Difference between revisions of "Monitoring openvz resources using nagios and snmp"
(add category monitoring) |
|||
(22 intermediate revisions by 9 users not shown) | |||
Line 5: | Line 5: | ||
</pre> | </pre> | ||
− | edit '''/etc/default/snmpd''' : remove ''-u snmp'' and replace ''127.0.0.1'' with your ip, Full'''/etc/default/snmpd''' example: | + | edit '''/etc/default/snmpd''' : remove ''-u snmp'' and replace ''127.0.0.1'' with your ip (ie : 207.46.250.119), Full'''/etc/default/snmpd''' example: |
<pre> | <pre> | ||
export MIBDIRS=/usr/share/snmp/mibs | export MIBDIRS=/usr/share/snmp/mibs | ||
Line 26: | Line 26: | ||
<pre> | <pre> | ||
/etc/init.d/snmpd stop | /etc/init.d/snmpd stop | ||
− | echo rouser my_username priv > /etc/snmp/snmpd.conf | + | 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 "extend .1.3.6.1.4.1.2021.51 beancounters /bin/cat /proc/user_beancounters" >> /etc/snmp/snmpd.conf | ||
echo "extend .1.3.6.1.4.1.2021.52 vzquota /bin/cat /proc/vz/vzquota" >> /etc/snmp/snmpd.conf | echo "extend .1.3.6.1.4.1.2021.52 vzquota /bin/cat /proc/vz/vzquota" >> /etc/snmp/snmpd.conf | ||
Line 32: | Line 32: | ||
/etc/init.d/snmpd start | /etc/init.d/snmpd start | ||
</pre> | </pre> | ||
+ | |||
+ | (Note that the createUser command goes into a separate file. On Centos5 this file is located in /var/net-snmp/snmpd.conf. Make sure you stop snmpd before putting the createUser command there!). | ||
Testing snmp: | Testing snmp: | ||
<pre> | <pre> | ||
− | snmpwalk -v 3 -u | + | snmpwalk -v 3 -u my_username -l authPriv -a MD5 -A my_password -x DES -X my_password $(hostname -i) |
</pre> | </pre> | ||
Line 208: | Line 210: | ||
##################################################################################### | ##################################################################################### | ||
− | if [ | + | if [ $RET1 -gt $RET2 ]; then |
RET=$RET1 | RET=$RET1 | ||
else | else | ||
Line 220: | Line 222: | ||
</source> | </source> | ||
− | === | + | === check_vzquota Without SNMP === |
− | <source lang= | + | <source lang="bash"> |
− | #!/usr/ | + | #!/bin/bash |
− | + | RET=0 | |
− | + | DATA=`echo;sudo /usr/sbin/vzlist -1 2>/dev/null | xargs -I {} bash -c "echo {}:;sudo /usr/sbin/vzquota stat {} | sed 's/\*//g'"` | |
− | + | if [ -z "$DATA" ]; then | |
− | + | VPS_err=$(sudo /usr/sbin/vzlist -1 2>&1 1>/dev/null) | |
+ | if [ -n "$VPS_err" ] && [ "$VPS_err" == "Container(s) not found" ]; then | ||
+ | echo "OK - $VPS_err"; | ||
+ | exit 0; | ||
+ | else | ||
+ | if [ -n "$VPS_err" ]; then | ||
+ | echo "UNKNOWN - Error: $VPS_err"; | ||
+ | else | ||
+ | echo "UNKNOWN - VZquota stats are not readable or empty. Maybe it is only readable for root and this script should be called by sudo."; | ||
+ | fi | ||
+ | exit 3; | ||
+ | fi | ||
+ | fi | ||
− | + | echo "$DATA" | perl -n -e' | |
− | + | my $vid ; | |
− | + | my $ret=0 ; | |
− | + | my $crit=""; | |
− | + | my $warn=""; | |
− | + | my $ok=""; | |
− | + | while(<STDIN>){ | |
+ | my %vid; | ||
+ | if ( /^(\d+):.*/ ){ $vid=$1; } | ||
+ | if ( /\D*(\d+):.*/ ){ $vid=$1; } | ||
+ | if ( /\s*(\S+)\s+(\d+)\s+(\d+)\s+(\d+).*/ ){ | ||
+ | $resource=$1 ; | ||
+ | $usage=$2 ; | ||
+ | $softlimit=$3 ; | ||
+ | $hardlimit=$4 ; | ||
+ | if ( $usage >= $hardlimit ){ | ||
+ | $crit=$crit."VZquota limit exceeded on $vid: $resource usage->$usage, softlimit->$softlimit, hardlimit->$hardlimit, time->$time, expire->$expire " ; | ||
+ | $ret=2; | ||
