zabbix自定义监控
zabbix自定义监控
- 进程监控
- 日志文件监控
- mysql主从状态监控
- mysql主从延迟监控
环境
server端：192.168.147.44
agent端：192.168.147.10
在agent端安装agent
将server端的zabbix-5.2.6的包传到agent端上
[root@localhost ~]# scp zabbix-5.2.6.tar.gz 192.168.147.10:/root/
The authenticity of host '192.168.147.10 (192.168.147.10)' can't be established.
ECDSA key fingerprint is SHA256:gSsPLJ32lTw4VyltfgKSGM3YOoC/tgzVRHXPrX8hyVY.
Are you sure you want to continue connecting (yes/no/[fingerprint])? yes
Warning: Permanently added '192.168.147.10' (ECDSA) to the list of known hosts.
root@192.168.147.10's password:
zabbix-5.2.6.tar.gz 100% 20MB 16.8MB/s 00:01
在agent端解压传过去的文件
[root@localhost ~]# tar xf zabbix-5.2.6.tar.gz
[root@localhost ~]# ls
公共 视频 文档 音乐 anaconda-ks.cfg zabbix-5.2.6
模板 图片 下载 桌面 initial-setup-ks.cfg zabbix-5.2.6.tar.gz
安装需要的安装包
[root@localhost zabbix-5.2.6]# useradd -r -M -s /sbin/nologin zabbix
[root@localhost ~]# dnf -y install gcc gcc-c++ make pcre-devel
编译安装agent
[root@localhost ~]# cd zabbix-5.2.6/
[root@localhost zabbix-5.2.6]# ./configure --enable-agent
........
***********************************************************
* Now run 'make install' *
* *
* Thank you for using Zabbix! *
* <http://www.zabbix.com> *
***********************************************************
[root@localhost zabbix-5.2.6]# make install
[root@localhost etc]# ls
zabbix_agentd.conf zabbix_agentd.conf.d
[root@localhost etc]# vim zabbix_agentd.conf
113 Server=192.168.147.44 //server端的ip
154 ServerActive=192.168.147.44 //server端的ip
165 Hostname=node3 //可是任意指定，最好是随机数
进程监控
在web界面创建一个主机
[root@localhost ~]# dnf -y install httpd //安装httpd
[root@localhost ~]# systemctl start httpd //启动httpd
[root@localhost ~]# ss -antl //有80端口
State Recv-Q Send-Q Local Address:Port Peer Address:Port Process
LISTEN 0 128 0.0.0.0:111 0.0.0.0:*
LISTEN 0 128 0.0.0.0:22 0.0.0.0:*
LISTEN 0 5 127.0.0.1:631 0.0.0.0:*
LISTEN 0 128 0.0.0.0:10050 0.0.0.0:*
LISTEN 0 128 [::]:111 [::]:*
LISTEN 0 128 *:80 *:*
LISTEN 0 80 *:2001 *:*
LISTEN 0 80 *:2002 *:*
LISTEN 0 80 *:2003 *:*
LISTEN 0 128 [::]:22 [::]:*
LISTEN 0 5 [::1]:631 [::]:*
httpd安装完成
[root@localhost ~]# cd /usr/local/etc/
[root@localhost etc]# ls
zabbix_agentd.conf zabbix_agentd.conf.d
[root@localhost etc]# vim zabbix_agentd.conf
UnsafeUserParameters=1 //将这行取消注释 并将数值改为1
在agent端
[root@localhost ~]# mkdir /scripts
[root@localhost ~]# cd /scripts
[root@localhost scripts]# ls
[root@localhost scripts]# vim check_process.sh //写进程监控的脚本
#!/bin/bash
process_status=$(ps -ef|grep -Ev "grep|$0"|grep -c $1)
if [ $process_status -eq 0 ];then
echo '1'
else
echo '0'
fi
[root@localhost etc]# pkill zabbix //重启zabbix
[root@localhost etc]# zabbix_agentd
[root@localhost scripts]# chmod +x check_process.sh //给脚本x的权限
[root@localhost scripts]# ll
总用量 4
-rwxr-xr-x. 1 root root 133 5月 19 19:09 check_process.sh
测试脚本
[root@localhost ~]# systemctl start httpd
[root@localhost ~]# su - zabbix -s /bin/bash
su: 警告：无法更改到 /home/zabbix 目录: 没有那个文件或目录
[zabbix@localhost root]$ /scripts/check_process.sh httpd
0
[zabbix@localhost root]$ ps -ef|grep -v grep|grep -c httpd
5
[root@localhost etc]# vim zabbix_agentd.conf //在文本最后添加下列一行内容
UserParameter=check_process[*],/bin/bash /scripts/check_process.sh $1
