Browse files

- add sanitized nagios module

  • Loading branch information...
1 parent 28d14bb commit e446636f0e15f41271f14249ab07efeb3f31eb3e @jordansissel jordansissel committed Aug 15, 2011
View
370 nagios/files/cgi.cfg
@@ -0,0 +1,370 @@
+#################################################################
+#
+# CGI.CFG - Sample CGI Configuration File for Nagios
+#
+#################################################################
+
+
+# MAIN CONFIGURATION FILE
+# This tells the CGIs where to find your main configuration file.
+# The CGIs will read the main and host config files for any other
+# data they might need.
+
+main_config_file=/etc/nagios3/nagios.cfg
+
+
+
+# PHYSICAL HTML PATH
+# This is the path where the HTML files for Nagios reside. This
+# value is used to locate the logo images needed by the statusmap
+# and statuswrl CGIs.
+
+physical_html_path=/usr/share/nagios3/htdocs
+
+
+
+# URL HTML PATH
+# This is the path portion of the URL that corresponds to the
+# physical location of the Nagios HTML files (as defined above).
+# This value is used by the CGIs to locate the online documentation
+# and graphics. If you access the Nagios pages with an URL like
+# http://www.myhost.com/nagios, this value should be '/nagios'
+# (without the quotes).
+
+url_html_path=/nagios3
+
+
+
+# CONTEXT-SENSITIVE HELP
+# This option determines whether or not a context-sensitive
+# help icon will be displayed for most of the CGIs.
+# Values: 0 = disables context-sensitive help
+# 1 = enables context-sensitive help
+
+show_context_help=1
+
+
+
+# PENDING STATES OPTION
+# This option determines what states should be displayed in the web
+# interface for hosts/services that have not yet been checked.
+# Values: 0 = leave hosts/services that have not been check yet in their original state
+# 1 = mark hosts/services that have not been checked yet as PENDING
+
+use_pending_states=1
+
+# NAGIOS PROCESS CHECK COMMAND
+# This is the full path and filename of the program used to check
+# the status of the Nagios process. It is used only by the CGIs
+# and is completely optional. However, if you don't use it, you'll
+# see warning messages in the CGIs about the Nagios process
+# not running and you won't be able to execute any commands from
+# the web interface. The program should follow the same rules
+# as plugins; the return codes are the same as for the plugins,
+# it should have timeout protection, it should output something
+# to STDIO, etc.
+#
+# Note: The command line for the check_nagios plugin below may
+# have to be tweaked a bit, as different versions of the plugin
+# use different command line arguments/syntaxes.
+
+nagios_check_command=/usr/lib/nagios/plugins/check_nagios /var/cache/nagios3/status.dat 5 '/usr/sbin/nagios3'
+
+
+# AUTHENTICATION USAGE
+# This option controls whether or not the CGIs will use any
+# authentication when displaying host and service information, as
+# well as committing commands to Nagios for processing.
+#
+# Read the HTML documentation to learn how the authorization works!
+#
+# NOTE: It is a really *bad* idea to disable authorization, unless
+# you plan on removing the command CGI (cmd.cgi)! Failure to do
+# so will leave you wide open to kiddies messing with Nagios and
+# possibly hitting you with a denial of service attack by filling up
+# your drive by continuously writing to your command file!
+#
+# Setting this value to 0 will cause the CGIs to *not* use
+# authentication (bad idea), while any other value will make them
+# use the authentication functions (the default).
+
+use_authentication=1
+
+
+
+
+# x509 CERT AUTHENTICATION
+# When enabled, this option allows you to use x509 cert (SSL)
+# authentication in the CGIs. This is an advanced option and should
+# not be enabled unless you know what you're doing.
+
+use_ssl_authentication=0
+
+
+
+
+# DEFAULT USER
+# Setting this variable will define a default user name that can
+# access pages without authentication. This allows people within a
+# secure domain (i.e., behind a firewall) to see the current status
+# without authenticating. You may want to use this to avoid basic
+# authentication if you are not using a secure server since basic
+# authentication transmits passwords in the clear.
+#
+# Important: Do not define a default username unless you are
+# running a secure web server and are sure that everyone who has
+# access to the CGIs has been authenticated in some manner! If you
+# define this variable, anyone who has not authenticated to the web
+# server will inherit all rights you assign to this user!
+
+#default_user_name=guest
+
+
+
+# SYSTEM/PROCESS INFORMATION ACCESS
+# This option is a comma-delimited list of all usernames that
+# have access to viewing the Nagios process information as
+# provided by the Extended Information CGI (extinfo.cgi). By
+# default, *no one* has access to this unless you choose to
+# not use authorization. You may use an asterisk (*) to
+# authorize any user who has authenticated to the web server.
+
+authorized_for_system_information=hoover
+
+
+
+# CONFIGURATION INFORMATION ACCESS
+# This option is a comma-delimited list of all usernames that
+# can view ALL configuration information (hosts, commands, etc).
+# By default, users can only view configuration information
+# for the hosts and services they are contacts for. You may use
+# an asterisk (*) to authorize any user who has authenticated
+# to the web server.
+
+authorized_for_configuration_information=hoover
+
+
+
+# SYSTEM/PROCESS COMMAND ACCESS
+# This option is a comma-delimited list of all usernames that
+# can issue shutdown and restart commands to Nagios via the
+# command CGI (cmd.cgi). Users in this list can also change
+# the program mode to active or standby. By default, *no one*
+# has access to this unless you choose to not use authorization.
+# You may use an asterisk (*) to authorize any user who has
+# authenticated to the web server.
+
+authorized_for_system_commands=hoover
+
+
+
+# GLOBAL HOST/SERVICE VIEW ACCESS
+# These two options are comma-delimited lists of all usernames that
+# can view information for all hosts and services that are being
+# monitored. By default, users can only view information
+# for hosts or services that they are contacts for (unless you
+# you choose to not use authorization). You may use an asterisk (*)
+# to authorize any user who has authenticated to the web server.
+
+
+authorized_for_all_services=hoover
+authorized_for_all_hosts=hoover
+
+
+
+# GLOBAL HOST/SERVICE COMMAND ACCESS
+# These two options are comma-delimited lists of all usernames that
+# can issue host or service related commands via the command
+# CGI (cmd.cgi) for all hosts and services that are being monitored.
+# By default, users can only issue commands for hosts or services
+# that they are contacts for (unless you you choose to not use
+# authorization). You may use an asterisk (*) to authorize any
+# user who has authenticated to the web server.
+
+authorized_for_all_service_commands=hoover
+authorized_for_all_host_commands=hoover
+
+
+
+# READ-ONLY USERS
+# A comma-delimited list of usernames that have read-only rights in
+# the CGIs. This will block any service or host commands normally shown
+# on the extinfo CGI pages. It will also block comments from being shown
+# to read-only users.
+
+#authorized_for_read_only=user1,user2
+
+
+
+
+# STATUSMAP BACKGROUND IMAGE
+# This option allows you to specify an image to be used as a
+# background in the statusmap CGI. It is assumed that the image
+# resides in the HTML images path (i.e. /usr/local/nagios/share/images).
+# This path is automatically determined by appending "/images"
+# to the path specified by the 'physical_html_path' directive.
+# Note: The image file may be in GIF, PNG, JPEG, or GD2 format.
+# However, I recommend that you convert your image to GD2 format
+# (uncompressed), as this will cause less CPU load when the CGI
+# generates the image.
+
+#statusmap_background_image=smbackground.gd2
+
+
+
+
+# STATUSMAP TRANSPARENCY INDEX COLOR
+# These options set the r,g,b values of the background color used the statusmap CGI,
+# so normal browsers that can't show real png transparency set the desired color as
+# a background color instead (to make it look pretty).
+# Defaults to white: (R,G,B) = (255,255,255).