+ | } elsif ( $usage >= $softlimit ){ | ||
+ | $warn=$warn."VZquota limit exceeded on $vid: $resource usage->$usage, softlimit->$softlimit, hardlimit->$hardlimit, time->$time, expire->$expire " ; | ||
+ | $ret=1; | ||
+ | } | ||
+ | $ok=$ok."$vid:$resource $usage/$softlimit\n"; | ||
+ | } | ||
+ | } | ||
+ | if ($ret == 0) { | ||
+ | print "OK - click on service-link for details...\n$ok"; | ||
+ | } elsif ($ret == 1) { | ||
+ | print "WARNING - $warn\n"; | ||
+ | } else { | ||
+ | print "CRITICAL - $crit\n"; | ||
+ | } | ||
+ | exit($ret); | ||
+ | ' | ||
+ | RET=$? | ||
+ | exit $RET | ||
+ | </source> | ||
+ | The script calls <code>/usr/sbin/vzlist</code> by sudo. When doing this it normally needs a password, which check_nrpe will not know. Because of this it is necessary that you append a line like the following to <code>/etc/sudors</code> (user name an path should be adapted to the right ones on your system): | ||
+ | nagios ALL=NOPASSWD: /usr/sbin/vzlist, /usr/sbin/vzquota | ||
− | + | === check_ubc Without SNMP === | |
− | + | <source lang="bash"> | |
− | + | #!/bin/bash | |
− | + | # Servicestate description can have a http-link to the openvz-wiki | |
− | + | # in case that a ressource is warning/critical. To use it: | |
+ | # 1. set "escape_html_tags=0" in nagios/etc/cgi.cfg | ||
+ | # 2. set "my $linked=1;" in the first perl lines in this script | ||
+ | # | ||
+ | export FILE=/tmp/check_ubc | ||
+ | RET=0 | ||
+ | ubc_file='/proc/user_beancounters'; | ||
+ | DATA=''; | ||
+ | if [ -r $ubc_file ]; then | ||
+ | DATA=`cat $ubc_file` | ||
+ | fi | ||
+ | if [ -z "$DATA" ]; then | ||
+ | echo "UNKNOWN - $ubc_file is not readable or empty. Maybe it is only readable for root and this script should be called by sudo."; | ||
+ | exit 3; | ||
+ | fi | ||
− | + | if [ -f $FILE ]; then | |
+ | echo "$DATA" | perl -n -e' | ||
+ | use Data::Dumper; | ||
+ | my $linked=1; # 0:plain text output, 1:resourcename is a http-link to OpenVZ-wiki | ||
+ | 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 $vid: ".&url($resource,$linked)." held->$held , barrier->$barrier ( limit->$limit ) " ; | ||
+ | $ret=1; | ||
+ | } | ||
+ | #print "$vid:$resource $held Barrier:$barrier "; | ||
+ | } | ||
+ | } | ||
− | + | # 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: Increased failcnt $vmachine_id: ".url($resource,$linked)." from $failcnt_old to $failcnt (held->$held , maxheld->$maxheld , barrier->$barrier , limit->$limit ) " ; | |
+ | $ret=2; | ||
+ | } | ||
+ | #print "$vmachine_id: Old_Failcnt: $failcnt_old Failcnt: $failcnt \n"; | ||
+ | } | ||
+ | } | ||
− | \n | + | } |
− | + | sub url { | |
+ | my ($name,$with_link) = @_; | ||
+ | if ($with_link) { | ||
+ | return "<a target=\"_blank\" href=\"http://wiki.openvz.org/".$name."#".$name."\">$name</a>"; | ||
+ | } else { | ||
+ | return $name; | ||
+ | } | ||
+ | } | ||
+ | if ($ret == 0 ) { print "OK: All bean counters fine \n" ; } | ||
+ | # print Dumper(%beancounters_old) ; | ||
+ | # print "\n"; | ||
+ | exit($ret); | ||
+ | ' | ||
− | + | RET=$? | |
+ | fi | ||
− | + | echo "$DATA" > $FILE | |
− | + | exit $RET | |
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
</source> | </source> | ||
+ | The script needs to read the <code>/proc/user_beancounters</code> file. This is normally only readable for root. Because of this it is necessary that you append a line like the following to <code>/etc/sudors</code> (user name an path should be adapted to the right ones on your system): | ||