[root@localhost etc]# pkill zabbix
[root@localhost etc]# zabbix_agentd
在server端
[root@localhost ~]# systemctl start httpd
[root@localhost ~]# zabbix_get -s 192.168.147.10 -k check_process['httpd']
0
添加监控项
查看是否有数据
再关闭httpd再次查看
添加触发器
开启声音报警
测试
[root@localhost ~]# systemctl stop httpd
[root@localhost ~]# ss -antl
State Recv-Q Send-Q Local Address:Port Peer Address:Port Process
LISTEN 0 128 0.0.0.0:111 0.0.0.0:*
LISTEN 0 128 0.0.0.0:22 0.0.0.0:*
LISTEN 0 5 127.0.0.1:631 0.0.0.0:*
LISTEN 0 128 0.0.0.0:10050 0.0.0.0:*
LISTEN 0 128 [::]:111 [::]:*
LISTEN 0 80 *:2001 *:*
LISTEN 0 80 *:2002 *:*
LISTEN 0 80 *:2003 *:*
LISTEN 0 128 [::]:22 [::]:*
LISTEN 0 5 [::1]:631 [::]:*
报警启动
日志文件监控
将写好的脚本拖入到scripts里
log.py
作用：检查日志文件中是否有指定的关键字
第一个参数为日志文件名（必须有，相对路径、绝对路径均可）
第二个参数为seek position文件的路径(可选项，若不设置则默认为/tmp/logseek文件，相对路径、绝对路径均可）
第三个参数为搜索关键字，默认为Error
查看日志文件
[root@localhost scripts]# cat log.py
#!/usr/bin/env python3
import sys
import re
def prePos(seekfile):
global curpos
try:
cf = open(seekfile)
except IOError:
curpos = 0
return curpos
except FileNotFoundError:
curpos = 0
return curpos
else:
try:
curpos = int(cf.readline().strip())
except ValueError:
curpos = 0
cf.close()
return curpos
cf.close()
return curpos
def lastPos(filename):
with open(filename) as lfile:
if lfile.readline():
lfile.seek(0,2)
else:
return 0
lastPos = lfile.tell()
return lastPos
def getSeekFile():
try:
seekfile = sys.argv[2]
except IndexError:
seekfile = '/tmp/logseek'
return seekfile
def getKey():
try:
tagKey = str(sys.argv[3])
except IndexError:
tagKey = 'Error'
return tagKey
def getResult(filename,seekfile,tagkey):
destPos = prePos(seekfile)
curPos = lastPos(filename)
if curPos < destPos:
curpos = 0
try:
f = open(filename)
except IOError:
print('Could not open file: %s' % filename)
except FileNotFoundError:
print('Could not open file: %s' % filename)
else:
f.seek(destPos)
while curPos != 0 and f.tell() < curPos:
rresult = f.readline().strip()
global result
if re.search(tagkey, rresult):
result = 1
break
else:
result = 0
with open(seekfile,'w') as sf:
sf.write(str(curPos))
finally:
f.close()
return result
if __name__ == "__main__":
result = 0
curpos = 0
tagkey = getKey()
seekfile = getSeekFile()
result = getResult(sys.argv[1],seekfile,tagkey)
print(result)
给脚本执行权限
[root@localhost ~]# chmod +x /scripts/log.py
[root@localhost ~]# ll /scripts/log.py
-rwxr-xr-x. 1 root root 1854 5月 19 20:31 /scripts/log.py
[root@localhost scripts]# which python3 //这里如果没有，就需要安装
/usr/bin/python3
测试脚本
[root@localhost ~]# ls /var/log/httpd/
access_log error_log
[root@localhost scripts]# setfacl -m u:zabbix:rx /var/log/httpd/
[root@localhost scripts]# mkdir /zabbix_item_log
[root@localhost scripts]# chown -R zabbix.zabbix /zabbix_item_log/
[root@localhost scripts]# cd
[root@localhost ~]# su - zabbix -s /bin/bash
su: 警告：无法更改到 /home/zabbix 目录: 没有那个文件或目录
[zabbix@localhost root]$ python3 /scripts/log.py /var/log/httpd/error_log /zabbix_item_log/logseek Failed
0
编写配置文件
[root@localhost etc]# vim zabbix_agentd.conf //在配置文件中添加下列这一行
UserParameter=check_logs[*],/scripts/log.py $1 $2 $3
[root@localhost etc]# pkill zabbix //重启zabbix
