Monitoring openvz resources using nagios and snmp - Revision history

Sergey Bronnikov: add category monitoring

2015-12-21T12:26:35Z

add category monitoring

217.33.40.98: /* check_ubc Without SNMP */

2013-02-04T11:53:08Z

‎check_ubc Without SNMP

Kir: Reverted edits by MalloryScoggin (Talk) to last revision by 195.177.123.4

2010-10-11T15:24:00Z

Reverted edits by MalloryScoggin (Talk) to last revision by 195.177.123.4

MalloryScoggin at 15:13, 11 October 2010

2010-10-11T15:13:27Z

195.177.123.4: /* nagios plugin */ correct if [ $RET gt $RET ] string

2010-03-19T12:52:06Z

‎nagios plugin: correct if [ $RET gt $RET ] string

Kako: /* check_ubc Without SNMP */ Resourcename can now be a link to OpenVZ-Wiki for more information in case of troubles

2009-04-08T09:11:33Z

‎check_ubc Without SNMP: Resourcename can now be a link to OpenVZ-Wiki for more information in case of troubles

Kako: /* check_vzquota Without SNMP */ script cahnged ! surpress the "unknow" error in case that all is ok, but there are simple no containers running

2009-04-07T09:12:45Z

‎check_vzquota Without SNMP: script cahnged ! surpress the "unknow" error in case that all is ok, but there are simple no containers running

Kako: /* check_vzquota Without SNMP */ some minor optical changes on OK state

2009-04-07T08:15:03Z

‎check_vzquota Without SNMP: some minor optical changes on OK state

Kako: /* check_ubc Without SNMP */

2009-04-07T07:52:44Z

‎check_ubc Without SNMP

Kako: /* check_vzquota Without SNMP */ ! script changed ! , state UNKNOWN and CRITICAL added

2009-04-07T07:51:42Z

‎check_vzquota Without SNMP: ! script changed ! , state UNKNOWN and CRITICAL added

← Older revision		Revision as of 12:26, 21 December 2015
Line 395:		Line 395:
	Also don't forget to consider this on your <code>nrpe.cfg</code>, so that you call the script with sudo:		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		command[check_ubc]=sudo /usr/local/nagios/libexec/check_ubc
		+
		+	[[Category: Monitoring]]

@@ Line 362: / Line 362: @@
                          my $limit=$beancounters{$vmachine_id}{$resource}[3];
                          if ( $failcnt_old < $failcnt ){
-                                 print "CRITICAL: Incrased failcnt  $vmachine_id: ".url($resource,$linked)." from $failcnt_old to $failcnt (held->$held , maxheld->$maxheld , barrier->$barrier , limit->$limit ) " ;
+                                 print "CRITICAL: Increased failcnt  $vmachine_id: ".url($resource,$linked)." from $failcnt_old to $failcnt (held->$held , maxheld->$maxheld , barrier->$barrier , limit->$limit ) " ;
                                  $ret=2;
+                         }
@@ Line 378: / Line 378: @@
+         }
+}
-if ($ret == 0 ) { print "OK. \n" ; }
+if ($ret == 0 ) { print "OK: All bean counters fine \n" ; }
 # print Dumper(%beancounters_old) ;
 # print "\n";

@@ Line 1: / Line 1: @@
 == snmpd configuration ==
-Debian Etch example: [http://www.research-service.com custom essay]
+Debian Etch example:
 <pre>
 apt-get install snmpd

@@ Line 1: / Line 1: @@
 == snmpd configuration ==
-Debian Etch example:
+Debian Etch example: [http://www.research-service.com custom essay]
 <pre>
 apt-get install snmpd

@@ Line 210: / Line 210: @@
 #####################################################################################
-if [  $RET1  -gt $RET2  ]; then
+if [ $RET1 -gt $RET2 ]; then
          RET=$RET1
          else
@@ Line 221: / Line 221: @@
 exit $RET
 </source>
 === check_vzquota Without SNMP ===
 <source lang="bash">

