, 1)
tablename_pos = 2
table_name = rollback_sql.split()[tablename_pos].replace(‘`’, ‘’)
# 获取该sql中的所有列
col_list = sorted(list(set(re.findall(‘@\d+’, rollback_sql))))
# 因为第一个列前面没有逗号或者and,所以单独替换
rollback_sql = rollback_sql.replace(‘@1=’, result_dict[table_name][0][1] + ‘=’)
for col in col_list[1:]:
i = int(col[1:]) - 1
rollback_sql = rollback_sql.replace(col+‘=’, ‘,’ + result_dict[table_name][i][1]+‘=’,1)
rollback_sql = re.sub(‘\n$’,‘;\n’,rollback_sql)
#print rollback_sql
fileoutput.write(rollback_sql)
except indexerror,e:
print “error:%s” % str(e)
sys.exit()
print “done!”
def usage():
help_info=“”“==========================================================================================
command line options :
--help # out : print help info
-f, --binlog # in : binlog file. (required)
-o, --outfile # out : output rollback sql file. (default ‘rollback.sql’)
-h, --host # in : host. (default ‘127.0.0.1’)
-u, --user # in : user. (required)
-p, --password # in : password. (required)
-p, --port # in : port. (default 3306)
--start-datetime # in : start datetime. (default ‘1970-01-01 00:00:00’)
--stop-datetime # in : stop datetime. default ‘2070-01-01 00:00:00’
--start-position # in : start position. (default ‘4’)
--stop-position # in : stop position. (default ‘18446744073709551615’)
-d, --database # in : list entries for just this database (no default value)。
--only-primary # in : only list primary key in where condition (default 0)
sample :
shell》 python binlog_rollback.py -f ‘mysql-bin.000001’ -o ‘/tmp/rollback.sql’ -h 192.168.0.1 -u ‘user’ -p ‘pwd’ -p 3307 -d dbname
==========================================================================================”“”
print help_info
sys.exit()
if __name__ == ‘__main__’:
getopts_parse_binlog()
init_col_name()
gen_rollback_sql()
演示
#首先创建一个只读账号
root:test》 grant select on *.* to ‘query’@‘127.0.0.1’ identified by ‘123456’;
query ok, 0 rows affected, 1 warning (0.01 sec)
#测试表结构如下
root:test》 create table `table1` (
-》 `id` int(11) not null auto_increment,
-》 `c1` int(11) default null,
-》 `c2` varchar(20) default null,
-》 `c3` int(11) default null,
-》 primary key (`id`)
-》 );
query ok, 0 rows affected (0.09 sec)
#插入三条数据
root:test》 insert into table1(c1,c2,c3) values (1,‘a’,1),(2,‘b’,2),(3,‘c’,3);
query ok, 3 rows affected (0.01 sec)
records: 3 duplicates: 0 warnings: 0
root:test》 select * from table1;
+----+------+------+------+
| id | c1 | c2 | c3 |
+----+------+------+------+
| 1 | 1 | a | 1 |
| 2 | 2 | b | 2 |
| 3 | 3 | c | 3 |
+----+------+------+------+
3 rows in set (0.00 sec)
#更新一条数据
root:test》 update table1 set c3=10 where id=3;
query ok, 1 row affected (0.01 sec)
rows matched: 1 changed: 1 warnings: 0
root:test》 select * from table1;
+----+------+------+------+
| id | c1 | c2 | c3 |
+----+------+------+------+
| 1 | 1 | a | 1 |
| 2 | 2 | b | 2 |
| 3 | 3 | c | 10 |
+----+------+------+------+
3 rows in set (0.00 sec)
#删除一条数据
root:test》 delete from table1 where id=1;
query ok, 1 row affected (0.01 sec)
root:test》 select * from table1;
+----+------+------+------+
| id | c1 | c2 | c3 |
+----+------+------+------+
| 2 | 2 | b | 2 |
| 3 | 3 | c | 10 |
+----+------+------+------+
2 rows in set (0.00 sec)
接下来利用脚本来生成反向sql
[root@diandi ~]# python binlog_rollback.py -f /log/mysql/bin/mysql-bin.000002 -o rollback.sql -u query -p 123456 --start-datetime=‘2016-10-28 00:00:00’ -d test
正在获取参数。..。.