[root@localhost etc]# zabbix_agentd
server端
[root@localhost ~]# zabbix_get -s 192.168.147.10 -k check_logs['/var/log/httpd/error_log','zabbix_item_log/logseek','Failed']
0
agent端
[root@localhost ~]# echo 'Failed' >> /var/log/httpd/error_log
[root@localhost ~]# cat /zabbix_item_log/logseek
6389
server端
[root@localhost ~]# zabbix_get -s 192.168.147.10 -k check_logs['/var/log/httpd/error_log','zabbix_item_log/logseek','Failed']
1
手动触发
[root@localhost ~]# echo 'Failed' >> /var/log/httpd/error_log
mysql主从状态监控
使用多实例部署来做
有实例2001、2002
将实例2001作为主
2002作为从
[root@localhost ~]# ss -antl
State Recv-Q Send-Q Local Address:Port Peer Address:Port Process
LISTEN 0 128 0.0.0.0:111 0.0.0.0:*
LISTEN 0 128 0.0.0.0:22 0.0.0.0:*
LISTEN 0 5 127.0.0.1:631 0.0.0.0:*
LISTEN 0 128 0.0.0.0:10050 0.0.0.0:*
LISTEN 0 128 [::]:111 [::]:*
LISTEN 0 128 *:80 *:*
LISTEN 0 80 *:2001 *:*
LISTEN 0 80 *:2002 *:*
LISTEN 0 80 *:2003 *:*
LISTEN 0 128 [::]:22 [::]:*
LISTEN 0 5 [::1]:631 [::]:*
进入实例2001
[root@localhost ~]# mysql -uroot -p'123.com.' -P2001 -h127.0.0.1
mysql> grant replication slave on *.* to 'repl'@'127.0.0.1' identified by 'repl123!';
Query OK, 0 rows affected, 1 warning (1.26 sec)
mysql> flush privileges;
Query OK, 0 rows affected (0.72 sec)
[root@localhost ~]# vim /etc/my.cnf
[mysqld2001]
datadir = /opt/data/2001
port = 2001
socket = /tmp/mysql2001.sock
pid-file = /opt/data/2001/mysql_2001.pid
log-error=/var/log/2001.log
server-id = 10 //加入这一行
log-bin = mybin //加入这一行
重启实例2001
[root@localhost ~]# ps -ef|grep 2001
root 973 1 0 15:22 ? 00:00:00 /bin/sh /usr/local/mysql/bin/mysqld_safe --datadir=/opt/data/2001 --port=2001 --socket=/tmp/mysql2001.sock --pid-file=/opt/data/2001/mysql_2001.pid --log-error=/var/log/2001.log
mysql 1381 973 0 15:22 ? 00:00:22 /usr/local/mysql/bin/mysqld --basedir=/usr/local/mysql --datadir=/opt/data/2001 --plugin-dir=/usr/local/mysql/lib/plugin --user=mysql --log-error=/var/log/2001.log --pid-file=/opt/data/2001/mysql_2001.pid --socket=/tmp/mysql2001.sock --port=2001
root 902282 189591 0 21:13 pts/0 00:00:00 grep --color=auto 2001
[root@localhost ~]# kill -9 973 1381
[root@localhost ~]# ss -antl
State Recv-Q Send-Q Local Address:Port Peer Address:Port Process
LISTEN 0 128 0.0.0.0:111 0.0.0.0:*
LISTEN 0 128 0.0.0.0:22 0.0.0.0:*
LISTEN 0 5 127.0.0.1:631 0.0.0.0:*
LISTEN 0 128 0.0.0.0:10050 0.0.0.0:*
LISTEN 0 128 [::]:111 [::]:*
LISTEN 0 128 *:80 *:*
LISTEN 0 80 *:2002 *:*
LISTEN 0 80 *:2003 *:*
LISTEN 0 128 [::]:22 [::]:*
LISTEN 0 5 [::1]:631 [::]:*
[root@localhost ~]# mysqld_multi start 2001
[root@localhost ~]# ss -antl
State Recv-Q Send-Q Local Address:Port Peer Address:Port Process
LISTEN 0 128 0.0.0.0:111 0.0.0.0:*
LISTEN 0 128 0.0.0.0:22 0.0.0.0:*
LISTEN 0 5 127.0.0.1:631 0.0.0.0:*
LISTEN 0 128 0.0.0.0:10050 0.0.0.0:*
LISTEN 0 128 [::]:111 [::]:*
LISTEN 0 128 *:80 *:*
LISTEN 0 80 *:2001 *:*
LISTEN 0 80 *:2002 *:*
LISTEN 0 80 *:2003 *:*
LISTEN 0 128 [::]:22 [::]:*
LISTEN 0 5 [::1]:631 [::]:*
mysql> show master status;
+--------------+----------+--------------+------------------+-------------------+
| File | Position | Binlog_Do_DB | Binlog_Ignore_DB | Executed_Gtid_Set |