+
+#color_transparency_index_r=255
+#color_transparency_index_g=255
+#color_transparency_index_b=255
+
+
+
+
+# DEFAULT STATUSMAP LAYOUT METHOD
+# This option allows you to specify the default layout method
+# the statusmap CGI should use for drawing hosts. If you do
+# not use this option, the default is to use user-defined
+# coordinates. Valid options are as follows:
+# 0 = User-defined coordinates
+# 1 = Depth layers
+# 2 = Collapsed tree
+# 3 = Balanced tree
+# 4 = Circular
+# 5 = Circular (Marked Up)
+
+default_statusmap_layout=5
+
+
+
+# DEFAULT STATUSWRL LAYOUT METHOD
+# This option allows you to specify the default layout method
+# the statuswrl (VRML) CGI should use for drawing hosts. If you
+# do not use this option, the default is to use user-defined
+# coordinates. Valid options are as follows:
+# 0 = User-defined coordinates
+# 2 = Collapsed tree
+# 3 = Balanced tree
+# 4 = Circular
+
+default_statuswrl_layout=4
+
+
+
+# STATUSWRL INCLUDE
+# This option allows you to include your own objects in the
+# generated VRML world. It is assumed that the file
+# resides in the HTML path (i.e. /usr/local/nagios/share).
+
+#statuswrl_include=myworld.wrl
+
+
+
+# PING SYNTAX
+# This option determines what syntax should be used when
+# attempting to ping a host from the WAP interface (using
+# the statuswml CGI. You must include the full path to
+# the ping binary, along with all required options. The
+# $HOSTADDRESS$ macro is substituted with the address of
+# the host before the command is executed.
+# Please note that the syntax for the ping binary is
+# notorious for being different on virtually ever *NIX
+# OS and distribution, so you may have to tweak this to
+# work on your system.
+
+ping_syntax=/bin/ping -n -U -c 5 $HOSTADDRESS$
+
+
+
+# REFRESH RATE
+# This option allows you to specify the refresh rate in seconds
+# of various CGIs (status, statusmap, extinfo, and outages).
+
+refresh_rate=90
+
+
+
+# ESCAPE HTML TAGS
+# This option determines whether HTML tags in host and service
+# status output is escaped in the web interface. If enabled,
+# your plugin output will not be able to contain clickable links.
+
+escape_html_tags=1
+
+
+
+
+# SOUND OPTIONS
+# These options allow you to specify an optional audio file
+# that should be played in your browser window when there are
+# problems on the network. The audio files are used only in
+# the status CGI. Only the sound for the most critical problem
+# will be played. Order of importance (higher to lower) is as
+# follows: unreachable hosts, down hosts, critical services,
+# warning services, and unknown services. If there are no
+# visible problems, the sound file optionally specified by
+# 'normal_sound' variable will be played.
+#
+#
+# <varname>=<sound_file>
+#
+# Note: All audio files must be placed in the /media subdirectory
+# under the HTML path (i.e. /usr/local/nagios/share/media/).
+
+#host_unreachable_sound=hostdown.wav
+#host_down_sound=hostdown.wav
+#service_critical_sound=critical.wav
+#service_warning_sound=warning.wav
+#service_unknown_sound=warning.wav
+#normal_sound=noproblem.wav
+
+
+
+# URL TARGET FRAMES
+# These options determine the target frames in which notes and
+# action URLs will open.
+
+action_url_target=_blank
+notes_url_target=_blank
+
+
+
+
+# LOCK AUTHOR NAMES OPTION
+# This option determines whether users can change the author name
+# when submitting comments, scheduling downtime. If disabled, the
+# author names will be locked into their contact name, as defined in Nagios.
+# Values: 0 = allow editing author names
+# 1 = lock author names (disallow editing)
+
+lock_author_names=1
+
+
+
+
+# SPLUNK INTEGRATION OPTIONS
+# These options allow you to enable integration with Splunk
+# in the web interface. If enabled, you'll be presented with
+# "Splunk It" links in various places in the CGIs (log file,
+# alert history, host/service detail, etc). Useful if you're
+# trying to research why a particular problem occurred.
+# For more information on Splunk, visit http://www.splunk.com/
+
+# This option determines whether the Splunk integration is enabled
+# Values: 0 = disable Splunk integration
+# 1 = enable Splunk integration
+
+#enable_splunk_integration=1
+
+
+# This option should be the URL used to access your instance of Splunk
+
+#splunk_url=http://127.0.0.1:8000/
+
+
+
View
21 nagios/files/contacts.cfg
@@ -0,0 +1,21 @@
+define contact {
+ name base-contact
+ service_notification_period 24x7
+ host_notification_period 24x7
+ service_notification_options w,u,c,f,s
+ host_notification_options d,u,f,s
+ service_notification_commands notify-nobody
+ host_notification_commands notify-nobody
+
+ register 0 # This is a template.
+}
+
+define contact {
+ use base-contact
+ contact_name default
+}
+
+define command {
+ command_name notify-nobody
+ command_line /bin/true
+}
View
16 nagios/files/hosts-base.cfg
@@ -0,0 +1,16 @@
+define host {
+ name base-host
+ register 0
+ check_command check-host-alive
+
+ contacts default
+ event_handler_enabled 1
+ failure_prediction_enabled 1
+ flap_detection_enabled 1
+ max_check_attempts 4
+ notification_period 24x7
+ notifications_enabled 1
+ process_perf_data 1
+ retain_nonstatus_information 1
+ retain_status_information 1
+}
View
49 nagios/files/nagios-to-loggly.rb
@@ -0,0 +1,49 @@
+#!/usr/bin/env ruby
+require "rubygems"
+require "eventmachine-tail"
+require "em-http-request"
+require "optparse"
+require "json"
+
+def main(args)
+ url = nil
+
+ opts = OptionParser.new do |opts|
+ opts.banner = "Usage: #{$0} [options]"
+
+ opts.on("-u URL", "--url URL",
+ "(required) The input key for the http input you configured on loggly") do |x|
+ url = x
+ end # -i / --input-key
+ end # OptionParser.new
+
+ opts.parse!(args)
+
+ if !url
+ $stderr.puts opts.banner
+ $stderr.puts "No url specified (-u flag missing)"
+ return 1
+ end
+
+ data = ENV.to_hash.reject { |k,value| k !~ /^NAGIOS_/ }.to_json
+
+ EventMachine.run do
+ http = EventMachine::HttpRequest.new(url)
+
+ p :data => data
+ req = http.post :body => data
+
+ start = Time.now
+ req.callback do
+ # TODO(sissel): Parse the json response and report errors, if any.
+ duration = Time.now - start
+ puts "(#{duration} secs) #{req.response}"
+ EventMachine::stop_event_loop
+ end # req.callback
+ req.errback do
+ $stderr.puts "Error while sending '#{line}' to '#{url}' {#{req}}"
+ end # req.errback
+ end # EventMachine.run
+end # def main
+
+main(ARGV)
View
1,328 nagios/files/nagios.cfg
@@ -0,0 +1,1328 @@
+##############################################################################
+#
+# NAGIOS.CFG - Sample Main Config File for Nagios
+#
+#
+##############################################################################
+
+
+# LOG FILE
+# This is the main log file where service and host events are logged
+# for historical purposes. This should be the first option specified
+# in the config file!!!
+
+log_file=/var/log/nagios3/nagios.log
+
+# Commands definitions
+cfg_file=/etc/nagios3/commands.cfg
+
+# Debian also defaults to using the check commands defined by the debian
+# nagios-plugins package
+cfg_dir=/etc/nagios-plugins/config
+
+# Debian uses by default a configuration directory where nagios3-common,
+# other packages and the local admin can dump or link configuration
+# files into.
+cfg_dir=/etc/nagios3/conf.d
+cfg_dir=/etc/nagios3/hosts.d
+cfg_dir=/etc/nagios3/checks.d
+
+# OBJECT CONFIGURATION FILE(S)
+# These are the object configuration files in which you define hosts,
+# host groups, contacts, contact groups, services, etc.
+# You can split your object definitions across several config files
+# if you wish (as shown below), or keep them all in a single config file.
