一、监控本地（localhost）内存
1、上传监控脚本 check_mem 到/usr/local/nagios/libexec
|
1
2
|
# chown -R nagios.nagios check_mem
# chmod +x check_mem
|
2、修改commands配置
|
1
2
3
4
5
|
# vim /usr/local/nagios/etc/objects/commands.cfg
define
command
{
command_name check_mem
command_line $USER1$
/check_mem
-w $ARG1$ -c $ARG2$
}
|
3、修改localhost.cfg
|
1
2
3
4
5
6
7
|
# vim /usr/local/nagios/etc/objects/localhost.cfg
define service{
use
local
-service
host_name localhost
service_description check_mem
check_command check_mem!20!10
}
|
4、重启nagios服务
|
1
|
# service nagios restart
|
5、check_mem 脚本
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
|
#!/bin/bash
USAGE=
"`basename $0` [-w|--warning]<percent free> [-c|--critical]<percent free>"
THRESHOLD_USAGE=
"WARNING threshold must be greater than CRITICAL: `basename $0` $*"
calc=
/tmp/memcalc
percent_free=
/tmp/mempercent
critical=
""
warning=
""
STATE_OK=0
STATE_WARNING=1
STATE_CRITICAL=2
STATE_UNKNOWN=3
# print usage
if
[[ $
# -lt 4 ]]
then
echo
""
echo
"Wrong Syntax: `basename $0` $*"
echo
""
echo
"Usage: $USAGE"
echo
""
exit
0
fi
# read input
while
[[ $
# -gt 0 ]]
do
case
"$1"
in
-w|--warning)
shift
warning=$1
;;
-c|--critical)
shift
critical=$1
;;
esac
shift
done
# verify input
if
[[ $warning -
eq
$critical || $warning -lt $critical ]]
then
echo
""
echo
"$THRESHOLD_USAGE"
echo
""
echo
"Usage: $USAGE"
echo
""
exit
0
fi
# Total memory available
total=`
free
-m |
head
-2 |
tail
-1 |
gawk
'{print $2}'
`
# Total memory used
used=`
free
-m |
head
-2 |
tail
-1 |
gawk
'{print $3}'
`
# Calc total minus used
free
=`
free
-m |
head
-2 |
tail
-1 |
gawk
'{print $2-$3}'
`
# normal values
#echo "$total"MB total
#echo "$used"MB used
#echo "$free"MB free
# make it into % percent free = ((free mem / total mem) * 100)
echo
"5"
> $calc
# decimal accuracy
echo
"k"
>> $calc
# commit
echo
"100"
>> $calc
# multiply
echo
"$free"
>> $calc
# division integer
echo
"$total"
>> $calc
# division integer
echo
"/"
>> $calc
# division sign
echo
"*"
>> $calc
# multiplication sign
echo
"p"
>> $calc
# print
percent=`
/usr/bin/dc
$calc|
/bin/sed
's/^\./0./'
|
/usr/bin/tr
"."
" "
|
/usr/bin/gawk
{
'print $1'
}`
#percent1=`/usr/bin/dc $calc`
#echo "$percent1"
if
[[
"$percent"
-
le
$critical ]]
then
echo
"CRITICAL - $free MB ($percent%) Free Memory"
exit
2
fi
if
[[
"$percent"
-
le
$warning ]]
then
echo
"WARNING - $free MB ($percent%) Free Memory"
exit
1
fi
if
[[
"$percent"
-gt $warning ]]
then
echo
"OK - $free MB ($percent%) Free Memory"
exit
0
fi
|
二、监控客户端内存使用情况
1、上传监控脚本 check_mem 到/usr/local/nagios/libexec
|
1
2
|
# chown -R nagios.nagios check_mem
# chmod +x check_mem
|
2、修改nrpe.cfg
|
1
2
3
4
5
6
7
8
9
|
# vim /usr/local/nagios/etc/nrpe.cfg
command
[check_users]=
/usr/local/nagios/libexec/check_users
-w 3 -c 5
command
[check_load]=
/usr/local/nagios/libexec/check_load
-w 15,10,5 -c 30,25,20
command
[check_xvda]=
/usr/local/nagios/libexec/check_disk
-w 10% -c 5% -p
/dev/xvda
command
[check_zombie_procs]=
/usr/local/nagios/libexec/check_procs
-w 5 -c 10 -s Z
command
[check_total_procs]=
/usr/local/nagios/libexec/check_procs
-w 150 -c 200
command
[check_xvdb2]=
/usr/local/nagios/libexec/check_disk
-w 10% -c 5% -p
/dev/xvdb2
command
[check_swap]=
/usr/local/nagios/libexec/check_swap
-w 20% -c 10%
command
[check_mem]=
/usr/bin/sudo
/usr/local/nagios/libexec/check_mem
-w 20 -c 10
#增加此行
|
3、在nagios服务器端增加监控服务
|
1
2
3
4
5
6
7
|
# vim /usr/local/nagios/etc/servers/192.168.200.111.cfg
define service{
use generic-service
host_name 192.168.200.111
service_description check_mem
check_command check_nrpe!check_mem
}
|
三、排错
1、NRPE: Unable to read output
（1）为nagios用户增加sudo权限
|
1
2
|
# visudo
nagios ALL=(ALL) NOPASSWD:
