python脚本监控Linux磁盘空间使用率

【转载】http://blog.chinaunix.net/uid-26978448-id-3408364.html

#cat check_snmp_storage.py

 

 

#!
/
usr/
bin/
python
#_*
_ coding:
 utf-
8 _*
_
#_*
_ coding:
 cp950 _*
_

''
'
Create date: 2012-10-30
Last update: 2012-10-30
Version: 1.0
Description: Monitor Disk usage
Author: Victor
QQ:1409175531
'''

import
 sys
import
 netsnmp
from
 decimal import
 *


def
 help(
)
:
  print
 ''
'Usage:
sys.argv[0] <Community> <Host> <Device> <Warning_threshold> <Critical_threshold>'''


if
 len(
sys.
argv)
 <
 6:
  help(
)
  sys.
exit(
3)
elif
 sys.
argv[
4]
 >
 sys.
argv[
5]
:
  print
 'Critical_threshold must be more than Warning_threshold'
  sys.
exit(
3)


try
:
  session =
 netsnmp.
Session(
Version=
2,
 Community=
sys.
argv[
1]
,
 DestHost=
sys.
argv[
2]
)
except
 IndexError
:
  sys.
exit(
3)

oid01 =
 netsnmp.
Varbind(
'hrStorageDescr'
)
oid02 =
 netsnmp.
Varbind(
'hrStorageSize'
)
oid03 =
 netsnmp.
Varbind(
'hrStorageUsed'
)
oid04 =
 netsnmp.
Varbind(
'hrStorageAllocationUnits'
)

oidlist01 =
 netsnmp.
VarList(
oid01)
oidlist02 =
 netsnmp.
VarList(
oid02)
oidlist03 =
 netsnmp.
VarList(
oid03)
oidlist04 =
 netsnmp.
VarList(
oid04)

rl01 =
 session.
walk(
oidlist01)
rl02 =
 session.
walk(
oidlist02)
rl03 =
 session.
walk(
oidlist03)
rl04 =
 session.
walk(
oidlist04)

try
:
  units =
 dict(
zip(
rl01,
rl04)
)
[
sys.
argv[
3]
]
  total =
 Decimal(
dict(
zip(
rl01,
rl02)
)
[
sys.
argv[
3]
]
)
 *
 Decimal(
units)
 /
 Decimal(
1024)
 /
 Decimal(
1024)
  used_1 =
 dict(
zip(
rl01,
rl03)
)
[
sys.
argv[
3]
]
  used_2 =
 Decimal(
used_1)
 *
 Decimal(
units)
 /
 Decimal(
1024)
 /
 Decimal(
1024)
except
 KeyError
:
  print
 'Timeout or please check syntax/community/Host or other params.'
  sys.
exit(
3)

getcontext(
)
.
prec =
 2

used_percent =
 int(
Decimal(
used_2)
 /
 Decimal(
total)
 *
 Decimal(
100)
)

warning =
 Decimal(
total)
 *
 Decimal(
sys.
argv[
4]
)
w_threshold =
 int(
warning)
w_percent =
 Decimal(
sys.
argv[
4]
)
 *
 Decimal(
100)

critical =
 Decimal(
total)
 *
 Decimal(
sys.
argv[
5]
)
c_threshold =
 int(
critical)
c_percent =
 Decimal(
sys.
argv[
5]
)
 *
 Decimal(
100)

if
 used_percent <
 w_percent:
  print
 'OK - "%s" 使用了:%s%% | 总容量:%s MB , 已使用:%s MB (w:%s%%, c:%s%%)'
 %
 (
sys.
argv[
3]
,
 used_percent,
 int(
total)
,
 int(
used_2)
,
 w_percent,
 c_percent)
  sys.
exit(
0)
elif
 c_percent >
 used_percent >
=
 w_percent:
  print
 'Warning - "%s" 使用了:%s%% | 总容量:%s MB , 已使用:%s MB (w:%s%%, c:%s%%)'
 %
 (
sys.
argv[
3]
,
 used_percent,
 int(
total)
,
 int(
used_2)
,
 w_percent,
 c_percent)
  sys.
exit(
1)
elif
 used_percent >
 c_percent:
  print
 'Critical - "%s" 使用了:%s%% | 总容量:%s MB , 已使用:%s MB (w:%s%%, c:%s%%)'
 %
 (
sys.
argv[
3]
,
 used_percent,
 int(
total)
,
 int(
used_2)
,
 w_percent,
 c_percent)
  sys.
exit(
2)
elif
 not
 used_2:
  print
 'Unknown'
  sys.
exit(
3)
else
:
  print
 'Unknown'
  sys.
exit(
3)

 

 

 

 

 

将脚本check_snmp_storage.py放到/usr/local/nagios/libexec目录下,给执行权限。直接执行脚本可以看到脚本的用法：

#python check_snmp_storage.py 

Usage:

sys.argv[0] <Community> <Host> <Device> <Warning_threshold> <Critical_threshold>

    <Device>  设备名，如“Physical memory”、“Swap space”、 “/usr/local”等，如果不确定设备名，可先使用snmpdf查看，如：

<Device>  需要与上图Description列的名字吻合，大小写必须一致，否则脚本通过snmp去取数据时会找不到设备。

    <Warning_threshold> 和<Critical_threshold>是报警阀值，用小数点表示，如0.8表示80%，0.9表示90%。

举例：

commands.cfg配置如下：

define command{

    command_name check_snmp_storage

    command_line $USER1$/check_snmp_storage.py $ARG1$ $HOSTADDRESS$ $ARG2$ $ARG3$ $ARG4$ $ARG5$

}

services.cfg配置如下：

define service{

        use                             service02

        host_name                   test

        service_description       Mem

        notifications_enabled     0

        check_command          check_snmp_storage_v4!public!'Physical memory'!0.85!0.9

}

以上完成后重启nagios服务，效果图如下：