+
+# You can specify individual object config files as shown below:
+#cfg_file=/etc/nagios3/objects/commands.cfg
+#cfg_file=/etc/nagios3/objects/contacts.cfg
+#cfg_file=/etc/nagios3/objects/timeperiods.cfg
+#cfg_file=/etc/nagios3/objects/templates.cfg
+
+# Definitions for monitoring a Windows machine
+#cfg_file=/etc/nagios3/objects/windows.cfg
+
+# Definitions for monitoring a router/switch
+#cfg_file=/etc/nagios3/objects/switch.cfg
+
+# Definitions for monitoring a network printer
+#cfg_file=/etc/nagios3/objects/printer.cfg
+
+
+# You can also tell Nagios to process all config files (with a .cfg
+# extension) in a particular directory by using the cfg_dir
+# directive as shown below:
+
+#cfg_dir=/etc/nagios3/servers
+#cfg_dir=/etc/nagios3/printers
+#cfg_dir=/etc/nagios3/switches
+#cfg_dir=/etc/nagios3/routers
+
+
+
+
+# OBJECT CACHE FILE
+# This option determines where object definitions are cached when
+# Nagios starts/restarts. The CGIs read object definitions from
+# this cache file (rather than looking at the object config files
+# directly) in order to prevent inconsistencies that can occur
+# when the config files are modified after Nagios starts.
+
+object_cache_file=/var/cache/nagios3/objects.cache
+
+
+
+# PRE-CACHED OBJECT FILE
+# This options determines the location of the precached object file.
+# If you run Nagios with the -p command line option, it will preprocess
+# your object configuration file(s) and write the cached config to this
+# file. You can then start Nagios with the -u option to have it read
+# object definitions from this precached file, rather than the standard
+# object configuration files (see the cfg_file and cfg_dir options above).
+# Using a precached object file can speed up the time needed to (re)start
+# the Nagios process if you've got a large and/or complex configuration.
+# Read the documentation section on optimizing Nagios to find our more
+# about how this feature works.
+
+precached_object_file=/var/lib/nagios3/objects.precache
+
+
+
+# RESOURCE FILE
+# This is an optional resource file that contains $USERx$ macro
+# definitions. Multiple resource files can be specified by using
+# multiple resource_file definitions. The CGIs will not attempt to
+# read the contents of resource files, so information that is
+# considered to be sensitive (usernames, passwords, etc) can be
+# defined as macros in this file and restrictive permissions (600)
+# can be placed on this file.
+
+resource_file=/etc/nagios3/resource.cfg
+
+
+
+# STATUS FILE
+# This is where the current status of all monitored services and
+# hosts is stored. Its contents are read and processed by the CGIs.
+# The contents of the status file are deleted every time Nagios
+# restarts.
+
+status_file=/var/cache/nagios3/status.dat
+
+
+
+# STATUS FILE UPDATE INTERVAL
+# This option determines the frequency (in seconds) that
+# Nagios will periodically dump program, host, and
+# service status data.
+
+status_update_interval=10
+
+
+
+# NAGIOS USER
+# This determines the effective user that Nagios should run as.
+# You can either supply a username or a UID.
+
+nagios_user=nagios
+
+
+
+# NAGIOS GROUP
+# This determines the effective group that Nagios should run as.
+# You can either supply a group name or a GID.
+
+nagios_group=nagios
+
+
+
+# EXTERNAL COMMAND OPTION
+# This option allows you to specify whether or not Nagios should check
+# for external commands (in the command file defined below). By default
+# Nagios will *not* check for external commands, just to be on the
+# cautious side. If you want to be able to use the CGI command interface
+# you will have to enable this.
+# Values: 0 = disable commands, 1 = enable commands
+
+check_external_commands=1
+
+
+
+# EXTERNAL COMMAND CHECK INTERVAL
+# This is the interval at which Nagios should check for external commands.
+# This value works of the interval_length you specify later. If you leave
+# that at its default value of 60 (seconds), a value of 1 here will cause
+# Nagios to check for external commands every minute. If you specify a
+# number followed by an "s" (i.e. 15s), this will be interpreted to mean
+# actual seconds rather than a multiple of the interval_length variable.
+# Note: In addition to reading the external command file at regularly
+# scheduled intervals, Nagios will also check for external commands after
+# event handlers are executed.
+# NOTE: Setting this value to -1 causes Nagios to check the external
+# command file as often as possible.
+
+#command_check_interval=15s
+command_check_interval=-1
+
+
+
+# EXTERNAL COMMAND FILE
+# This is the file that Nagios checks for external command requests.
+# It is also where the command CGI will write commands that are submitted
+# by users, so it must be writeable by the user that the web server
+# is running as (usually 'nobody'). Permissions should be set at the
+# directory level instead of on the file, as the file is deleted every
+# time its contents are processed.
+# Debian Users: In case you didn't read README.Debian yet, _NOW_ is the
+# time to do it.
+
+command_file=/var/lib/nagios3/rw/nagios.cmd
+
+
+
+# EXTERNAL COMMAND BUFFER SLOTS
+# This settings is used to tweak the number of items or "slots" that
+# the Nagios daemon should allocate to the buffer that holds incoming
+# external commands before they are processed. As external commands
+# are processed by the daemon, they are removed from the buffer.
+
+external_command_buffer_slots=4096
+
+
+
+# LOCK FILE
+# This is the lockfile that Nagios will use to store its PID number
+# in when it is running in daemon mode.
+
+lock_file=/var/run/nagios3/nagios3.pid
+
+
+
+# TEMP FILE
+# This is a temporary file that is used as scratch space when Nagios
+# updates the status log, cleans the comment file, etc. This file
+# is created, used, and deleted throughout the time that Nagios is
+# running.
+
+temp_file=/var/cache/nagios3/nagios.tmp
+
+
+
+# TEMP PATH
+# This is path where Nagios can create temp files for service and
+# host check results, etc.
+
+temp_path=/tmp
+
+
+
+# EVENT BROKER OPTIONS
+# Controls what (if any) data gets sent to the event broker.
+# Values: 0 = Broker nothing
+# -1 = Broker everything
+# <other> = See documentation
+
+event_broker_options=-1
+
+
+
+# EVENT BROKER MODULE(S)
+# This directive is used to specify an event broker module that should
+# by loaded by Nagios at startup. Use multiple directives if you want
+# to load more than one module. Arguments that should be passed to
+# the module at startup are seperated from the module path by a space.
+#
+#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+# WARNING !!! WARNING !!! WARNING !!! WARNING !!! WARNING !!! WARNING
+#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+#
+# Do NOT overwrite modules while they are being used by Nagios or Nagios
+# will crash in a fiery display of SEGFAULT glory. This is a bug/limitation
+# either in dlopen(), the kernel, and/or the filesystem. And maybe Nagios...
+#
+# The correct/safe way of updating a module is by using one of these methods:
+# 1. Shutdown Nagios, replace the module file, restart Nagios
+# 2. Delete the original module file, move the new module file into place, restart Nagios
+#
+# Example:
+#
+# broker_module=<modulepath> [moduleargs]
+
+#broker_module=/somewhere/module1.o
+#broker_module=/somewhere/module2.o arg1 arg2=3 debug=0
+
+
+
+# LOG ROTATION METHOD
+# This is the log rotation method that Nagios should use to rotate
+# the main log file. Values are as follows..
+# 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_rotation_method=d
+
+
+
+# LOG ARCHIVE PATH
+# This is the directory where archived (rotated) log files should be
+# placed (assuming you've chosen to do log rotation).
+
+log_archive_path=/var/log/nagios3/archives
+
+
+
+# LOGGING OPTIONS
+# If you want messages logged to the syslog facility, as well as the
+# Nagios log file set this option to 1. If not, set it to 0.
+
+use_syslog=1
+
+
+
+# NOTIFICATION LOGGING OPTION
+# 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_notifications=1
+
+
+
+# SERVICE RETRY LOGGING OPTION
+# If you don't want service check retries to be logged, set this value
+# to 0. If retries should be logged, set the value to 1.
+
+log_service_retries=1
+
+
+
+# HOST RETRY LOGGING OPTION
+# If you don't want host check retries to be logged, set this value to
+# 0. If retries should be logged, set the value to 1.
+
+log_host_retries=1
+
+
+
+# EVENT HANDLER LOGGING OPTION
+# If you don't want host and service event handlers to be logged, set
+# this value to 0. If event handlers should be logged, set the value
+# to 1.