+--------------+----------+--------------+------------------+-------------------+
| mybin.000001 | 154 | | | |
+--------------+----------+--------------+------------------+-------------------+
1 row in set (0.12 sec)
进入2002
[root@localhost ~]# mysql -uroot -p'123.com.' -P2002 -h127.0.0.1
[root@localhost ~]# vim /etc/my.cnf
[mysqld2002]
datadir = /opt/data/2002
port = 2002
socket = /tmp/mysql2002.sock
pid-file = /opt/data/2002/mysql_2002.pid
log-error=/var/log/2002.log
server-id = 20 //加入这行
relay-log = myrelay //加入这行
重启实例2002
[root@localhost ~]# ps -ef|grep 2002
root 979 1 0 15:22 ? 00:00:00 /bin/sh /usr/local/mysql/bin/mysqld_safe --datadir=/opt/data/2002 --port=2002 --socket=/tmp/mysql2002.sock --pid-file=/opt/data/2002/mysql_2002.pid --log-error=/var/log/2002.log
mysql 1378 979 0 15:22 ? 00:00:22 /usr/local/mysql/bin/mysqld --basedir=/usr/local/mysql --datadir=/opt/data/2002 --plugin-dir=/usr/local/mysql/lib/plugin --user=mysql --log-error=/var/log/2002.log --pid-file=/opt/data/2002/mysql_2002.pid --socket=/tmp/mysql2002.sock --port=2002
root 923555 191915 0 21:34 pts/3 00:00:00 mysql -uroot -px xxxxxx -P2002 -h127.0.0.1
root 924832 189591 0 21:37 pts/0 00:00:00 grep --color=auto 2002
[root@localhost ~]# kill -9 979 1378 923555
[root@localhost ~]# ss -antl
State Recv-Q Send-Q Local Address:Port Peer Address:Port Process
LISTEN 0 128 0.0.0.0:111 0.0.0.0:*
LISTEN 0 128 0.0.0.0:22 0.0.0.0:*
LISTEN 0 5 127.0.0.1:631 0.0.0.0:*
LISTEN 0 128 0.0.0.0:10050 0.0.0.0:*
LISTEN 0 128 [::]:111 [::]:*
LISTEN 0 128 *:80 *:*
LISTEN 0 80 *:2001 *:*
LISTEN 0 80 *:2003 *:*
LISTEN 0 128 [::]:22 [::]:*
LISTEN 0 5 [::1]:631 [::]:*
root@localhost ~]# /usr/local/mysql/bin/mysqld_multi start 2002
Wide character in print at /usr/local/mysql/bin/mysqld_multi line 678.
[root@localhost ~]# ss -antl
State Recv-Q Send-Q Local Address:Port Peer Address:Port Process
LISTEN 0 128 0.0.0.0:111 0.0.0.0:*
LISTEN 0 128 0.0.0.0:22 0.0.0.0:*
LISTEN 0 5 127.0.0.1:631 0.0.0.0:*
LISTEN 0 128 0.0.0.0:10050 0.0.0.0:*
LISTEN 0 128 [::]:111 [::]:*
LISTEN 0 128 *:80 *:*
LISTEN 0 80 *:2001 *:*
LISTEN 0 80 *:2002 *:*
LISTEN 0 80 *:2003 *:*
LISTEN 0 128 [::]:22 [::]:*
LISTEN 0 5 [::1]:631 [::]:*
配置2002
mysql> change master to \
-> master_host='127.0.0.1',
-> master_user='repl',
-> master_password='repl123!',
-> master_log_file='mybin.000001',
-> master_log_pos=154;
ERROR 2006 (HY000): MySQL server has gone away
No connection. Trying to reconnect...
Connection id: 2
Current database: *** NONE ***
Query OK, 0 rows affected, 1 warning (0.02 sec)
mysql> start slave;
Query OK, 0 rows affected (0.01 sec)
mysql> show slave status\G
*************************** 1. row ***************************
Slave_IO_State: Waiting for master to send event
Master_Host: 127.0.0.1
Master_User: repl
Master_Port: 2002
Connect_Retry: 60
Master_Log_File: mybin.000001
Read_Master_Log_Pos: 154
Relay_Log_File: myrelay.000002
Relay_Log_Pos: 316
Relay_Master_Log_File: mybin.000001
Slave_IO_Running: Yes
Slave_SQL_Running: Yes
[root@localhost ~]# mysql -uroot -p'123.com' -P2002 -h127.0.0.1 -e 'show slave status\G' | grep "Running: Yes"
mysql: [Warning] Using a password on the command line interface can be insecure.