正在解析binlog.。..。
正在初始化列名。..。.
正在开始拼凑sql.。..。
done!
查看反向sql,最新的dml会生成在输入文件的最前面
[root@diandi ~]# cat rollback.sql
## at 155848
##161028 17:07:10 server id 22100 end_log_pos 155898 crc32 0x5000bca7 delete_rows: table id 351 flags: stmt_end_f
insert into `test`。`table1`
set
id=1
,c1=1
,c2=‘a’
,c3=1;
## at 155560
##161028 17:04:56 server id 22100 end_log_pos 155626 crc32 0x11d91e2d update_rows: table id 351 flags: stmt_end_f
update `test`。`table1`
set
id=3
,c1=3
,c2=‘c’
,c3=3
where
id=3
and c1=3
and c2=‘c’
and c3=10;
## at 155258
##161028 16:59:31 server id 22100 end_log_pos 155338 crc32 0x3978c1c1 write_rows: table id 351 flags: stmt_end_f
delete from `test`。`table1`
where
id=3
and c1=3
and c2=‘c’
and c3=3;
delete from `test`。`table1`
where
id=2
and c1=2
and c2=‘b’
and c3=2;
delete from `test`。`table1`
where
id=1
and c1=1
and c2=‘a’
and c3=1;
执行回滚操作
#直接source整个文件,table1将恢复到原来的空表状态(实际情况,在测试环境上按需索取,然后再恢复线上)
root:test》 source /root/rollback.sql
query ok, 1 row affected (0.01 sec)
query ok, 1 row affected (0.01 sec)
rows matched: 1 changed: 1 warnings: 0
query ok, 1 row affected (0.01 sec)
query ok, 1 row affected (0.01 sec)
query ok, 1 row affected (0.01 sec)
root:test》 select * from table1;
empty set (0.00 sec)
具体的参数使用方法如下:
[root@diandi ~]# python binlog_rollback.py
==========================================================================================
command line options :
--help # out : print help info
-f, --binlog # in : binlog file. (required)
-o, --outfile # out : output rollback sql file. (default ‘rollback.sql’)
-h, --host # in : host. (default ‘127.0.0.1’)
-u, --user # in : user. (required)
-p, --password # in : password. (required)
-p, --port # in : port. (default 3306)
--start-datetime # in : start datetime. (default ‘1970-01-01 00:00:00’)
--stop-datetime # in : stop datetime. default ‘2070-01-01 00:00:00’
--start-position # in : start position. (default ‘4’)
--stop-position # in : stop position. (default ‘18446744073709551615’)
-d, --database # in : list entries for just this database (no default value)。
--only-primary # in : only list primary key in where condition (default 0)
sample :
shell》 python binlog_rollback.py -f ‘mysql-bin.000001’ -o ‘/tmp/rollback.sql’ -h 192.168.0.1 -u ‘user’ -p ‘pwd’ -p 3307 -d dbname

铜箔软连接常用铜箔0.1定制规格
《节奏空间》携手网易正式入华,现已开放预约!
一季度报出炉,蜂窝模组各大厂都在往哪“卷”?
高速电机驱动技术及其发展趋势
血管芯片可协助验证抗发炎化合物作用与成效
mysqlbinlog闪回数据
柔性智造属于那个行业类别
以太网与工业以太网的区别
一文详解600V稳压电路模块
通过CANopen转Modbus TCP网关的伺服系统
钽电容优点
激光雷达业务发展顺利 Waymo在2020年的估值将会大幅提升
对于未来市场上的三大趋势“模拟”“共享”“自由”分析
意法半导体携手微电子研究所将在碳化硅领域展开合作
谐振型开关电容变换器的工作原理和参数设计方法
留住你从前的开发环境的方法
手机RF抗干扰能力的测试
西门子洗碗机在中国市场占据绝对优势,呈现出碾压之势
单片机入门之数码管时钟
TI 通用电量计选型指南