+
+log_event_handlers=1
+
+
+
+# INITIAL STATES LOGGING OPTION
+# If you want Nagios to log all initial host and service states to
+# the main log file (the first time the service or host is checked)
+# you can enable this option by setting this value to 1. If you
+# are not using an external application that does long term state
+# statistics reporting, you do not need to enable this option. In
+# this case, set the value to 0.
+
+log_initial_states=0
+
+
+
+# EXTERNAL COMMANDS LOGGING OPTION
+# If you don't want Nagios to log external commands, set this value
+# to 0. If external commands should be logged, set this value to 1.
+# Note: This option does not include logging of passive service
+# checks - see the option below for controlling whether or not
+# passive checks are logged.
+
+log_external_commands=1
+
+
+
+# PASSIVE CHECKS LOGGING OPTION
+# If you don't want Nagios to log passive host and service checks, set
+# this value to 0. If passive checks should be logged, set
+# this value to 1.
+
+log_passive_checks=1
+
+
+
+# GLOBAL HOST AND SERVICE EVENT HANDLERS
+# These options allow you to specify a host and service event handler
+# command that is to be run for every host or service state change.
+# The global event handler is executed immediately prior to the event
+# handler that you have optionally specified in each host or
+# service definition. The command argument is the short name of a
+# command definition that you define in your host configuration file.
+# Read the HTML docs for more information.
+
+global_host_event_handler=log-to-loggly
+global_service_event_handler=log-to-loggly
+
+
+
+# SERVICE INTER-CHECK DELAY METHOD
+# This is the method that Nagios should use when initially
+# "spreading out" service checks when it starts monitoring. The
+# default is to use smart delay calculation, which will try to
+# space all service checks out evenly to minimize CPU load.
+# Using the dumb setting will cause all checks to be scheduled
+# at the same time (with no delay between them)! This is not a
+# good thing for production, but is useful when testing the
+# parallelization functionality.
+# 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
+
+service_inter_check_delay_method=s
+
+
+
+# MAXIMUM SERVICE CHECK SPREAD
+# This variable determines the timeframe (in minutes) from the
+# program start time that an initial check of all services should
+# be completed. Default is 30 minutes.
+
+max_service_check_spread=30
+
+
+
+# SERVICE CHECK INTERLEAVE FACTOR
+# This variable determines how service checks are interleaved.
+# Interleaving the service checks allows for a more even
+# distribution of service checks and reduced load on remote
+# hosts. Setting this value to 1 is equivalent to how versions
+# of Nagios previous to 0.0.5 did service checks. Set this
+# value to s (smart) for automatic calculation of the interleave
+# factor unless you have a specific reason to change it.
+# s = Use "smart" interleave factor calculation
+# x = Use an interleave factor of x, where x is a
+# number greater than or equal to 1.
+
+service_interleave_factor=s
+
+
+
+# HOST INTER-CHECK DELAY METHOD
+# This is the method that Nagios should use when initially
+# "spreading out" host checks when it starts monitoring. The
+# default is to use smart delay calculation, which will try to
+# space all host checks out evenly to minimize CPU load.
+# Using the dumb setting will cause all checks to be scheduled
+# at the same time (with no delay between them)!
+# 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
+
+host_inter_check_delay_method=s
+
+
+
+# MAXIMUM HOST CHECK SPREAD
+# This variable determines the timeframe (in minutes) from the
+# program start time that an initial check of all hosts should
+# be completed. Default is 30 minutes.
+
+max_host_check_spread=30
+
+
+
+# MAXIMUM CONCURRENT SERVICE CHECKS
+# This option allows you to specify the maximum number of
+# service checks that can be run in parallel at any given time.
+# Specifying a value of 1 for this variable essentially prevents
+# any service checks from being parallelized. A value of 0
+# will not restrict the number of concurrent checks that are
+# being executed.
+
+max_concurrent_checks=0
+
+
+
+# HOST AND SERVICE CHECK REAPER FREQUENCY
+# This is the frequency (in seconds!) that Nagios will process
+# the results of host and service checks.
+
+check_result_reaper_frequency=10
+
+
+
+
+# MAX CHECK RESULT REAPER TIME
+# This is the max amount of time (in seconds) that a single
+# check result reaper event will be allowed to run before
+# returning control back to Nagios so it can perform other
+# duties.
+
+max_check_result_reaper_time=30
+
+
+
+
+# CHECK RESULT PATH
+# This is directory where Nagios stores the results of host and
+# service checks that have not yet been processed.
+#
+# Note: Make sure that only one instance of Nagios has access
+# to this directory!
+
+check_result_path=/var/lib/nagios3/spool/checkresults
+
+
+
+
+# MAX CHECK RESULT FILE AGE
+# This option determines the maximum age (in seconds) which check
+# result files are considered to be valid. Files older than this
+# threshold will be mercilessly deleted without further processing.
+
+max_check_result_file_age=3600
+
+
+
+
+# CACHED HOST CHECK HORIZON
+# This option determines the maximum amount of time (in seconds)
+# that the state of a previous host check is considered current.
+# Cached host states (from host checks that were performed more
+# recently that the timeframe specified by this value) can immensely
+# improve performance in regards to the host check logic.
+# Too high of a value for this option may result in inaccurate host
+# states being used by Nagios, while a lower value may result in a
+# performance hit for host checks. Use a value of 0 to disable host
+# check caching.
+
+cached_host_check_horizon=15
+
+
+
+# CACHED SERVICE CHECK HORIZON
+# This option determines the maximum amount of time (in seconds)
+# that the state of a previous service check is considered current.
+# Cached service states (from service checks that were performed more
+# recently that the timeframe specified by this value) can immensely
+# improve performance in regards to predictive dependency checks.
+# Use a value of 0 to disable service check caching.
+
+cached_service_check_horizon=15
+
+
+
+# ENABLE PREDICTIVE HOST DEPENDENCY CHECKS
+# This option determines whether or not Nagios will attempt to execute
+# checks of hosts when it predicts that future dependency logic test
+# may be needed. These predictive checks can help ensure that your
+# host dependency logic works well.
+# Values:
+# 0 = Disable predictive checks
+# 1 = Enable predictive checks (default)
+
+enable_predictive_host_dependency_checks=1
+
+
+
+# ENABLE PREDICTIVE SERVICE DEPENDENCY CHECKS
+# This option determines whether or not Nagios will attempt to execute
+# checks of service when it predicts that future dependency logic test
+# may be needed. These predictive checks can help ensure that your
+# service dependency logic works well.
+# Values:
+# 0 = Disable predictive checks
+# 1 = Enable predictive checks (default)
+
+enable_predictive_service_dependency_checks=1
+
+
+
+# SOFT STATE DEPENDENCIES
+# This option determines whether or not Nagios will use soft state
+# information when checking host and service dependencies. Normally
+# Nagios will only use the latest hard host or service state when
+# checking dependencies. If you want it to use the latest state (regardless
+# of whether its a soft or hard state type), enable this option.
+# Values:
+# 0 = Don't use soft state dependencies (default)
+# 1 = Use soft state dependencies
+
+soft_state_dependencies=0
+
+
+
+# TIME CHANGE ADJUSTMENT THRESHOLDS
+# These options determine when Nagios will react to detected changes
+# in system time (either forward or backwards).
+
+#time_change_threshold=900
+
+
+
+# AUTO-RESCHEDULING OPTION
+# This option determines whether or not Nagios will attempt to
+# automatically reschedule active host and service checks to
+# "smooth" them out over time. This can help balance the load on
+# the monitoring server.
+# WARNING: THIS IS AN EXPERIMENTAL FEATURE - IT CAN DEGRADE
+# PERFORMANCE, RATHER THAN INCREASE IT, IF USED IMPROPERLY
+
+auto_reschedule_checks=0
+
+
+
+# AUTO-RESCHEDULING INTERVAL
+# This option determines how often (in seconds) Nagios will
+# attempt to automatically reschedule checks. This option only
+# has an effect if the auto_reschedule_checks option is enabled.
+# Default is 30 seconds.
