nagios插件:通过snmp采集数据并实现告警(原创).

本插件主要功能是可以通过一个OID采集一个数据,并设置告警阀值，将处理结果返回给nagios来处理。

应用场景：如监查各类设备的CPU是否过高，或某条带宽线路是否拥塞等等。

 

代码如下

#!/usr/bin/perl
# Version : 0.1
# Date : 2012-04-05

# Licence : GPL - http://www.fsf.org/licenses/gpl.txt

# help perldoc Net::SNMP

use strict;
use Net::SNMP;
use Getopt::Std;


my $script = GetScriptName($0);
my $script_version = "0.1";


my $ipaddress = "127.0.0.1";
my $port = 161;
my $version = "snmpv2c";
my $community = "public";
my $vOID = '1.3.6.1.4.1.9.2.2.1.1.3.1';
my $timeout = 2;
my $warning = 90;
my $critical = 95;
my $vMAX = 100;
my $status = 0;
my $returnstring = "";
my $temp = 5;

if (@ARGV < 1) {
     print "Too few arguments\n";
     usage();
}

my %opt=();
getopts("hvH:p:C:o:w:c:m:t:",\%opt);

if($opt{h} || $opt{v})
{
    usage();
    exit(0);
}

$ipaddress = $opt{H} if defined $opt{H} ;
$port = $opt{p} if defined $opt{p} ;
$community = $opt{C} if defined $opt{C} ;
$vOID = $opt{o} if defined $opt{o} ;
$warning = $opt{w} if defined $opt{w} ;
$critical = $opt{c} if defined $opt{c} ;
$vMAX = $opt{m} if defined $opt{m} ;

#print "-H $ipaddress\n";
#print "-p $port\n";
#print "-C $community\n";
#print "-o $vOID\n";
#print "-w $warning\n";
#print "-c $critical\n";
#print "-m $vMAX\n";

# Create the SNMP session
my ($session, $error) = Net::SNMP->session(
     -community => $community,
     -hostname => $ipaddress,
     -port => $port,
     -version => $version,
     -timeout => $timeout

main();

# Close the session
$session->close();

if ($returnstring eq ""){
    $status = 3;
}

if ($status == 0){
    print "Status is OK - $returnstring\n";
    # print "$returnstring\n";
}
elsif ($status == 1){
    print "Status is a WARNING level - $returnstring\n";
}
elsif ($status == 2){
    print "Status is CRITICAL - $returnstring\n";
}
else{
    print "Status is UNKNOWN\n";
}

exit $status;


####################################################################
# sub program #
####################################################################
sub main()
{
    my $result = $session->get_request(-varbindlist=>[$vOID]);
    my $len = length($result->{$vOID});
    if ( $len == 0)
    {
       $status =3;
    }
    else
    {
       my $OID_value = $result->{$vOID};
       $returnstring = "Current $OID_value,OK:0-$warning,Warning:$warning-$critical,Critical:$critical-$vMAX | $vOID=$OID_value\n";
       $status =0 if( $OID_value <= $warning );
       $status =1 if( ($OID_value > $warning) && ($OID_value <= $critical) );
       $status =2 if( $OID_value > $critical );
    }
}



sub usage {
    print << "USAGE";
--------------------------------------------------------------------
$script v$script_version

SnmpGet on All devices

Usage: $script -H <hostname> -C <community> [...]
Options: -H Hostname or IP address
                 -p snmp port(default is tcp161)
                 -v snmp Version(default is v2c)
                 -o snmp OID
                 -C Community (default is public)
                 -w Warning threshold
                 -c Critical threshold
                 -m MAX vlaue
                 -h or -v Help

--------------------------------------------------------------------

This program is free software; you can redistribute it or modify
it under the terms of the GNU General Public License
--------------------------------------------------------------------

USAGE
     exit 1;
}


sub GetScriptName
{
   my @str = @_;
   my $len = rindex($str[0],"/");
   return substr($str[0],$len + 1);
}

使用说明

step1:

    将check_snmp_perl.pl复制到nagios脚本目录，并设置可执行权限。

step2:

     在nagios中定义命令，代码如下：

#vi /usr/local/nagios/etc/objects/commands.cfg
...
define command{
        command_name check_perl
        command_line $USER1$/check_snmp_perl -H $HOSTADDRESS$ -C $ARG1$ -o $ARG2$ -w $ARG3$ -c $ARG4$ -m $ARG5$
        }

step3:定义对像

#vi /usr/local/nagios/etc/objects/list/ciscoCPU254.cfg
;Host monitor
define host {
        use generic-switch
        host_name cisco3750-1.254
        address 10.1.1.2
        active_checks_enabled 0
}
;SNMP test
define service{
        use generic-service
        host_name cisco3750-1.254
        service_description SNMP-cpu
        check_command check_perl!abc123!1.3.6.1.4.1.9.9.109.1.1.1.1.3.1!50!80!100
        check_interval 0.3
        retry_interval 0.1
        max_check_attempts 2
        notifications_enabled 1
        notification_interval 120
        notification_period 24x7
        notification_options w,u,c,r
        contact_groups IDC-group

step4:

#vi /usr/local/nagios/etc/nagios.cfg
cfg_file=/usr/local/nagios/etc/objects/list/ciscoCPU254.cfg

service nagios restart

 

结果如图所示：