Slave_IO_Running: Yes
Slave_SQL_Running: Yes
[root@localhost ~]# mysql -uroot -p'123.com' -P2002 -h127.0.0.1 -e 'show slave status\G' | grep "Running: Yes"|awk '{print $2}'|grep -c 'Yes'
mysql: [Warning] Using a password on the command line interface can be insecure.
2
-c 取出数值
编写脚本
[root@localhost scripts]# vim check_mysql_replistatus.sh
[root@localhost scripts]# cat check_mysql_replistatus.sh
#!/bin/bash
mysql=/usr/local/mysql/bin/mysql
status=$($mysql -uroot -p'123.com' -P2002 -h127.0.0.1 -e 'show slave status\G' | grep "Running: Yes"|awk '{print $2}'|grep -c 'Yes')
if [ $status -ne 2 ];then
echo '1'
else
echo '0'
fi
给脚本权限
[root@localhost scripts]# chmod +x check_mysql_replistatus.sh
[root@localhost ~]# mysql -uroot -p'123.com' -P2002 -h127.0.0.1 -e 'show slave status\G' | grep "Running: Yes"|awk '{print $2}'|grep -c 'Yes'
mysql: [Warning] Using a password on the command line interface can be insecure.
2
启动脚本
[zabbix@localhost scripts]$ ./check_mysql_replistatus.sh
mysql: [Warning] Using a password on the command line interface can be insecure.
0 //数值为0，说明没有问题
测试
[root@localhost scripts]# mysql -uroot -p'123.com' -P2002 -h127.0.0.1 -e 'stop slave;'
mysql: [Warning] Using a password on the command line interface can be insecure.
[root@localhost scripts]# mysql -uroot -p'123.com' -P2002 -h127.0.0.1 -e 'show slave status\G'
mysql: [Warning] Using a password on the command line interface can be insecure.
*************************** 1. row ***************************
Slave_IO_State:
Master_Host: 127.0.0.1
Master_User: repl
Master_Port: 3306
Connect_Retry: 60
Master_Log_File: mybin.000001
Read_Master_Log_Pos: 154
Relay_Log_File: myrelay.000002
Relay_Log_Pos: 316
Relay_Master_Log_File: mybin.000001
Slave_IO_Running: No
Slave_SQL_Running: No
//停止从库
[zabbix@localhost scripts]$ ./check_mysql_replistatus.sh
mysql: [Warning] Using a password on the command line interface can be insecure.
1
编写配置文件
[root@localhost ~]# vim zabbix_agentd.conf
//在配置文件中添加这一行
UserParameter=check_mysql_replication,/scripts/check_mysql_replistatus.sh
[root@localhost etc]# pkill zabbix
[root@localhost etc]# zabbix_agentd
server端
[root@localhost ~]# zabbix_get -s 192.168.147.10 -k check_mysql_replication
mysql: [Warning] Using a password on the command line interface can be insecure.
1
mysql主从延迟监控
取出主从延迟的值
[root@localhost scripts]# mysql -uroot -p'123.com' -P2002 -h127.0.0.1 -e 'show slave status\G'|grep 'Seconds_Behind_Master'
mysql: [Warning] Using a password on the command line interface can be insecure.
Seconds_Behind_Master: 0
[root@localhost scripts]# mysql -uroot -p'123.com' -P2002 -h127.0.0.1 -e 'show slave status\G'|grep 'Seconds_Behind_Master'|awk '{print $2}'
mysql: [Warning] Using a password on the command line interface can be insecure.
0
编辑脚本
[root@localhost scripts]# vim check_mysql_delay.sh
[root@localhost scripts]# cat check_mysql_delay.sh
#!/bin/bash
delay=$(mysql -uroot -p'123.com' -P2002 -h127.0.0.1 -e 'show slave status\G'|grep 'Seconds_Behind_Master'|awk '{print $2}')
echo $delay
给脚本权限
[root@localhost scripts]# chmod +x check_mysql_delay.sh
[root@localhost scripts]# ./check_mysql_delay.sh
mysql: [Warning] Using a password on the command line interface can be insecure.
0
编辑配置文件
[root@localhost etc]# vim zabbix_agentd.conf
UserParameter=check_mysql_delay,/scripts/check_mysql_delay.sh
[root@localhost etc]# pkill zabbix
[root@localhost etc]# zabbix_agentd
server端执行
[root@localhost ~]# zabbix_get -s 192.168.147.10 -k check_mysql_delay
mysql: [Warning] Using a password on the command line interface can be insecure.
0
