Monitoring openvz resources using nagios and snmp

snmpd configuration

Debian Etch example:

apt-get install snmpd

edit /etc/default/snmpd : remove -u snmp and repleace 127.0.0.1 witch your ip, Full/etc/default/snmpd example:

export MIBDIRS=/usr/share/snmp/mibs
SNMPDRUN=yes
SNMPDOPTS='-Lsd -Lf /dev/null  -I -smux -p /var/run/snmpd.pid 207.46.250.119'
TRAPDRUN=no
TRAPDOPTS='-Lsd -p /var/run/snmptrapd.pid'

Create user(my_username) and add new mib:

/etc/init.d/snmpd stop
echo rouser my_username priv > /etc/snmp/snmpd.conf
echo "extend  .1.3.6.1.4.1.2021.51  beancounters  /bin/cat /proc/user_beancounters" >> /etc/snmp/snmpd.conf
echo  createUser my_username MD5 my_password DES >> /var/lib/snmp/snmpd.conf
/etc/init.d/snmpd start 

Testing snmp:

snmpwalk   -v 3  -u my_usrname -l authPriv   -a MD5 -A my_password -x DES -X my_password  207.46.250.119

Warning: the minimum pass phrase length is 8 characters.

nagios configuration

example nagios configuration

add to configuration:

define command {
command_name check_snmp_openvz_on_port
# command_line /usr/local/bin/check_snmp_openvz.sh  $HOSTADDRESS$ PORT    USER    PASSWORD
command_line /usr/local/bin/check_snmp_openvz.sh  $HOSTADDRESS$ $ARG1$  $ARG2$  $ARG3$
}

define host {
        host_name   openvz-server
        alias       Serwer Openvz
        address     207.46.130.108
        use         generic-host
        contact_groups  admins
        }

define service{
        use                             generic-service
        host_name                       openvz-server
        service_description             Virtual Machines Limits
        check_command                   check_snmp_openvz_on_port!161!my_username!my_password
        max_check_attempts              1
        }

nagios plugin

It is shell script:

# cat /usr/local/bin/check_snmp_openvz.sh
#!/bin/bash
HOST=$1
PORT=$2
USER=$3
PASS=$4
export FILE=/tmp/$HOST.beancounters
RET=0

DATA=`snmpwalk   -v 3  -u $USER -l authPriv   -a MD5 -A $PASS -x DES -X $PASS $HOST:$PORT .1.3.6.1.4.1.2021.51.4 \
|  perl -ne '/"(.*)"/ ; print "$1\n" ;'`

if [ "$?" != "0" ]; then
        echo "Unknown snmp error"
        exit 1
fi

if [ -f $FILE ]; then
echo "$DATA" | perl  -n -e'
use Data::Dumper;
my $file=$ENV{"FILE"};
my $ret=0 ;
my $vid ;
my $resource ;
my $held ;
my $maxheld ;
my $barrier ;
my $limit ;
my $failcnt ;
my %beancounters ;
my %beancounters_old ;
while(<STDIN>){
        my %vmachine;
        if ( /\D*(\d+):.*/ ){ $vid=$1; $beancounters{$vid}=\%vmachine ; }
        if ( /^[\W\d]+([a-z]+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+).*/ ) {
                $resource=$1 ;
                $held=$2 ;
                $maxheld=$3 ;
                $barrier=$4 ;
                $limit=$5 ;
                $failcnt=$6 ;
                ${beancounters{$vid}}{$resource}=[$held , $maxheld , $barrier , $limit ,$failcnt ];
                if ( ($held  > $barrier) && ($barrier != 0) ) {
                        print "WARNING: Limits on $vid: $resource  held->$held , barrier->$barrier ( limit->$limit ) \n" ;
                        $ret=1;
                }
        }
}

# read and parse old data
open(MYINPUTFILE, "<$file");
while(<MYINPUTFILE>){
        my %vmachine;
        if ( /\D*(\d+):.*/ ){ $vid=$1; $beancounters_old{$vid}=\%vmachine ; }
        if ( /^[\W\d]+([a-z]+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+).*/ ) {
                $resource=$1 ;
                $held=$2 ;
                $maxheld=$3 ;
                $barrier=$4 ;
                $limit=$5 ;
                $failcnt=$6 ;
                ${beancounters_old{$vid}}{$resource}=[$held , $maxheld , $barrier , $limit ,$failcnt ];
        }
}

foreach my $vmachine_id (keys %beancounters) {
        foreach my $resource (keys %{$beancounters{$vmachine_id}} ) {
                if ( defined($beancounters{$vmachine_id}{$resource}[4]) && defined($beancounters_old{$vmachine_id}{$resource}[4]) ){
                        my $failcnt=$beancounters{$vmachine_id}{$resource}[4];
                        my $failcnt_old=$beancounters_old{$vmachine_id}{$resource}[4];
                        my $held=$beancounters{$vmachine_id}{$resource}[0];
                        my $maxheld=$beancounters{$vmachine_id}{$resource}[1];
                        my $barrier=$beancounters{$vmachine_id}{$resource}[2];
                        my $limit=$beancounters{$vmachine_id}{$resource}[3];
                        if ( $failcnt_old < $failcnt ){
                                print "CRITICAL: Incrased failcnt  $vmachine_id: $resource from $failcnt_old to $failcnt (held->$held , maxheld->$maxheld , barrier->$barrier , limit->$limit ) \n" ;
                                $ret=2;
                        }
                }
        }

}

if ($ret == 0 ) { print "Ok. \n" ; }
# print Dumper(%beancounters_old) ;
exit($ret);
'

RET=$?
fi

echo "$DATA" > $FILE

exit $RET