序言:
业务报警订单提交异常,页面一直没有反应,排查后是事务没有提交或者回滚导致,想到如果及时监控事务的运行状态报警出来,那么就可以及时排查出问题所在,方便运营处理,所以自己就弄了一个shell脚本放在nagios来处理事务报警情况。
1,编写事务监控脚本
#!/bin/bash
# author: tim.man
# version: 1.0
# desc: check the RUNNING TRANSACTION over
ST_OK=0
ST_WR=1
ST_CR=2
ST_UK=3
TIME_TRX=10
# 提示信息
print_help() {
echo "$PROGNAME -w INT -c INT"
echo "Options:"
echo " -w/--warning)"
echo " Sets a warning number"
echo " -c/--critical)"
echo " Sets a critical level for io"
exit $ST_UK
}
while test -n "$1"; do
case "$1" in
-help|-h)
print_help
exit $ST_UK
;;
--warning|-w)
warning=$2
shift
;;
--critical|-c)
critical=$2
shift
;;
*)
echo "Unknown argument: $1"
print_help
exit $ST_UK
;;
esac
shift
done
get_wcdiff() {
if [ ! -z "$warning" -a ! -z "$critical" ]
then
wclvls=1
if [ ${warning} -gt ${critical} ]
then
wcdiff=1
fi
elif [ ! -z "$warning" -a -z "$critical" ]
then
wcdiff=2
elif [ -z "$warning" -a ! -z "$critical" ]
then
wcdiff=3
fi
}
# 脚本判断
val_wcdiff() {
if [ "$wcdiff" = 1 ]
then
echo "Please adjust your warning/critical thresholds. The warning must be lower than the critical level!"
exit $ST_UK
elif [ "$wcdiff" = 2 ]
then
echo "Please also set a critical value when you want to use warning/critical thresholds!"
exit $ST_UK
elif [ "$wcdiff" = 3 ]
then
echo "Please also set a warning value when you want to use warning/critical thresholds!"
exit $ST_UK
fi
}
get_wcdiff
val_wcdiff
# 统计mysql的事务中最大运行时间
max_over_time=`/usr/local/mysql/bin/mysql --user=nagios --password="nagiosq@xxx" -NS /usr/local/mysql/mysql.sock -e "SELECT TIME_TO_SEC(TIMEDIFF(NOW(),t.trx_started)) FROM information_schem
a.INNODB_TRX t WHERE TIME_TO_SEC(TIMEDIFF(NOW(),t.trx_started))>$TIME_TRX ORDER BY TIME_TO_SEC(TIMEDIFF(NOW(),t.trx_started)) DESC LIMIT 1;" |awk '{print $1}'`
# 如果当前没有RUNNING的事务,则直接赋值为0,以免下面if判断出错
if [ ! -n "$max_over_time" ];then max_over_time=0
fi
# 取得当前所以阻塞的事务数量
num_trx=`/usr/local/mysql/bin/mysql --user=nagios --password="nagiosq@xxx" -NS /usr/local/mysql/mysql.sock -e "SELECT COUNT(1) FROM information_schema.INNODB_TRX t WHERE TIME_TO_SEC(TIMEDIF
F(NOW(),t.trx_started))>$TIME_TRX;" |awk '{print $1}'`
if [ -n "$warning" -a -n "$critical" ]
then
if [ `expr $max_over_time \> $warning` -eq 1 -a `expr $max_over_time \< $critical` -eq 1 ]
then
echo "WARNING - $num_trx TRANSACTIONS RUNNING,go over for $max_over_time seconds"
exit $ST_WR
elif [ `expr $max_over_time \> $critical` -eq 1 ]
then
echo "CRITICAL- $num_trx TRANSACTIONS RUNNNING,go over for $max_over_time seconds"
exit $ST_CR
else
echo "OK- TRANSACTIONS RAN successfully."
exit $ST_OK
fi
fi
2,在nagios客户端添加脚本监控
先测试下脚本
[root@wgq_idc_dbm_3_61 binlog]# /usr/local/nagios/libexec/check_trx -w 30 -c 60
Warning: Using a password on the command line interface can be insecure.
Warning: Using a password on the command line interface can be insecure.
OK- TRANSACTIONS RAN successfully.
[root@wgq_idc_dbm_3_61 binlog]#
在nrpe.cfg里面添加监控命令
[root@wgq_idc_dbm_3_61 binlog]# vim /usr/local/nagios/etc/nrpe.cfg
command[check_mysql_trx]=/usr/local/nagios/libexec/check_trx -w 30 -c 60
之后重启nagios客户端监控, service nrpe restart
4,在nagios主监控服务器上面添加配置选项
先去nagios服务器上面check一下
[root@localhost etc]# /usr/local/nagios/libexec/check_nrpe -H10.254.3.61 -c check_mysql_trx
OK- TRANSACTIONS RAN successfully.
[root@localhost etc]#
在services.cfg里面添加事务监控选项:
define service{
host_name mysqlserver
service_description Check mysql transctions
check_command check_nrpe!check_mysql_trx
max_check_attempts 5
check_command check_nrpe!check_mysql_trx
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups opsweb
}
在commands.cnf里面添加事务监控命令:
# add by tim.man on 20141201
define command{
command_name check_mysql_trx
command_line $USER1$/check_mysql_trx -w $ARG1$ -c $ARG2$
}
邮件短信报警电话报警已经添加,所以无需重新配置。
然后重新加载nagios
[root@localhost objects]# service nagios reload
Running configuration check...