+# WARNING: THIS IS AN EXPERIMENTAL FEATURE - IT CAN DEGRADE
+# PERFORMANCE, RATHER THAN INCREASE IT, IF USED IMPROPERLY
+
+auto_rescheduling_interval=30
+
+
+
+# AUTO-RESCHEDULING WINDOW
+# This option determines the "window" of time (in seconds) that
+# Nagios will look at when automatically rescheduling checks.
+# Only host and service checks that occur in the next X seconds
+# (determined by this variable) will be rescheduled. This option
+# only has an effect if the auto_reschedule_checks option is
+# enabled. Default is 180 seconds (3 minutes).
+# WARNING: THIS IS AN EXPERIMENTAL FEATURE - IT CAN DEGRADE
+# PERFORMANCE, RATHER THAN INCREASE IT, IF USED IMPROPERLY
+
+auto_rescheduling_window=180
+
+
+
+# SLEEP TIME
+# This is the number of seconds to sleep between checking for system
+# events and service checks that need to be run.
+
+sleep_time=0.25
+
+
+
+# TIMEOUT VALUES
+# These options control how much time Nagios will allow various
+# types of commands to execute before killing them off. Options
+# are available for controlling maximum time allotted for
+# service checks, host checks, event handlers, notifications, the
+# ocsp command, and performance data commands. All values are in
+# seconds.
+
+service_check_timeout=600
+host_check_timeout=30
+event_handler_timeout=30
+notification_timeout=30
+ocsp_timeout=5
+perfdata_timeout=5
+
+
+
+# RETAIN STATE INFORMATION
+# This setting determines whether or not Nagios will save state
+# information for services and hosts before it shuts down. Upon
+# startup Nagios will reload all saved service and host state
+# information before starting to monitor. This is useful for
+# maintaining long-term data on state statistics, etc, but will
+# slow Nagios down a bit when it (re)starts. Since its only
+# a one-time penalty, I think its well worth the additional
+# startup delay.
+
+retain_state_information=1
+
+
+
+# STATE RETENTION FILE
+# This is the file that Nagios should use to store host and
+# service state information before it shuts down. The state
+# information in this file is also read immediately prior to
+# starting to monitor the network when Nagios is restarted.
+# This file is used only if the preserve_state_information
+# variable is set to 1.
+
+state_retention_file=/var/lib/nagios3/retention.dat
+
+
+
+# RETENTION DATA UPDATE INTERVAL
+# This setting determines how often (in minutes) that Nagios
+# will automatically save retention data during normal operation.
+# If you set this value to 0, Nagios will not save retention
+# data at regular interval, but it will still save retention
+# data before shutting down or restarting. If you have disabled
+# state retention, this option has no effect.
+
+retention_update_interval=60
+
+
+
+# USE RETAINED PROGRAM STATE
+# This setting determines whether or not Nagios will set
+# program status variables based on the values saved in the
+# retention file. If you want to use retained program status
+# information, set this value to 1. If not, set this value
+# to 0.
+
+use_retained_program_state=1
+
+
+
+# USE RETAINED SCHEDULING INFO
+# This setting determines whether or not Nagios will retain
+# the scheduling info (next check time) for hosts and services
+# based on the values saved in the retention file. If you
+# If you want to use retained scheduling info, set this
+# value to 1. If not, set this value to 0.
+
+use_retained_scheduling_info=1
+
+
+
+# RETAINED ATTRIBUTE MASKS (ADVANCED FEATURE)
+# The following variables are used to specify specific host and
+# service attributes that should *not* be retained by Nagios during
+# program restarts.
+#
+# The values of the masks are bitwise ANDs of values specified
+# by the "MODATTR_" definitions found in include/common.h.
+# For example, if you do not want the current enabled/disabled state
+# of flap detection and event handlers for hosts to be retained, you
+# would use a value of 24 for the host attribute mask...
+# MODATTR_EVENT_HANDLER_ENABLED (8) + MODATTR_FLAP_DETECTION_ENABLED (16) = 24
+
+# This mask determines what host attributes are not retained
+retained_host_attribute_mask=0
+
+# This mask determines what service attributes are not retained
+retained_service_attribute_mask=0
+
+# These two masks determine what process attributes are not retained.
+# There are two masks, because some process attributes have host and service
+# options. For example, you can disable active host checks, but leave active
+# service checks enabled.
+retained_process_host_attribute_mask=0
+retained_process_service_attribute_mask=0
+
+# These two masks determine what contact attributes are not retained.
+# There are two masks, because some contact attributes have host and
+# service options. For example, you can disable host notifications for
+# a contact, but leave service notifications enabled for them.
+retained_contact_host_attribute_mask=0
+retained_contact_service_attribute_mask=0
+
+
+
+# INTERVAL LENGTH
+# This is the seconds per unit interval as used in the
+# host/contact/service configuration files. Setting this to 60 means
+# that each interval is one minute long (60 seconds). Other settings
+# have not been tested much, so your mileage is likely to vary...
+
+interval_length=60
+
+
+
+# CHECK FOR UPDATES
+# This option determines whether Nagios will automatically check to
+# see if new updates (releases) are available. It is recommend that you
+# enable this option to ensure that you stay on top of the latest critical
+# patches to Nagios. Nagios is critical to you - make sure you keep it in
+# good shape. Nagios will check once a day for new updates. Data collected
+# by Nagios Enterprises from the update check is processed in accordance
+# with our privacy policy - see http://api.nagios.org for details.
+
+check_for_updates=1
+
+
+
+# BARE UPDATE CHECK
+# This option deterines what data Nagios will send to api.nagios.org when
+# it checks for updates. By default, Nagios will send information on the
+# current version of Nagios you have installed, as well as an indicator as
+# to whether this was a new installation or not. Nagios Enterprises uses
+# this data to determine the number of users running specific version of
+# Nagios. Enable this option if you do not want this information to be sent.
+
+bare_update_check=0
+
+
+
+# AGGRESSIVE HOST CHECKING OPTION
+# If you don't want to turn on aggressive host checking features, set
+# this value to 0 (the default). Otherwise set this value to 1 to
+# enable the aggressive check option. Read the docs for more info
+# on what aggressive host check is or check out the source code in
+# base/checks.c
+
+use_aggressive_host_checking=0
+
+
+
+# SERVICE CHECK EXECUTION OPTION
+# This determines whether or not Nagios will actively execute
+# service checks when it initially starts. If this option is
+# disabled, checks are not actively made, but Nagios can still
+# receive and process passive check results that come in. Unless
+# you're implementing redundant hosts or have a special need for
+# disabling the execution of service checks, leave this enabled!
+# Values: 1 = enable checks, 0 = disable checks
+
+execute_service_checks=1
+
+
+
+# PASSIVE SERVICE CHECK ACCEPTANCE OPTION
+# This determines whether or not Nagios will accept passive
+# service checks results when it initially (re)starts.
+# Values: 1 = accept passive checks, 0 = reject passive checks
+
+accept_passive_service_checks=1
+
+
+
+# HOST CHECK EXECUTION OPTION
+# This determines whether or not Nagios will actively execute
+# host checks when it initially starts. If this option is
+# disabled, checks are not actively made, but Nagios can still
+# receive and process passive check results that come in. Unless
+# you're implementing redundant hosts or have a special need for
+# disabling the execution of host checks, leave this enabled!
+# Values: 1 = enable checks, 0 = disable checks
+
+execute_host_checks=1
+
+
+
+# PASSIVE HOST CHECK ACCEPTANCE OPTION
+# This determines whether or not Nagios will accept passive
+# host checks results when it initially (re)starts.
+# Values: 1 = accept passive checks, 0 = reject passive checks
+
+accept_passive_host_checks=1
+
+
+
+# NOTIFICATIONS OPTION
+# This determines whether or not Nagios will sent out any host or
+# service notifications when it is initially (re)started.
+# Values: 1 = enable notifications, 0 = disable notifications
+
+enable_notifications=1
+
+
+
+# EVENT HANDLER USE OPTION
+# This determines whether or not Nagios will run any host or
+# service event handlers when it is initially (re)started. Unless
+# you're implementing redundant hosts, leave this option enabled.