@@ Line 284: / Line 284: @@
 <source lang="bash">
 #!/bin/bash
 export FILE=/tmp/check_ubc
 RET=0
 ubc_file='/proc/user_beancounters';
 DATA='';
@@ Line 293: / Line 297: @@
 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.";
+         echo "UNKNOWN - $ubc_file is not readable or empty. Maybe it is only readable for root and this script should be called by sudo.";
          exit 3;
 fi
@@ Line 300: / Line 304: @@
 echo "$DATA" | perl  -n -e'
 use Data::Dumper;
 my $file=$ENV{"FILE"};
 my $ret=0 ;
@@ Line 323: / Line 328: @@
                  ${beancounters{$vid}}{$resource}=[$held , $maxheld , $barrier , $limit ,$failcnt ];
                  if ( ($held  > $barrier) && ($barrier != 0) ) {
-                         print "WARNING: Limits on $vid: $resource  held->$held , barrier->$barrier ( limit->$limit ) " ;
+                         print "WARNING: Limits on $vid: ".&url($resource,$linked)."  held->$held , barrier->$barrier ( limit->$limit ) " ;
                          $ret=1;
+                 }
@@ Line 356: / Line 361: @@
                          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 ) " ;
+                                 print "CRITICAL: Incrased failcnt  $vmachine_id: ".url($resource,$linked)." from $failcnt_old to $failcnt (held->$held , maxheld->$maxheld , barrier->$barrier , limit->$limit ) " ;
                                  $ret=2;
+                         }
@@ Line 364: / Line 369: @@
+}
+sub url {
 if ($ret == 0 ) { print "OK. \n" ; }
 # print Dumper(%beancounters_old) ;

@@ Line 225: / Line 225: @@
 #!/bin/bash
 RET=0
-DATA=`echo;sudo /usr/sbin/vzlist -1 | xargs -I {} bash -c "echo {}:;sudo /usr/sbin/vzquota stat {} | sed 's/\*//g'"`
+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 "$DATA" ]; then
-         echo "UNKNOWN - VZquota stats are not readable or empty. Maybe it is only readable for root and this script should be called by sudo.";
+         VPS_err=$(sudo /usr/sbin/vzlist -1 2>&1 1>/dev/null)
-        exit 3;
+        if [ -n "$VPS_err" ] && [ "$VPS_err" == "Container(s) not found" ]; then
 fi

@@ Line 253: / Line 253: @@
                          $ret=1;
+                 }
-                 $ok=$ok."$vid:$resource $usage/$softlimit ";
+                 $ok=$ok."$vid:$resource $usage/$softlimit\n";
+         }
+}
 if ($ret == 0) {
-         print "OK - $ok";
+         print "OK - click on service-link for details...\n$ok";
 } elsif ($ret == 1)  {
-         print "WARNING - $warn";
+         print "WARNING - $warn\n";
 } else {
-         print "CRITICAL - $crit";
+         print "CRITICAL - $crit\n";
+}
 exit($ret);
+'
 RET=$?
 exit $RET
 </source>

@@ Line 225: / Line 225: @@
 #!/bin/bash
 RET=0
-DATA=`echo;sudo /usr/sbin/vzlist -1 | xargs -I {} bash -c "echo {}:;sudo /usr/sbin/vzquota stat {}"`
+DATA=`echo;sudo /usr/sbin/vzlist -1 | xargs -I {} bash -c "echo {}:;sudo /usr/sbin/vzquota stat {} | sed 's/\*//g'"`
 echo "$DATA" | perl  -n -e'
 my $vid ;
 my $ret=0 ;
 while(<STDIN>){
          my %vid;
@@ Line 238: / Line 246: @@
                  $softlimit=$3 ;
                  $hardlimit=$4 ;
-                 if ( $usage >= $softlimit ){
+                 if ( $usage >= $hardlimit ){
-                         print "WARNING: VZquota limit exceeded on $vid: $resource  usage->$usage, softlimit->$softlimit, hardlimit->$hardlimit, time->$time, expire->$expire  " ;
+                        $crit=$crit."VZquota limit exceeded on $vid: $resource  usage->$usage, softlimit->$softlimit, hardlimit->$hardlimit, time->$time, expire->$expire  " ;
                          $ret=1;
+                 }
-                                print "$vid:$resource $usage/$softlimit ";
+                $ok=$ok."$vid:$resource $usage/$softlimit ";
+         }
+}
 exit($ret);
@@ Line 250: / Line 268: @@
 echo
 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):