Hi,
We are trying to setup one distributed nagios monitoring with one central nagios server and two distributed nagios server. We have installed nsca deamon on the central server and added the nrpe service under xinetd. We have also setup the distributed server with send_nsca. Below are our central and distributed server setup and configurations.
If we are executing a send_nsca command manually, its working fine like below...
root# printf "temphost\ttempservice\t0\t Ashish Singh NSCA\n" | /usr/local/nagios/bin/send_nsca -H 192.168.16.2 -c /usr/local/nagios/etc/send_nsca.cfg
1 data packet(s) sent to host successfully.
and it logs on central server in nagios.log as below
[1299216743] EXTERNAL COMMAND: PROCESS_SERVICE_CHECK_RESULT;temphost;tempservice;0; Ashish Singh NSCA
-------------------------------------------------------------------------------------------------------------------------------------------\
But we are not able to understand why the nagios log on central and distributed is giving the following error. It looks like distributed server is not sending the nagios data to the central server and trying to do a force check from central. Please help us on this...
6315] Warning: The results of service 'Current Load' on host '192.168.16.10' are stale by 0d 0h 0m 30s (threshold=0d 0h 6m 0s). I'm forcing an immediate check of the service.
[1299216315] Warning: The results of service 'Current Users' on host '192.168.16.10' are stale by 0d 0h 0m 30s (threshold=0d 0h 6m 0s). I'm forcing an immediate check of the service.
[1299216315] Warning: The results of service 'MySql' on host '192.168.16.10' are stale by 0d 0h 0m 30s (threshold=0d 0h 6m 0s). I'm forcing an immediate check of the service.
[1299216315] Warning: The results of service 'Total Processes' on host '192.168.16.10' are stale by 0d 0h 0m 30s (threshold=0d 0h 6m 0s). I'm forcing an immediate check of the service.
[1299216405] Warning: The results of service 'Current Load' on host '192.168.16.20' are stale by 0d 0h 0m 30s (threshold=0d 0h 6m 0s). I'm forcing an immediate check of the service.
[1299216405] Warning: The results of service 'Current Users' on host '192.168.16.20' are stale by 0d 0h 0m 30s (threshold=0d 0h 6m 0s). I'm forcing an immediate check of the service.
[1299216405] Warning: The results of service 'PING' on host '192.168.16.20' are stale by 0d 0h 0m 30s (threshold=0d 0h 6m 0s). I'm forcing an immediate check of the service.
[1299216525] Warning: The results of service 'PING' on host '192.168.16.10' are stale by 0d 0h 0m 30s (threshold=0d 0h 6m 0s). I'm forcing an immediate check of the service.
[1299216525] Warning: The results of service 'Root Partition' on host '192.168.16.10' are stale by 0d 0h 0m 30s (threshold=0d 0h 6m 0s). I'm forcing an immediate check of the service.
[1299216585] Warning: The results of service 'SSH' on host '192.168.16.10' are stale by 0d 0h 0m 30s (threshold=0d 0h 6m 0s). I'm forcing an immediate check of the service.
####################################CENTRAL SERVER########################################################
#cd nsca-2.7.2
./configure
$ make all
# cp src/nsca /usr/local/nagios/bin
# cp sample_config/nsca.cfg /usr/local/nagios/etc/nsca.cfg
# vi /usr/local/nagios/etc/nsca.cfg
#password=********** (here we are not using any password)
#decryption_method=3 (here we are not using any password)
