nagios isn't running well
Eric Hill
eric at spins.com
Fri Jan 3 21:44:47 CET 2003
check_ping works fine both from a root prompt and from `su nagios`
check_http behaves the same.
-eric
> -----Original Message-----
> From: Jolet, John [mailto:John.Jolet at misyshealthcare.com]
> Sent: Friday, January 03, 2003 12:25 PM
> To: 'Eric Hill'
> Subject: RE: [Nagios-users] nagios isn't running well
>
>
> what happens when you run the plugins from the command line?
>
> -----Original Message-----
> From: Eric Hill [mailto:eric at spins.com]
> Sent: Friday, January 03, 2003 1:46 PM
> To: nagios-users at lists.sourceforge.net
> Subject: [Nagios-users] nagios isn't running well
>
>
> Hi All,
>
> I'm just getting started with Nagios on FreeBSD, and it's (or
> I'm) limping
> out of the gate. I've set up two hosts, one with ping and
> http and one with
> just ping. Nagios isn't seeing either of them and I've been
> wracking my
> brain trying to figure out what is going on. Per the earlier message,
> /sbin/ping is indeed suid root. I haven't been able to install
> nagios-plugins from ports because it is broken somehow (both
> make and gmake
> break), but I have the basic checks installed in
> nagios/libexec so I should
> at least be able to set up basic hosts, right? Unfortunately, I get
> notifications like "check_ping: %s: Warning threshold must be
> integer or
> percentage!" or "CRITICAL - Plugin timed out after 10
> seconds" (both for
> ping). check_http gives "Socket timeout after 10 seconds"
> though (presumably
> it's a port 80 check) this is our main corporate webserver. Could it
> possibly be because I'm running Apache2 rather than 1.x?
> FreeBSD vs. Linux?
> I'm going to have to choose something else if I can't figure
> this out. My
> sense is that Nagios shouldn't be this finicky, but for me it is.
>
> -eric
>
> hosts.cfg
> ---------
> # Generic host definition template
> define host{
> ; The name of this host template - referenced in other host
> definitions, used for template recursion/resolution
> name generic-host
> notifications_enabled 1 ; Host
> notifications are
> enabled
> event_handler_enabled 1 ; Host event
> handler is
> enabled
> flap_detection_enabled 1 ; Flap
> detection 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
>
> register 0 ; DONT REGISTER THIS
> DEFINITION - ITS NOT A REAL HOST, JUST A TEMPLATE!
> }
>
> # 'nt1' host definition
> define host{
> use generic-host ; Name of host
> template to use
> host_name comet
> alias Corp. File/Print Server
> address xx.xx.xx.xx
> check_command check-host-alive
> max_check_attempts 10
> notification_interval 60
> notification_period 24x7
> notification_options d,u,r
> }
>
> # 'linux1' host definition
> define host{
> use generic-host ; Name of host
> template to use
>
> host_name elguapo
> alias Linux Server #1
> address xx.xx.xx.xx
> check_command check-host-alive
> max_check_attempts 10
> notification_interval 60
> notification_period 24x7
> notification_options d,u,r
> }
>
> nagios.cfg
> ----------
> log_file=/usr/local/nagios/var/nagios.log
> cfg_file=/usr/local/nagios/etc/checkcommands.cfg
> cfg_file=/usr/local/nagios/etc/misccommands.cfg
>
> # You can split other types of object definitions across several
> # config files if you wish (as done here), or keep them all in a
> # single config file.
>
> cfg_file=/usr/local/nagios/etc/contactgroups.cfg
> cfg_file=/usr/local/nagios/etc/contacts.cfg
> #cfg_file=/usr/local/nagios/etc/dependencies.cfg
> #cfg_file=/usr/local/nagios/etc/escalations.cfg
> cfg_file=/usr/local/nagios/etc/hostgroups.cfg
> cfg_file=/usr/local/nagios/etc/hosts.cfg
> cfg_file=/usr/local/nagios/etc/services.cfg
> cfg_file=/usr/local/nagios/etc/timeperiods.cfg
>
> resource_file=/usr/local/nagios/etc/resource.cfg
> status_file=/usr/local/nagios/var/status.log
>
> nagios_user=nagios
> nagios_group=nagios
>
> check_external_commands=1
> #command_check_interval=15s
> command_check_interval=-1
> command_file=/usr/local/nagios/var/rw/nagios.cmd
>
> comment_file=/usr/local/nagios/var/comment.log
> downtime_file=/usr/local/nagios/var/downtime.log
> lock_file=/usr/local/nagios/var/nagios.lock
> temp_file=/usr/local/nagios/var/nagios.tmp
>
> # n = None - don't rotate the log
> # h = Hourly rotation (top of the hour)
> # d = Daily rotation (midnight every day)
> # w = Weekly rotation (midnight on Saturday evening)
> # m = Monthly rotation (midnight last day of month)
> log_archive_path=/usr/local/nagios/var/archives
> use_syslog=1
>
> # If you don't want notifications to be logged, set this value to 0.