+ | nagios ALL=NOPASSWD: /usr/local/nagios/libexec/check_ubc | ||
+ | Also don't forget to consider this on your <code>nrpe.cfg</code>, so that you call the script with sudo: | ||
+ | command[check_ubc]=sudo /usr/local/nagios/libexec/check_ubc | ||
− | + | [[Category: Monitoring]] | |
− | [[Category: |
Latest revision as of 12:26, 21 December 2015
Contents
snmpd configuration[edit]
Debian Etch example:
apt-get install snmpd
edit /etc/default/snmpd : remove -u snmp and replace 127.0.0.1 with your ip (ie : 207.46.250.119), 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'
For Debian 4.x:
export MIBDIRS=/usr/share/snmp/mibs SNMPDRUN=yes SNMPDOPTS='-Lsd -Lf /dev/null -I -smux -p /var/run/snmpd.pid' TRAPDRUN=no TRAPDOPTS='-Lsd -p /var/run/snmptrapd.pid'
Create user(my_username) and add new mib. Password need a min. of 8 charactes. Username only characters:
/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 "extend .1.3.6.1.4.1.2021.52 vzquota /bin/cat /proc/vz/vzquota" >> /etc/snmp/snmpd.conf echo createUser my_username MD5 my_password DES >> /var/lib/snmp/snmpd.conf /etc/init.d/snmpd start
(Note that the createUser command goes into a separate file. On Centos5 this file is located in /var/net-snmp/snmpd.conf. Make sure you stop snmpd before putting the createUser command there!).
Testing snmp:
snmpwalk -v 3 -u my_username -l authPriv -a MD5 -A my_password -x DES -X my_password $(hostname -i)
Warning: the minimum pass phrase length is 8 characters.
nagios configuration[edit]
example nagios configuration[edit]
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 207.46.250.119 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[edit]
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_TMP=`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`
if [ "$?" != "0" ]; then
echo "Unknown snmp error"
exit 1
fi
DATA=`echo "$DATA_TMP"| perl -ne '/"(.*)"/ ; print "$1\n" ;'`
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 ) " ;
$ret=1;
}
}
}
# read and parse old data
open(MYINPUTFILE, "<$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 ) " ;
$ret=2;
}
}
}
}
# if ($ret == 0 ) { print "Ok. \n" ; }
# print Dumper(%beancounters_old) ;
# print "\n";
exit($ret);
'
RET1=$?
fi
echo "$DATA" > $FILE
#####################################################################################
######### quota check
#####################################################################################
DATA=`snmpwalk -v 3 -u $USER -l authPriv -a MD5 -A $PASS -x DES -X $PASS $HOST:$PORT .1.3.6.1.4.1.2021.52.4 \
| perl -ne '/"(.*)"/ ; print "$1\n" ;'`
if [ "$?" != "0" ]; then
echo "Unknown snmp error"
exit 1
fi
echo "$DATA" | perl -n -e'
my $vid ;
my $ret=0 ;
while(<STDIN>){
my %vid;
if ( /\D*(\d+):.*/ ){ $vid=$1; }
if ( /\s*(\S+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+).*/ ){
$resource=$1 ;
$usage=$2 ;
$softlimit=$3 ;
$hardlimit=$4 ;
$time=$5 ;
$expire=$6 ;
if ( $usage >= $softlimit ){
print "WARNING: VZquota limit exceeded on $vid: $resource usage->$usage, softlimit->$softlimit, hardlimit->$hardlimit, time->$time, expire->$expire " ;
$ret=1;
}
}
}
exit($ret);
'
RET2=$?
#####################################################################################
########### return
#####################################################################################
if [ $RET1 -gt $RET2 ]; then
RET=$RET1
else
RET=$RET2
fi
if [ $RET = 0 ]; then
echo Ok.