Reloading nagios configuration...
done
[root@localhost objects]#
5,去nagios主监控界面查看监控效果
正常监控效果:
严重监控效果:
业务报警订单提交异常,页面一直没有反应,排查后是事务没有提交或者回滚导致,想到如果及时监控事务的运行状态报警出来,那么就可以及时排查出问题所在,方便运营处理,所以自己就弄了一个shell脚本放在nagios来处理事务报警情况。
1,编写事务监控脚本
#!/bin/bash
# author: tim.man
# version: 1.0
# desc: check the RUNNING TRANSACTION over
ST_OK=0
ST_WR=1
ST_CR=2
ST_UK=3
TIME_TRX=10
# 提示信息
print_help() {
echo "$PROGNAME -w INT -c INT"
echo "Options:"
echo " -w/--warning)"
echo " Sets a warning number"
echo " -c/--critical)"
echo " Sets a critical level for io"
exit $ST_UK
}
while test -n "$1"; do
case "$1" in
-help|-h)
print_help
exit $ST_UK
;;
--warning|-w)
warning=$2
shift
;;
--critical|-c)
critical=$2
shift
;;
*)
echo "Unknown argument: $1"
print_help
exit $ST_UK
;;
esac
shift
done
get_wcdiff() {
if [ ! -z "$warning" -a ! -z "$critical" ]
then
wclvls=1
if [ ${warning} -gt ${critical} ]
then
wcdiff=1
fi
elif [ ! -z "$warning" -a -z "$critical" ]
then
wcdiff=2
elif [ -z "$warning" -a ! -z "$critical" ]
then
wcdiff=3
fi
}
# 脚本判断
val_wcdiff() {
if [ "$wcdiff" = 1 ]
then
echo "Please adjust your warning/critical thresholds. The warning must be lower than the critical level!"
exit $ST_UK
elif [ "$wcdiff" = 2 ]
then
echo "Please also set a critical value when you want to use warning/critical thresholds!"
exit $ST_UK
elif [ "$wcdiff" = 3 ]
then
echo "Please also set a warning value when you want to use warning/critical thresholds!"
exit $ST_UK
fi
}
get_wcdiff
val_wcdiff
# 统计mysql的事务中最大运行时间
max_over_time=`/usr/local/mysql/bin/mysql --user=nagios --password="nagiosq@xxx" -NS /usr/local/mysql/mysql.sock -e "SELECT TIME_TO_SEC(TIMEDIFF(NOW(),t.trx_started)) FROM information_schem
a.INNODB_TRX t WHERE TIME_TO_SEC(TIMEDIFF(NOW(),t.trx_started))>$TIME_TRX ORDER BY TIME_TO_SEC(TIMEDIFF(NOW(),t.trx_started)) DESC LIMIT 1;" |awk '{print $1}'`
# 如果当前没有RUNNING的事务,则直接赋值为0,以免下面if判断出错
if [ ! -n "$max_over_time" ];then max_over_time=0
fi
# 取得当前所以阻塞的事务数量
num_trx=`/usr/local/mysql/bin/mysql --user=nagios --password="nagiosq@xxx" -NS /usr/local/mysql/mysql.sock -e "SELECT COUNT(1) FROM information_schema.INNODB_TRX t WHERE TIME_TO_SEC(TIMEDIF
F(NOW(),t.trx_started))>$TIME_TRX;" |awk '{print $1}'`
if [ -n "$warning" -a -n "$critical" ]
then
if [ `expr $max_over_time \> $warning` -eq 1 -a `expr $max_over_time \< $critical` -eq 1 ]
then
echo "WARNING - $num_trx TRANSACTIONS RUNNING,go over for $max_over_time seconds"
exit $ST_WR
elif [ `expr $max_over_time \> $critical` -eq 1 ]
then
echo "CRITICAL- $num_trx TRANSACTIONS RUNNNING,go over for $max_over_time seconds"
exit $ST_CR
else
echo "OK- TRANSACTIONS RAN successfully."
exit $ST_OK
fi
fi
2,在nagios客户端添加脚本监控
先测试下脚本
[root@wgq_idc_dbm_3_61 binlog]# /usr/local/nagios/libexec/check_trx -w 30 -c 60
Warning: Using a password on the command line interface can be insecure.
Warning: Using a password on the command line interface can be insecure.
OK- TRANSACTIONS RAN successfully.
[root@wgq_idc_dbm_3_61 binlog]#
在nrpe.cfg里面添加监控命令
[root@wgq_idc_dbm_3_61 binlog]# vim /usr/local/nagios/etc/nrpe.cfg
command[check_mysql_trx]=/usr/local/nagios/libexec/check_trx -w 30 -c 60
之后重启nagios客户端监控, service nrpe restart
4,在nagios主监控服务器上面添加配置选项
先去nagios服务器上面check一下
[root@localhost etc]# /usr/local/nagios/libexec/check_nrpe -H10.254.3.61 -c check_mysql_trx
OK- TRANSACTIONS RAN successfully.
[root@localhost etc]#
在services.cfg里面添加事务监控选项:
define service{
host_name mysqlserver
service_description Check mysql transctions
check_command check_nrpe!check_mysql_trx
max_check_attempts 5
check_command check_nrpe!check_mysql_trx
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups opsweb
}
在commands.cnf里面添加事务监控命令:
# add by tim.man on 20141201
define command{
command_name check_mysql_trx
command_line $USER1$/check_mysql_trx -w $ARG1$ -c $ARG2$
}
邮件短信报警电话报警已经添加,所以无需重新配置。
然后重新加载nagios
[root@localhost objects]# service nagios reload
Running configuration check...
Reloading nagios configuration...
done
[root@localhost objects]#
5,去nagios主监控界面查看监控效果
正常监控效果:
![](http://blog.itpub.net/attachment/201412/3/26230597_14176119813LLe.jpg)
严重监控效果:
![](http://blog.itpub.net/attachment/201412/3/26230597_141761199890JZ.png)