/usr/local/nagios/libexec/check_mem
|
（2）注释掉一下行，表示不需要控制终端
|
1
2
|
# visudo
#Defaults requiretty
|
四、nagios监控mysql
1、check_mysql
nagios监控mysql使用的是 check_mysql 这个插件，需要在nagios服务器上先安装mysql-devel，然后再重新安装nagios-plugin，这样才会出现check_mysql。否则即使copy了一份，也照样用不了。
2、编译或重新编译 nagios-plugin
|
1
2
3
4
|
#yum -y install mysql-devl
#cd nagios-plugins-2.0.3
#./configure --with-nagios-user=nagios --with-nagios-group=nagios
#make && make install
|
3、查看 check_mysql
|
1
|
# ls /usr/local/nagios/libexec/check_mysql
|
4、建立专用数据库
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
|
# mysql -uroot -p
mysql> create database nagios_monitor;
mysql> grant
select
on nagios_monitor.* to nagios@
'%'
identified by
'123qaz!@#'
;
Query OK, 0 rows affected (0.00 sec)
mysql> flush privileges;
Query OK, 0 rows affected (0.00 sec)
mysql>
select
User,Password,Host from mysql.user;
+--------+-------------------------------------------+--------------+
| User | Password | Host |
+--------+-------------------------------------------+--------------+
| root | *B9627CB37815863D1E98D0C41E0233A772355E2B | localhost |
| root | *B9627CB37815863D1E98D0C41E0233A772355E2B | 127.0.0.1 |
| root | *B9627CB37815863D1E98D0C41E0233A772355E2B | ::1 |
| cacti | *BC3E1F14C7940F9C8BCDB05A38385754BB55CD64 | localhost |
| nagios | *BC3E1F14C7940F9C8BCDB05A38385754BB55CD64 | % |
+--------+-------------------------------------------+--------------+
8 rows
in
set
(0.00 sec)
|
5、check 一下
|
1
2
3
4
5
6
7
8
|
# /usr/local/nagios/libexec/check_mysql -H 192.168.200.105 -unagios -dnagios_monitor -p 123qaz!@#
# 报了一个错
/usr/local/nagios/libexec/check_mysql
: error
while
loading shared libraries: libmysqlclient.so.18: cannot
open
shared object
file
: No such
file
or directory
# 解决：
ln
-sv
/usr/local/mysql/lib/libmysqlclient
.so.18
/usr/lib64/libmysqlclient
.so.18
# 再重新测试
# /usr/local/nagios/libexec/check_mysql -H 192.168.200.111 -unagios -dnagios_monitor -p 123qaz!@#
Uptime: 13991 Threads: 5 Questions: 1242101 Slow queries: 0 Opens: 159 Flush tables: 1 Open tables: 60 Queries per second avg: 88.778|Connections=315c;;; Open_files=85;;; Open_tables=60;;; Qcache_free_memory=16285768;;; Qcache_hits=1210926c;;; Qcache_inserts=16654c;;; Qcache_lowmem_prunes=0c;;; Qcache_not_cached=2c;;; Qcache_queries_in_cache=283;;; Queries=1242101c;;; Questions=1242101c;;; Table_locks_waited=2c;;; Threads_connected=5;;; Threads_running=1;;; Uptime=13991c;;;
|
6、监控localhost
（1）修改 commands.cfg
|
1
2
3
4
5
|
# vim /usr/local/nagios/etc/objects/commands.cfg
define
command
{
command_name check_mysql
command_line $USER1$
/check_mysql
-H $HOSTADDRESS$ -unagios -dnagios_monitor -p123qaz!@
#
}
|
（2）修改 localhost.cfg
|
1
2
3
4
5
6
7
|
# vim /usr/local/nagios/etc/objects/localhost.cfg
define service{
use
local
-service
host_name localhost
service_description check_mysql
check_command check_mysql
}
|
（3）重启 nagios
|
1
|
# service nagios restart
|
7、监控客户端
（1）check 一下
|
1
|
# /usr/local/nagios/libexec/check_mysql -H 192.168.200.111 -unagios -dnagios_monitor -p123qaz!@#
|
（2）客户端修改 nrpe.cfg
|
1
2
|
# vim /usr/local/nagios/etc/nrpe.cfg
command
[check_mysql]=
/usr/local/nagios/libexec/check_mysql
-H 192.168.200.111 -unagios -dnagios_monitor -p123qaz!@
#
|
（3）重启 nrpe
|
1
2
|
# killall nrpe
# /usr/local/nagios/bin/nrpe -c /usr/local/nagios/etc/nrpe.cfg -d
|
（4）服务端定义服务
|
1
2
3
4
5
6
7
|
# vim /usr/local/nagios/etc/servers/192.168.200.111.cfg
define service{
use generic-service
host_name 192.168.200.111
service_description check_mysql
check_command check_nrpe!check_mysql
}
|
（5）重启 nagios 服务
|
1
|
# service nagios restart
|
本文转自 nmshuishui 51CTO博客，原文链接：http://blog.51cto.com/nmshuishui/1553445，如需转载请自行联系原作者