fi
exit $RET
check_vzquota Without SNMP[edit]
#!/bin/bash
RET=0
DATA=`echo;sudo /usr/sbin/vzlist -1 2>/dev/null | xargs -I {} bash -c "echo {}:;sudo /usr/sbin/vzquota stat {} | sed 's/\*//g'"`
if [ -z "$DATA" ]; then
VPS_err=$(sudo /usr/sbin/vzlist -1 2>&1 1>/dev/null)
if [ -n "$VPS_err" ] && [ "$VPS_err" == "Container(s) not found" ]; then
echo "OK - $VPS_err";
exit 0;
else
if [ -n "$VPS_err" ]; then
echo "UNKNOWN - Error: $VPS_err";
else
echo "UNKNOWN - VZquota stats are not readable or empty. Maybe it is only readable for root and this script should be called by sudo.";
fi
exit 3;
fi
fi
echo "$DATA" | perl -n -e'
my $vid ;
my $ret=0 ;
my $crit="";
my $warn="";
my $ok="";
while(<STDIN>){
my %vid;
if ( /^(\d+):.*/ ){ $vid=$1; }
if ( /\D*(\d+):.*/ ){ $vid=$1; }
if ( /\s*(\S+)\s+(\d+)\s+(\d+)\s+(\d+).*/ ){
$resource=$1 ;
$usage=$2 ;
$softlimit=$3 ;
$hardlimit=$4 ;
if ( $usage >= $hardlimit ){
$crit=$crit."VZquota limit exceeded on $vid: $resource usage->$usage, softlimit->$softlimit, hardlimit->$hardlimit, time->$time, expire->$expire " ;
$ret=2;
} elsif ( $usage >= $softlimit ){
$warn=$warn."VZquota limit exceeded on $vid: $resource usage->$usage, softlimit->$softlimit, hardlimit->$hardlimit, time->$time, expire->$expire " ;
$ret=1;
}
$ok=$ok."$vid:$resource $usage/$softlimit\n";
}
}
if ($ret == 0) {
print "OK - click on service-link for details...\n$ok";
} elsif ($ret == 1) {
print "WARNING - $warn\n";
} else {
print "CRITICAL - $crit\n";
}
exit($ret);
'
RET=$?
exit $RET
The script calls /usr/sbin/vzlist
by sudo. When doing this it normally needs a password, which check_nrpe will not know. Because of this it is necessary that you append a line like the following to /etc/sudors
(user name an path should be adapted to the right ones on your system):
nagios ALL=NOPASSWD: /usr/sbin/vzlist, /usr/sbin/vzquota
check_ubc Without SNMP[edit]
#!/bin/bash
# Servicestate description can have a http-link to the openvz-wiki
# in case that a ressource is warning/critical. To use it:
# 1. set "escape_html_tags=0" in nagios/etc/cgi.cfg
# 2. set "my $linked=1;" in the first perl lines in this script
#
export FILE=/tmp/check_ubc
RET=0
ubc_file='/proc/user_beancounters';
DATA='';
if [ -r $ubc_file ]; then
DATA=`cat $ubc_file`
fi
if [ -z "$DATA" ]; then
echo "UNKNOWN - $ubc_file is not readable or empty. Maybe it is only readable for root and this script should be called by sudo.";
exit 3;
fi
if [ -f $FILE ]; then
echo "$DATA" | perl -n -e'
use Data::Dumper;
my $linked=1; # 0:plain text output, 1:resourcename is a http-link to OpenVZ-wiki
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 $vid: ".&url($resource,$linked)." held->$held , barrier->$barrier ( limit->$limit ) " ;
$ret=1;
}
#print "$vid:$resource $held Barrier:$barrier ";
}
}
# 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: Increased failcnt $vmachine_id: ".url($resource,$linked)." from $failcnt_old to $failcnt (held->$held , maxheld->$maxheld , barrier->$barrier , limit->$limit ) " ;
$ret=2;
}
#print "$vmachine_id: Old_Failcnt: $failcnt_old Failcnt: $failcnt \n";
}
}
}
sub url {
my ($name,$with_link) = @_;
if ($with_link) {
return "<a target=\"_blank\" href=\"http://wiki.openvz.org/".$name."#".$name."\">$name</a>";
} else {
return $name;
}
}
if ($ret == 0 ) { print "OK: All bean counters fine \n" ; }
# print Dumper(%beancounters_old) ;
# print "\n";
exit($ret);
'
RET=$?
fi
echo "$DATA" > $FILE
exit $RET
The script needs to read the /proc/user_beancounters
file. This is normally only readable for root. Because of this it is necessary that you append a line like the following to /etc/sudors
(user name an path should be adapted to the right ones on your system):
nagios ALL=NOPASSWD: /usr/local/nagios/libexec/check_ubc
Also don't forget to consider this on your nrpe.cfg
, so that you call the script with sudo:
command[check_ubc]=sudo /usr/local/nagios/libexec/check_ubc