+# Values: 1 = enable event handlers, 0 = disable event handlers
+
+enable_event_handlers=1
+
+
+
+# PROCESS PERFORMANCE DATA OPTION
+# This determines whether or not Nagios will process performance
+# data returned from service and host checks. If this option is
+# enabled, host performance data will be processed using the
+# host_perfdata_command (defined below) and service performance
+# data will be processed using the service_perfdata_command (also
+# defined below). Read the HTML docs for more information on
+# performance data.
+# Values: 1 = process performance data, 0 = do not process performance data
+
+process_performance_data=0
+
+
+
+# HOST AND SERVICE PERFORMANCE DATA PROCESSING COMMANDS
+# These commands are run after every host and service check is
+# performed. These commands are executed only if the
+# enable_performance_data option (above) is set to 1. The command
+# argument is the short name of a command definition that you
+# define in your host configuration file. Read the HTML docs for
+# more information on performance data.
+
+#host_perfdata_command=process-host-perfdata
+#service_perfdata_command=process-service-perfdata
+
+
+
+# HOST AND SERVICE PERFORMANCE DATA FILES
+# These files are used to store host and service performance data.
+# Performance data is only written to these files if the
+# enable_performance_data option (above) is set to 1.
+
+#host_perfdata_file=/tmp/host-perfdata
+#service_perfdata_file=/tmp/service-perfdata
+
+
+
+# HOST AND SERVICE PERFORMANCE DATA FILE TEMPLATES
+# These options determine what data is written (and how) to the
+# performance data files. The templates may contain macros, special
+# characters (\t for tab, \r for carriage return, \n for newline)
+# and plain text. A newline is automatically added after each write
+# to the performance data file. Some examples of what you can do are
+# shown below.
+
+#host_perfdata_file_template=[HOSTPERFDATA]\t$TIMET$\t$HOSTNAME$\t$HOSTEXECUTIONTIME$\t$HOSTOUTPUT$\t$HOSTPERFDATA$
+#service_perfdata_file_template=[SERVICEPERFDATA]\t$TIMET$\t$HOSTNAME$\t$SERVICEDESC$\t$SERVICEEXECUTIONTIME$\t$SERVICELATENCY$\t$SERVICEOUTPUT$\t$SERVICEPERFDATA$
+
+
+
+# HOST AND SERVICE PERFORMANCE DATA FILE MODES
+# This option determines whether or not the host and service
+# performance data files are opened in write ("w") or append ("a")
+# mode. If you want to use named pipes, you should use the special
+# pipe ("p") mode which avoid blocking at startup, otherwise you will
+# likely want the defult append ("a") mode.
+
+#host_perfdata_file_mode=a
+#service_perfdata_file_mode=a
+
+
+
+# HOST AND SERVICE PERFORMANCE DATA FILE PROCESSING INTERVAL
+# These options determine how often (in seconds) the host and service
+# performance data files are processed using the commands defined
+# below. A value of 0 indicates the files should not be periodically
+# processed.
+
+#host_perfdata_file_processing_interval=0
+#service_perfdata_file_processing_interval=0
+
+
+
+# HOST AND SERVICE PERFORMANCE DATA FILE PROCESSING COMMANDS
+# These commands are used to periodically process the host and
+# service performance data files. The interval at which the
+# processing occurs is determined by the options above.
+
+#host_perfdata_file_processing_command=process-host-perfdata-file
+#service_perfdata_file_processing_command=process-service-perfdata-file
+
+
+
+# OBSESS OVER SERVICE CHECKS OPTION
+# This determines whether or not Nagios will obsess over service
+# checks and run the ocsp_command defined below. Unless you're
+# planning on implementing distributed monitoring, do not enable
+# this option. Read the HTML docs for more information on
+# implementing distributed monitoring.
+# Values: 1 = obsess over services, 0 = do not obsess (default)
+
+obsess_over_services=0
+
+
+
+# OBSESSIVE COMPULSIVE SERVICE PROCESSOR COMMAND
+# This is the command that is run for every service check that is
+# processed by Nagios. This command is executed only if the
+# obsess_over_services option (above) is set to 1. The command
+# argument is the short name of a command definition that you
+# define in your host configuration file. Read the HTML docs for
+# more information on implementing distributed monitoring.
+
+#ocsp_command=somecommand
+
+
+
+# OBSESS OVER HOST CHECKS OPTION
+# This determines whether or not Nagios will obsess over host
+# checks and run the ochp_command defined below. Unless you're
+# planning on implementing distributed monitoring, do not enable
+# this option. Read the HTML docs for more information on
+# implementing distributed monitoring.
+# Values: 1 = obsess over hosts, 0 = do not obsess (default)
+
+obsess_over_hosts=0
+
+
+
+# OBSESSIVE COMPULSIVE HOST PROCESSOR COMMAND
+# This is the command that is run for every host check that is
+# processed by Nagios. This command is executed only if the
+# obsess_over_hosts option (above) is set to 1. The command
+# argument is the short name of a command definition that you
+# define in your host configuration file. Read the HTML docs for
+# more information on implementing distributed monitoring.
+
+#ochp_command=somecommand
+
+
+
+# TRANSLATE PASSIVE HOST CHECKS OPTION
+# This determines whether or not Nagios will translate
+# DOWN/UNREACHABLE passive host check results into their proper
+# state for this instance of Nagios. This option is useful
+# if you have distributed or failover monitoring setup. In
+# these cases your other Nagios servers probably have a different
+# "view" of the network, with regards to the parent/child relationship
+# of hosts. If a distributed monitoring server thinks a host
+# is DOWN, it may actually be UNREACHABLE from the point of
+# this Nagios instance. Enabling this option will tell Nagios
+# to translate any DOWN or UNREACHABLE host states it receives
+# passively into the correct state from the view of this server.
+# Values: 1 = perform translation, 0 = do not translate (default)
+
+translate_passive_host_checks=0
+
+
+
+# PASSIVE HOST CHECKS ARE SOFT OPTION
+# This determines whether or not Nagios will treat passive host
+# checks as being HARD or SOFT. By default, a passive host check
+# result will put a host into a HARD state type. This can be changed
+# by enabling this option.
+# Values: 0 = passive checks are HARD, 1 = passive checks are SOFT
+
+passive_host_checks_are_soft=0
+
+
+
+# ORPHANED HOST/SERVICE CHECK OPTIONS
+# These options determine whether or not Nagios will periodically
+# check for orphaned host service checks. Since service checks are
+# not rescheduled until the results of their previous execution
+# instance are processed, there exists a possibility that some
+# checks may never get rescheduled. A similar situation exists for
+# host checks, although the exact scheduling details differ a bit
+# from service checks. Orphaned checks seem to be a rare
+# problem and should not happen under normal circumstances.
+# If you have problems with service checks never getting
+# rescheduled, make sure you have orphaned service checks enabled.
+# Values: 1 = enable checks, 0 = disable checks
+
+check_for_orphaned_services=1
+check_for_orphaned_hosts=1
+
+
+
+# SERVICE FRESHNESS CHECK OPTION
+# This option determines whether or not Nagios will periodically
+# check the "freshness" of service results. Enabling this option
+# is useful for ensuring passive checks are received in a timely
+# manner.
+# Values: 1 = enabled freshness checking, 0 = disable freshness checking
+
+check_service_freshness=1
+
+
+
+# SERVICE FRESHNESS CHECK INTERVAL
+# This setting determines how often (in seconds) Nagios will
+# check the "freshness" of service check results. If you have
+# disabled service freshness checking, this option has no effect.
+
+service_freshness_check_interval=60
+
+
+
+# HOST FRESHNESS CHECK OPTION
+# This option determines whether or not Nagios will periodically
+# check the "freshness" of host results. Enabling this option
+# is useful for ensuring passive checks are received in a timely
+# manner.
+# Values: 1 = enabled freshness checking, 0 = disable freshness checking
+
+check_host_freshness=0
+
+
+
+# HOST FRESHNESS CHECK INTERVAL
+# This setting determines how often (in seconds) Nagios will
+# check the "freshness" of host check results. If you have
+# disabled host freshness checking, this option has no effect.