> # If notifications should be logged, set the value to 1.
>
> log_service_retries=1
> log_host_retries=1
> log_event_handlers=1
> log_passive_service_checks=1
>
> #global_host_event_handler=somecommand
> #global_service_event_handler=somecommand
>
> # n = None - don't use any delay between checks
> # d = Use a "dumb" delay of 1 second between checks
> # s = Use "smart" inter-check delay calculation
> # x.xx = Use an inter-check delay of x.xx seconds
> inter_check_delay_method=s
>
> # s = Use "smart" interleave factor calculation
> # x = Use an interleave factor of x, where x is a
> # number greater than or equal to 1.
>
> # being executed.
>
> sleep_time=1
>
> service_check_timeout=60
> host_check_timeout=30
> event_handler_timeout=30
> notification_timeout=30
> ocsp_timeout=5
> perfdata_timeout=5
>
> retain_state_information=1
> state_retention_file=/usr/local/nagios/var/status.sav
> retention_update_interval=60
> use_retained_program_state=0
> interval_length=60
>
> use_agressive_host_checking=0
> execute_service_checks=1
> accept_passive_service_checks=1
>
> enable_notifications=1
>
> #host_perfdata_command=process-host-perfdata
> #service_perfdata_command=process-service-perfdata
>
> obsess_over_services=0
> #ocsp_command=somecommand
>
> # If you have problems with service checks never getting
> # rescheduled, you might want to try enabling this option.
> # Values: 1 = enable checks, 0 = disable checks
> check_for_orphaned_services=1
>
> check_service_freshness=1
> freshness_check_interval=60
> aggregate_status_updates=1
> status_update_interval=15
>
> enable_flap_detection=1
> low_service_flap_threshold=5.0
> high_service_flap_threshold=20.0
> low_host_flap_threshold=5.0
> high_host_flap_threshold=20.0
>
> # us (MM-DD-YYYY HH:MM:SS)
> # euro (DD-MM-YYYY HH:MM:SS)
> # iso8601 (YYYY-MM-DD HH:MM:SS)
> # strict-iso8601 (YYYY-MM-DDTHH:MM:SS)
> date_format=us
>
> illegal_object_name_chars=`~!$%^&*|'"<>?,()=
> illegal_macro_output_chars=`~$&|'"<>
>
> admin_email=helpdesk at spins.com
> admin_pager=pagenagios
>
> # EOF (End of file)
>
> services.cfg
> ------------
> # Generic service definition template
> define service{
> ; The 'name' of this service template, referenced in
> other service
> definitions
> name generic-service
> active_checks_enabled 1 ; Active
> service checks are
> enabled
> passive_checks_enabled 1 ; Passive
> service checks are
> enabled/accepted
> parallelize_check 1 ; Active
> service checks
> should be parallelized (disabling this can lead to major per
> formance problems)
> obsess_over_service 1 ; We should
> obsess over this
> service (if necessary)
> check_freshness 0 ; Default is
> to NOT check
> service 'freshness'
> notifications_enabled 1 ; Service
> notifications are
> enabled
> event_handler_enabled 1 ; Service
> event handler is
> enabled
> flap_detection_enabled 1 ; Flap
> detection 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
>
> register 0 ; DONT REGISTER THIS
> DEFINITION - ITS NOT A REAL SERVICE, JUST A TEMPLATE!
> }
>
> # Service definition
> define service{
> use generic-service
> ; Name of
> service template to use
>
> host_name comet,elguapo
> service_description PING
> is_volatile 0
> check_period 24x7
> max_check_attempts 3
> normal_check_interval 5
> retry_check_interval 1
> contact_groups nt-admins
> notification_interval 120
> notification_period 24x7
> notification_options c,r
> check_command check_ping!100.0,20%!500.0,60%
> }
>
> # Service definition
> define service{
> use generic-service
> ; Name of
> service template to use
>
> host_name comet
> service_description HTTP
> is_volatile 0
> check_period 24x7
> max_check_attempts 3
> normal_check_interval 5
> retry_check_interval 1
> contact_groups nt-admins
> notification_interval 120
> notification_period 24x7
> notification_options w,u,c,r
> check_command check_http
> }
>
> (etc...most cfg is stock)
>
>
> -------------------------------------------------------
> This sf.net email is sponsored by:ThinkGeek
> Welcome to geek heaven.
> http://thinkgeek.com/sf
> _______________________________________________
> Nagios-users mailing list
> Nagios-users at lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/nagios-users
>
-------------------------------------------------------
This sf.net email is sponsored by:ThinkGeek
Welcome to geek heaven.
http://thinkgeek.com/sf
More information about the Users
mailing list