Hi Everyone,
Sorry the last post didn't contain any configuration information. I was
hoping someone had seen this before. Here are the relevant files:
nagios.cfg:
# Written by NSFG (1.0 Release Candidate 1) at: May 3, 2006, 11:36 am#
Generated for IBS Network
log_file=/var/log/nagios/nagios.log
cfg_file=/etc/nagios/host_templates.cfg
cfg_file=/etc/nagios/hosts.cfg
cfg_file=/etc/nagios/commands.cfg
cfg_file=/etc/nagios/timeperiods.cfg
cfg_file=/etc/nagios/contactgroups.cfg
cfg_file=/etc/nagios/contacts.cfg
cfg_file=/etc/nagios/hostgroups.cfg
cfg_file=/etc/nagios/service_templates.cfg
cfg_file=/etc/nagios/services.cfg
cfg_file=/etc/nagios/servicegroups.cfg
resource_file=/etc/nagios/resources.cfg
cfg_file=/etc/nagios/hostextinfo.cfg
cfg_file=/etc/nagios/serviceextinfo.cfg
cfg_file=/etc/nagios/dependencies.cfg
log_file=/var/log/nagios/nagios.log
temp_file=/var/log/nagios/nagios.tmp
status_file=/var/log/nagios/status.dat
aggregate_status_updates=1
status_update_interval=15
nagios_user=nagios
nagios_group=nagios
enable_notifications=1
execute_service_checks=1
accept_passive_service_checks=1
enable_event_handlers=1
log_rotation_method=d
log_archive_path=/var/log/nagios/archives
check_external_commands=1
command_check_interval=-1
command_file=/var/log/nagios/rw/nagios.cmd
downtime_file=/var/log/nagios/downtime.dat
comment_file=/var/log/nagios/comments.dat
lock_file=/var/run/nagios.pid
p1_file=/usr/bin/p1.pl
retain_state_information=1
state_retention_file=/var/log/nagios/retention.dat
retention_update_interval=60
use_retained_program_state=1
use_syslog=1
log_notifications=1
log_service_retries=1
log_host_retries=1
log_event_handlers=1
log_initial_states=0
log_external_commands=1
log_passive_checks=1
sleep_time=0.25
service_interleave_factor=s
max_concurrent_checks=0
service_reaper_frequency=10
interval_length=60
use_aggressive_host_checking=0
enable_flap_detection=0
low_service_flap_threshold=5
high_service_flap_threshold=20
low_host_flap_threshold=5
high_host_flap_threshold=20
service_check_timeout=60
host_check_timeout=30
event_handler_timeout=30
notification_timeout=30
ocsp_timeout=5
perfdata_timeout=5
obsess_over_services=0
process_performance_data=0
check_for_orphaned_services=0
check_service_freshness=0
date_format=us
illegal_object_name_chars=`~!$%^&*|'"<>?,()=
illegal_macro_output_chars=`~$&|'"<>
[EMAIL PROTECTED]
admin_pager=pagenagios
object_cache_file=/var/log/nagios/objects.cache
execute_host_checks=1
service_inter_check_delay_method=s
use_retained_scheduling_info=0
accept_passive_host_checks=1
max_service_check_spread=30
host_inter_check_delay_method=s
max_host_check_spread=30
auto_reschedule_checks=0
auto_rescheduling_interval=30
auto_rescheduling_window=180
check_host_freshness=0
host_freshness_check_interval=60
service_freshness_check_interval=60
use_regexp_matching=0
use_true_regexp_matching=0
event_broker_options=-1
daemon_dumps_core=0
some entries from hosts.cfg:
define host {
use IBS External Support Server
host_name nbs-sapg1.jpl.nasa.gov
alias Ultra-60 - Solaris 9 - NBU Master Server ISO
address 128.149.128.51
check_command check_ssh
hostgroups UNIX Servers,Unix FTP Access
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
use IBS External Production Server
host_name nbs-uprd002.jpl.nasa.gov
alias x86_64 - Linux - SUSE Enterprise Server 9 - ccharvest host
address 128.149.128.137
check_command check_ssh
hostgroups LINUX,UNIX Servers
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
use IBS Internal Support Server
host_name media1.jpl.nasa.gov
alias SunFire-280R - Solaris 9 - NBU Media Server 1
address 137.78.46.30
hostgroups UNIX Servers,Unix FTP Access
contact_groups SystemAdmins-WH,OnCall_SA
}
the host_template.cfg file:
# Written by NSFG (1.0 Release Candidate 1) at: May 3, 2006, 11:36 am
# Generated for IBS Network
define host {
name IBS BOSS Server
use IBS External Production Server
check_command check_ssh
max_check_attempts 8
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
name IBS DCO Server
check_period 24x7
notification_interval 0
notification_period NBSServiceHours
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
name IBS DMZ Server
use IBS External Production Server
check_command check_ssh
max_check_attempts 8
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
name IBS Equipment
use IBS DCO Server
check_command check-host-alive
check_interval 1
event_handler host-notify-by-epager
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