+
+host_freshness_check_interval=60
+
+
+
+
+# ADDITIONAL FRESHNESS THRESHOLD LATENCY
+# This setting determines the number of seconds that Nagios
+# will add to any host and service freshness thresholds that
+# it calculates (those not explicitly specified by the user).
+
+additional_freshness_latency=15
+
+
+
+
+# FLAP DETECTION OPTION
+# This option determines whether or not Nagios will try
+# and detect hosts and services that are "flapping".
+# Flapping occurs when a host or service changes between
+# states too frequently. When Nagios detects that a
+# host or service is flapping, it will temporarily suppress
+# notifications for that host/service until it stops
+# flapping. Flap detection is very experimental, so read
+# the HTML documentation before enabling this feature!
+# Values: 1 = enable flap detection
+# 0 = disable flap detection (default)
+
+enable_flap_detection=1
+
+
+
+# FLAP DETECTION THRESHOLDS FOR HOSTS AND SERVICES
+# Read the HTML documentation on flap detection for
+# an explanation of what this option does. This option
+# has no effect if flap detection is disabled.
+
+low_service_flap_threshold=5.0
+high_service_flap_threshold=20.0
+low_host_flap_threshold=5.0
+high_host_flap_threshold=20.0
+
+
+
+# DATE FORMAT OPTION
+# This option determines how short dates are displayed. Valid options
+# include:
+# 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=iso8601
+
+
+
+
+# TIMEZONE OFFSET
+# This option is used to override the default timezone that this
+# instance of Nagios runs in. If not specified, Nagios will use
+# the system configured timezone.
+#
+# NOTE: In order to display the correct timezone in the CGIs, you
+# will also need to alter the Apache directives for the CGI path
+# to include your timezone. Example:
+#
+# <Directory "/usr/local/nagios/sbin/">
+# SetEnv TZ "Australia/Brisbane"
+# ...
+# </Directory>
+
+#use_timezone=US/Mountain
+#use_timezone=Australia/Brisbane
+
+
+
+
+# P1.PL FILE LOCATION
+# This value determines where the p1.pl perl script (used by the
+# embedded Perl interpreter) is located. If you didn't compile
+# Nagios with embedded Perl support, this option has no effect.
+
+p1_file=/usr/lib/nagios3/p1.pl
+
+
+
+# EMBEDDED PERL INTERPRETER OPTION
+# This option determines whether or not the embedded Perl interpreter
+# will be enabled during runtime. This option has no effect if Nagios
+# has not been compiled with support for embedded Perl.
+# Values: 0 = disable interpreter, 1 = enable interpreter
+
+enable_embedded_perl=1
+
+
+
+# EMBEDDED PERL USAGE OPTION
+# This option determines whether or not Nagios will process Perl plugins
+# and scripts with the embedded Perl interpreter if the plugins/scripts
+# do not explicitly indicate whether or not it is okay to do so. Read
+# the HTML documentation on the embedded Perl interpreter for more
+# information on how this option works.
+
+use_embedded_perl_implicitly=1
+
+
+
+# ILLEGAL OBJECT NAME CHARACTERS
+# This option allows you to specify illegal characters that cannot
+# be used in host names, service descriptions, or names of other
+# object types.
+
+illegal_object_name_chars=`~!$%^&*|'"<>?,()=
+
+
+
+# ILLEGAL MACRO OUTPUT CHARACTERS
+# This option allows you to specify illegal characters that are
+# stripped from macros before being used in notifications, event
+# handlers, etc. This DOES NOT affect macros used in service or
+# host check commands.
+# The following macros are stripped of the characters you specify:
+# $HOSTOUTPUT$
+# $HOSTPERFDATA$
+# $HOSTACKAUTHOR$
+# $HOSTACKCOMMENT$
+# $SERVICEOUTPUT$
+# $SERVICEPERFDATA$
+# $SERVICEACKAUTHOR$
+# $SERVICEACKCOMMENT$
+
+illegal_macro_output_chars=`~$&|'"<>
+
+
+
+# REGULAR EXPRESSION MATCHING
+# This option controls whether or not regular expression matching
+# takes place in the object config files. Regular expression
+# matching is used to match host, hostgroup, service, and service
+# group names/descriptions in some fields of various object types.
+# Values: 1 = enable regexp matching, 0 = disable regexp matching
+
+use_regexp_matching=0
+
+
+
+# "TRUE" REGULAR EXPRESSION MATCHING
+# This option controls whether or not "true" regular expression
+# matching takes place in the object config files. This option
+# only has an effect if regular expression matching is enabled
+# (see above). If this option is DISABLED, regular expression
+# matching only occurs if a string contains wildcard characters
+# (* and ?). If the option is ENABLED, regexp matching occurs
+# all the time (which can be annoying).
+# Values: 1 = enable true matching, 0 = disable true matching
+
+use_true_regexp_matching=0
+
+
+
+# ADMINISTRATOR EMAIL/PAGER ADDRESSES
+# The email and pager address of a global administrator (likely you).
+# Nagios never uses these values itself, but you can access them by
+# using the $ADMINEMAIL$ and $ADMINPAGER$ macros in your notification
+# commands.
+
+admin_email=root@localhost
+admin_pager=pageroot@localhost
+
+
+
+# DAEMON CORE DUMP OPTION
+# This option determines whether or not Nagios is allowed to create
+# a core dump when it runs as a daemon. Note that it is generally
+# considered bad form to allow this, but it may be useful for
+# debugging purposes. Enabling this option doesn't guarantee that
+# a core file will be produced, but that's just life...
+# Values: 1 - Allow core dumps
+# 0 - Do not allow core dumps (default)
+
+daemon_dumps_core=0
+
+
+
+# LARGE INSTALLATION TWEAKS OPTION
+# This option determines whether or not Nagios will take some shortcuts
+# which can save on memory and CPU usage in large Nagios installations.
+# Read the documentation for more information on the benefits/tradeoffs
+# of enabling this option.
+# Values: 1 - Enabled tweaks
+# 0 - Disable tweaks (default)
+
+use_large_installation_tweaks=0
+
+
+
+# ENABLE ENVIRONMENT MACROS
+# This option determines whether or not Nagios will make all standard
+# macros available as environment variables when host/service checks
+# and system commands (event handlers, notifications, etc.) are
+# executed. Enabling this option can cause performance issues in
+# large installations, as it will consume a bit more memory and (more
+# importantly) consume more CPU.
+# Values: 1 - Enable environment variable macros (default)
+# 0 - Disable environment variable macros
+
+enable_environment_macros=1
+
+
+
+# CHILD PROCESS MEMORY OPTION
+# This option determines whether or not Nagios will free memory in
+# child processes (processed used to execute system commands and host/
+# service checks). If you specify a value here, it will override
+# program defaults.
+# Value: 1 - Free memory in child processes
+# 0 - Do not free memory in child processes
+
+#free_child_process_memory=1
+
+
+
+# CHILD PROCESS FORKING BEHAVIOR
+# This option determines how Nagios will fork child processes
+# (used to execute system commands and host/service checks). Normally
+# child processes are fork()ed twice, which provides a very high level
+# of isolation from problems. Fork()ing once is probably enough and will
+# save a great deal on CPU usage (in large installs), so you might
+# want to consider using this. If you specify a value here, it will
+# program defaults.
+# Value: 1 - Child processes fork() twice
+# 0 - Child processes fork() just once
+
+#child_processes_fork_twice=1
+
+
+
+# DEBUG LEVEL
+# This option determines how much (if any) debugging information will
+# be written to the debug file. OR values together to log multiple
+# types of information.
+# Values:
+# -1 = Everything
+# 0 = Nothing
+# 1 = Functions
+# 2 = Configuration
+# 4 = Process information
+# 8 = Scheduled events
+# 16 = Host/service checks
+# 32 = Notifications
+# 64 = Event broker
+# 128 = External commands
+# 256 = Commands
+# 512 = Scheduled downtime
+# 1024 = Comments
+# 2048 = Macros
+
+debug_level=0
+
+
+
+# DEBUG VERBOSITY
+# This option determines how verbose the debug log out will be.
