Implement more detailed bandwidth monitoring

manifests/monitoringserver.pp

Index: manifests/monitoringserver.pp
===================================================================
--- a/manifests/monitoringserver.pp
+++ b/manifests/monitoringserver.pp
@@ -39,16 +39,20 @@ node 'server4' {
     }
 
     nagios_contactgroup {'admins':
       alias => 'Nagios Administrators',
       members => 'abp-admins'
     }
   }
 
+  nagios_command {'check_nrpe_timeout':
+    command_line => '/usr/lib/nagios/plugins/check_nrpe -H $HOSTADDRESS$ -c $ARG1$ -t $ARG2$'
+  }
+
   nagios_command {'check_easylist_http':
     command_line => '/usr/lib/nagios/plugins/check_http -S -I $HOSTADDRESS$ -H easylist-downloads.adblockplus.org -u /easylist.txt -k "Accept-Encoding: gzip,deflate" -e "HTTP/1.1 200 OK"'
   }
 
   nagios_command {'check_notification_http':
     command_line => '/usr/lib/nagios/plugins/check_http -S -I $HOSTADDRESS$ -H notification.adblockplus.org -u /notification.json -k "Accept-Encoding: gzip,deflate" -e "HTTP/1.1 200 OK"'
   }
 
@@ -134,17 +138,17 @@ node 'server4' {
     service_description => 'HTTP',
     check_command => 'check_notification_http'
   }
 
   nagios_service {'bandwidth':
     use => 'generic-service',
     hostgroup_name => 'all',
     service_description => 'Bandwidth',
-    check_command => 'check_nrpe_1arg!check_bandwidth',
+    check_command => 'check_nrpe_timeout!check_bandwidth!20',

[Felix Dahlke, 2013/10/10 08:29:08]

Why does this need a timeout now?

[Wladimir Palant, 2013/10/10 09:37:46]

There is always a timeout, the default is 10 seconds - which is too little for
bandwidth monitoring. tcpdump needs to run 5 seconds, plus the processing of the
data needs to happen. As I said, on some busy servers this doesn't finish in 10
seconds.

     first_notification_delay => '15'
   }
 
   nagios_service {'connections':
     use => 'generic-service',
     hostgroup_name => 'all',
     service_description => 'Connections',
     check_command => 'check_nrpe_1arg!check_connections',