# cp sample-config/nsca.xinetd /etc/xinetd.d/nsca
#vi /etc/xinetd.d/nsca
# default: on
# description: NSCA (Nagios Service Check Acceptor)
service nsca
{
flags = REUSE
socket_type = stream
wait = no
user = nagios
group = nagios
server = /usr/local/nagios/bin/nsca
server_args = -c /usr/local/nagios/etc/nsca.cfg --inetd
log_on_failure += USERID
disable = no
only_from = 127.0.0.1 192.168.16.2
}
#cp sample-config/nsca.cfg /usr/local/nagios/etc/nsca.cfg
#cp src/nsca /usr/local/nagios/bin/nsca
# vi /usr/local/nagios/etc/nagios.cfg
cfg_dir=/usr/local/nagios/etc/servers
enable_notifications=1
execute_service_checks=1
check_external_commands=1
accept_passive_service_checks=1
accept_passive_host_checks=1
translate_passive_host_checks=1
obsess_over_services=0
#ocsp_command=
check_service_freshness=1
service_freshness_check_interval=60
check_host_freshness=1
host_freshness_check_interval=60
enable_event_handlers=1
#vi /usr/local/nagios/etc/objects/template.cfg
# Generic host definition template - This is NOT a real host, just a template!
define host{
name linux-server ; The name of this host template
use linux-server ; This template inherits other values from the generic-host template
check_period 24x7 ; By default, Linux hosts are checked round the clock
check_interval 5 ; Actively check the host every 5 minutes
retry_interval 1 ; Schedule host check retries at 1 minute intervals
max_check_attempts 10 ; Check each Linux host 10 times (max)
notifications_enabled 1
notification_period workhours ; Linux admins hate to be woken up, so we only notify during the day
notification_interval 30 ; Resend notifications every 2 hours
notification_options d,u,r ; Only send notifications for specific host states
check_freshness 1 ; Default is to NOT check service 'freshness'
event_handler_enabled 1 ; Host event handler is enabled
flap_detection_enabled 1 ; Flap detection is enabled
failure_prediction_enabled 1 ; Failure prediction is enabled
process_perf_data 1 ; Process performance data
retain_status_information 1 ; Retain status information across program restarts
retain_nonstatus_information 1 ; Retain non-status information across program restarts
notification_period 24x7 ; Send host notifications at any time
register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL HOST, JUST A TEMPLATE!
process_perf_data 1 ; Process performance data
contact_groups admins ; Notifications get sent to the admins by default
active_checks_enabled 0 ; Active service checks are enabled
passive_checks_enabled 1 ; Passive service checks are enabled/accepted
# check_command check-host-alive ; Default command to check Linux hosts
}
# Linux host definition template - This is NOT a real host, just a template!
define service{
name generic-service ; The name of this host template
active_checks_enabled 0 ; Active service checks are enabled
passive_checks_enabled 1 ; Passive service checks are enabled/accepted
parallelize_check 0 ; Active service checks should be parallelized (disabling this can lead to majorperformance problems)
obsess_over_service 0
check_period 24x7 ; By default, Linux hosts are checked round the clock
check_interval 5 ; Actively check the host every 5 minutes
retry_interval 1 ; Schedule host check retries at 1 minute intervals
retry_check_interval 10 ; Check the service every 10 minutes under normal conditions
max_check_attempts 10 ; Check each Linux host 10 times (max)
notifications_enabled 1
notification_period workhours ; Linux admins hate to be woken up, so we only notify during the day
notification_interval 60 ; Resend notifications every 2 hours
#notification_options d,u,r ; Only send notifications for specific host states
check_freshness 1 ; Default is to NOT check service 'freshness'
normal_check_interval 3 ; Check the service every 10 minutes under normal conditions
freshness_threshold 30
contact_groups admins,nagios ; Notifications get sent to the admins by default
event_handler_enabled 1 ; Host event handler is enabled
flap_detection_enabled 1 ; Flap detection is enabled
failure_prediction_enabled 1 ; Failure prediction is enabled
process_perf_data 1 ; Process performance data
retain_status_information 1 ; Retain status information across program restarts
is_volatile 0
retain_nonstatus_information 1 ; Retain non-status information across program restarts
notification_period 24x7 ; Send host notifications at any time
register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL HOST, JUST A TEMPLATE!