name IBS External Development Server
use IBS External Production Server
check_command check_ssh
max_check_attempts 8
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
name IBS External Production Server
use IBS External Server
check_command check_ssh
max_check_attempts 15
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
name IBS External Server
use IBS DCO Server
check_command check_ssh
check_interval 5
event_handler host-notify-by-epager
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
name IBS External Support Server
use IBS External Production Server
check_command check_ssh
max_check_attempts 8
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
name IBS Internal Development Server
use IBS Internal Production Server
check_command check-host-alive
max_check_attempts 8
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
name IBS Internal Production Server
use IBS Internal Server
check_command check-host-alive
max_check_attempts 15
register 0
notification_options d,u,r
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
name IBS Internal Support Equipment
use IBS Equipment
check_command check-host-alive
max_check_attempts 8
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
name IBS Internal Support Server
use IBS Internal Production Server
check_command check-host-alive
max_check_attempts 8
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
define host {
name Library Server
use IBS External Production Server
check_command check_ssh
max_check_attempts 8
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
some entries from the services.cfg file:
define service {
use FTP Service
service_description FTP
check_command check_ftp
hostgroup_name Unix FTP Access
contact_groups OnCall_SA,SystemAdmins-WH
}
define service {
use CPULOAD00
service_description CPU Load
hostgroup_name UNIXCPU10
contact_groups SystemAdmins-WH,OnCall_SA
}
define service {
service_description HTTP
passive_checks_enabled 1
host_name nbs.jpl.nasa.gov
}
The service_templates.cfg:
define service {
name CPULOAD00
use System Level Service
check_command check_nrpe!check_load!10,5,5!15,10,10
register 0
contact_groups SystemAdmins-WH,OnCall_SA
}
define service {
name FTP Service
use Production Service
check_command check_ftp
normal_check_interval 10
notification_interval 0
register 0
contact_groups OnCall_SA,SystemAdmins-WH
}
define service {
name HTTP Service
use Production Service
check_command check_http
register 0
}
define service {
name HTTP-check-uri Service
use Production Service
check_command check_uri
register 0
}
define service {
name IBS DCO Service
max_check_attempts 5
normal_check_interval 5
retry_check_interval 1
check_period 24x7
event_handler host-notify-by-epager
event_handler_enabled 1
notification_interval 0
notification_period 24x7
notifications_enabled 1
register 0
notification_options w,u,c
}
define service {
name Support Service
use IBS DCO Service
register 0
}
define service {
name System Level Service
use IBS DCO Service
check_command check_nrpe
register 0
}
define service {
name TNS Ping Service
use Production Service
check_command check_oracle
register 0
contact_groups OnCall_DBA,DatabaseAdmins-WH
}
If you need any other configuration information, let me know and I'll
post that as well.
Thanks in advance!
-Frank Guarino
Original message:
I'm still fairly new to Nagios and I'm having a problem with notifications.
I keep getting unwanted UP messages like:
>Subject: PROBLEM alert - Host /xxxhostname.domainname/ is UP
Host 'SunFire-880 - Solaris 9 - NBU Media Server 2' is UP
Info: PING OK - Packet loss = 0%, RTA = 0.29 ms
Time: Fri Apr 28 14:16:19 PDT 2006
These messages only occur when a service is down (for something like
maintenance) but the host is up. This is occurring from all
hosts/servers. Also, these messages don't appear under the
'Notifications' page on the web interface. I've adjusted the settings
and eliminated any 'Recovery' options for events or notifications, but I
still get the messages.
Has anyone seen these messages before? Can anyone give me advice on
what setting I have wrong or is this a bug I need to report?
Thanks in advance for any help!
-Frank Guarino
[EMAIL PROTECTED]
begin:vcard
fn:Frank Guarino
n:Guarino;Frank
org:Institutional Business Systems;Data Center Operation
adr:M/S: 601-150;;4800 Oak Grove Dr.;Pasadena;CA;91109;USA
email;internet:[EMAIL PROTECTED]
title:Unix System Administrator
tel;work:818.393.7542
tel;fax:818.354.3448
x-mozilla-html:FALSE
version:2.1
end:vcard