}
# mkdir /usr/local/nagios/etc/servers
# /etc/init.d/nagios start
#/usr/local/nagios/bin/nsca -c /usr/local/nagios/etc/nsca.cfg –inetd
===========================================================================
DISTRIBUTED SERVER SETUP
$ cd nsca-2.7.2
$ ./configure
$ make all
# cp src/send_nsca /usr/local/nagios/bin
# cp sample_config/send_nsca.cfg /usr/local/nagios/etc/send_nsca.cfg
# vi /usr/local/nagios/etc/send_nsca.cfg
password=**********
decryption_method=3
# chown nagios /usr/local/nagios/etc/send_nsca.cfg
# chmod 400 /usr/local/nagios/etc/send_nsca.cfg
# vi nagios.cfg
cfg_dir=/usr/local/nagios/etc/servers
enable_notifications=0
obsess_over_services=1
ocsp_command=submit_check_result
obsess_over_host=1
accept_passive_service_checks=0
accept_passive_host_checks=0
#ls -l /usr/local/nagios/libexec/eventhandlers/submit_check_result
-rwxrwxrwx 1 nagios root 1119 Mar 8 20:54 /usr/local/nagios/libexec/eventhandlers/submit_check_result
###################################################################3
#vi submit_check_result
#!/bin/bash
# Arguments:
# $1 = host_name (Short name of host that the service is
# associated with)
# $2 = svc_description (Description of the service)
# $3 = state_string (A string representing the status of
# the given service - "OK", "WARNING", "CRITICAL"
# or "UNKNOWN")
# $4 = plugin_output (A text string that should be used
# as the plugin output for the service checks)
#
# Convert the state string to the corresponding return code
return_code=-1
case "$3" in
OK)
return_code=0
;;
WARNING)
return_code=1
;;
CRITICAL)
return_code=2
;;
UNKNOWN)
return_code=-1
;;
esac
# pipe the service check info into the send_nsca program, which
# in turn transmits the data to the nsca daemon on the central
# monitoring server
/usr/bin/printf "%s\t%s\t%s\t%s\n" "$1" "$2" "$return_code" "$4" | /usr/local/nagios/bin/send_nsca -H 192.168.16.2 -c /usr/local/nagios/etc/send_nsca.cfg
#sh submit_service_check
0 data packet(s) sent to host successfully.
# vi etc/objects/command.cfg
define command{
command_name submit_check_result
command_line /usr/local/nagios/libexec/eventhandlers/submit_check_result $HOSTNAME$ 'SERVICEDESC$' $SERVICESTATEID$ '$SERVICEOUTPUT$'
}
#chmod 755 libexec/eventhandlers/submit_check_result
#vi /etc/services
Nsca 5667/tcp # NSCA
Nrpe 5666/tcp #NRPE
#vi /usr/local/nagios/etc/objects/templates.cfg
define host{
name generic-host ; The name of this host template
use generic-host ; This template inherits other values from the generic-host template
check_period 24x7 ; By default, Linux hosts are checked round the clock
check_interval 5 ; Actively check the host every 5 minutes
retry_interval 1 ; Schedule host check retries at 1 minute intervals
max_check_attempts 10 ; Check each Linux host 10 times (max)
notifications_enabled 1
notification_period workhours ; Linux admins hate to be woken up, so we only notify during the day
notification_interval 60 ; Resend notifications every 2 hours
notification_options d,u,r ; Only send notifications for specific host states
check_freshness 1 ; Default is to NOT check service 'freshness'
contact_groups admins ; Notifications get sent to the admins by default
event_handler_enabled 1 ; Host event handler is enabled
flap_detection_enabled 1 ; Flap detection is enabled
failure_prediction_enabled 1 ; Failure prediction is enabled
process_perf_data 1 ; Process performance data
retain_status_information 1 ; Retain status information across program restarts
retain_nonstatus_information 1 ; Retain non-status information across program restarts
notification_period 24x7 ; Send host notifications at any time
register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL HOST, JUST A TEMPLATE!
process_perf_data 1 ; Process performance data
}
define service{
name generic-service ; The name of this host template
active_checks_enabled 1 ; Active service checks are enabled
passive_checks_enabled 0 ; Passive service checks are enabled/accepted
parallelize_check 1 ; Active service checks should be parallelized (disabling this can lead to majorperformance problems)
obsess_over_service 0
check_period 24x7 ; By default, Linux hosts are checked round the clock
check_interval 5 ; Actively check the host every 5 minutes
retry_interval 1 ; Schedule host check retries at 1 minute intervals
retry_check_interval 10 ; Check the service every 10 minutes under normal conditions
max_check_attempts 10 ; Check each Linux host 10 times (max)
notifications_enabled 1
notification_period workhours ; Linux admins hate to be woken up, so we only notify during the day
notification_interval 60 ; Resend notifications every 2 hours
check_freshness 1 ; Default is to NOT check service 'freshness'
normal_check_interval 3 ; Check the service every 10 minutes under normal conditions
freshness_threshold 30
contact_groups admins,nagios ; Notifications get sent to the admins by default
event_handler_enabled 1 ; Host event handler is enabled
flap_detection_enabled 1 ; Flap detection is enabled
failure_prediction_enabled 1 ; Failure prediction is enabled
process_perf_data 1 ; Process performance data
retain_status_information 1 ; Retain status information across program restarts
is_volatile 0
retain_nonstatus_information 1 ; Retain non-status information across program restarts
notification_period 24x7 ; Send host notifications at any time
register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL HOST, JUST A TEMPLATE!
}
================================================================