+# Values: 0 = Brief output
+# 1 = More detailed
+# 2 = Very detailed
+
+debug_verbosity=1
+
+
+
+# DEBUG FILE
+# This option determines where Nagios should write debugging information.
+
+debug_file=/var/log/nagios3/nagios.debug
+
+
+
+# MAX DEBUG FILE SIZE
+# This option determines the maximum size (in bytes) of the debug file. If
+# the file grows larger than this size, it will be renamed with a .old
+# extension. If a file already exists with a .old extension it will
+# automatically be deleted. This helps ensure your disk space usage doesn't
+# get out of control when debugging Nagios.
+
+max_debug_file_size=1000000
+
+
View
225 nagios/files/nrpe/nrpe.cfg
@@ -0,0 +1,225 @@
+#############################################################################
+# Sample NRPE Config File
+# Written by: Ethan Galstad (nagios@nagios.org)
+#
+#
+# NOTES:
+# This is a sample configuration file for the NRPE daemon. It needs to be
+# located on the remote host that is running the NRPE daemon, not the host
+# from which the check_nrpe client is being executed.
+#############################################################################
+
+
+# LOG FACILITY
+# The syslog facility that should be used for logging purposes.
+
+log_facility=daemon
+
+
+
+# PID FILE
+# The name of the file in which the NRPE daemon should write it's process ID
+# number. The file is only written if the NRPE daemon is started by the root
+# user and is running in standalone mode.
+
+pid_file=/var/run/nagios/nrpe.pid
+
+
+
+# PORT NUMBER
+# Port number we should wait for connections on.
+# NOTE: This must be a non-priviledged port (i.e. > 1024).
+# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
+
+server_port=5666
+
+
+
+# SERVER ADDRESS
+# Address that nrpe should bind to in case there are more than one interface
+# and you do not want nrpe to bind on all interfaces.
+# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
+
+#server_address=127.0.0.1
+
+
+
+# NRPE USER
+# This determines the effective user that the NRPE daemon should run as.
+# You can either supply a username or a UID.
+#
+# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
+
+nrpe_user=nagios
+
+
+
+# NRPE GROUP
+# This determines the effective group that the NRPE daemon should run as.
+# You can either supply a group name or a GID.
+#
+# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
+
+nrpe_group=nagios
+
+
+
+# ALLOWED HOST ADDRESSES
+# This is an optional comma-delimited list of IP address or hostnames
+# that are allowed to talk to the NRPE daemon.
+#
+# Note: The daemon only does rudimentary checking of the client's IP
+# address. I would highly recommend adding entries in your /etc/hosts.allow
+# file to allow only the specified host to connect to the port
+# you are running this daemon on.
+#
+# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
+
+#allowed_hosts=
+
+
+
+# COMMAND ARGUMENT PROCESSING
+# This option determines whether or not the NRPE daemon will allow clients
+# to specify arguments to commands that are executed. This option only works
+# if the daemon was configured with the --enable-command-args configure script
+# option.
+#
+# *** ENABLING THIS OPTION IS A SECURITY RISK! ***
+# Read the SECURITY file for information on some of the security implications
+# of enabling this variable.
+#
+# Values: 0=do not allow arguments, 1=allow command arguments
+
+dont_blame_nrpe=0
+
+
+
+# COMMAND PREFIX
+# This option allows you to prefix all commands with a user-defined string.
+# A space is automatically added between the specified prefix string and the
+# command line from the command definition.
+#
+# *** THIS EXAMPLE MAY POSE A POTENTIAL SECURITY RISK, SO USE WITH CAUTION! ***
+# Usage scenario:
+# Execute restricted commmands using sudo. For this to work, you need to add
+# the nagios user to your /etc/sudoers. An example entry for alllowing
+# execution of the plugins from might be:
+#
+# nagios ALL=(ALL) NOPASSWD: /usr/lib/nagios/plugins/
+#
+# This lets the nagios user run all commands in that directory (and only them)
+# without asking for a password. If you do this, make sure you don't give
+# random users write access to that directory or its contents!
+
+# command_prefix=/usr/bin/sudo
+
+
+
+# DEBUGGING OPTION
+# This option determines whether or not debugging messages are logged to the
+# syslog facility.
+# Values: 0=debugging off, 1=debugging on
+
+debug=0
+
+
+
+# COMMAND TIMEOUT
+# This specifies the maximum number of seconds that the NRPE daemon will
+# allow plugins to finish executing before killing them off.
+
+command_timeout=60
+
+
+
+# CONNECTION TIMEOUT
+# This specifies the maximum number of seconds that the NRPE daemon will
+# wait for a connection to be established before exiting. This is sometimes
+# seen where a network problem stops the SSL being established even though
+# all network sessions are connected. This causes the nrpe daemons to
+# accumulate, eating system resources. Do not set this too low.
+
+connection_timeout=300
+
+
+
+# WEEK RANDOM SEED OPTION
+# This directive allows you to use SSL even if your system does not have
+# a /dev/random or /dev/urandom (on purpose or because the necessary patches
+# were not applied). The random number generator will be seeded from a file
+# which is either a file pointed to by the environment valiable $RANDFILE
+# or $HOME/.rnd. If neither exists, the pseudo random number generator will
+# be initialized and a warning will be issued.
+# Values: 0=only seed from /dev/[u]random, 1=also seed from weak randomness
+
+#allow_weak_random_seed=1
+
+
+
+# INCLUDE CONFIG FILE
+# This directive allows you to include definitions from an external config file.
+
+#include=<somefile.cfg>
+
+
+
+# INCLUDE CONFIG DIRECTORY
+# This directive allows you to include definitions from config files (with a
+# .cfg extension) in one or more directories (with recursion).
+
+#include_dir=<somedirectory>
+#include_dir=<someotherdirectory>
+
+
+
+# COMMAND DEFINITIONS
+# Command definitions that this daemon will run. Definitions
+# are in the following format:
+#
+# command[<command_name>]=<command_line>
+#
+# When the daemon receives a request to return the results of <command_name>
+# it will execute the command specified by the <command_line> argument.
+#
+# Unlike Nagios, the command line cannot contain macros - it must be
+# typed exactly as it should be executed.
+#
+# Note: Any plugins that are used in the command lines must reside
+# on the machine that this daemon is running on! The examples below
+# assume that you have plugins installed in a /usr/local/nagios/libexec
+# directory. Also note that you will have to modify the definitions below
+# to match the argument format the plugins expect. Remember, these are
+# examples only!
+
+
+# The following examples use hardcoded command arguments...
+
+command[check_users]=/usr/lib/nagios/plugins/check_users -w 5 -c 10
+command[check_load]=/usr/lib/nagios/plugins/check_load -w 15,10,5 -c 30,25,20
+command[check_hda1]=/usr/lib/nagios/plugins/check_disk -w 20% -c 10% -p /dev/hda1
+command[check_zombie_procs]=/usr/lib/nagios/plugins/check_procs -w 5 -c 10 -s Z
+command[check_total_procs]=/usr/lib/nagios/plugins/check_procs -w 150 -c 200
+
+
+# The following examples allow user-supplied arguments and can
+# only be used if the NRPE daemon was compiled with support for
+# command arguments *AND* the dont_blame_nrpe directive in this
+# config file is set to '1'. This poses a potential security risk, so
+# make sure you read the SECURITY file before doing this.
+
+#command[check_users]=/usr/lib/nagios/plugins/check_users -w $ARG1$ -c $ARG2$
+#command[check_load]=/usr/lib/nagios/plugins/check_load -w $ARG1$ -c $ARG2$
+#command[check_disk]=/usr/lib/nagios/plugins/check_disk -w $ARG1$ -c $ARG2$ -p $ARG3$
+#command[check_procs]=/usr/lib/nagios/plugins/check_procs -w $ARG1$ -c $ARG2$ -s $ARG3$
+
+#
+# local configuration:
+# if you'd prefer, you can instead place directives here
+include=/etc/nagios/nrpe_local.cfg
+
+#
+# you can place your config snipplets into nrpe.d/
+include_dir=/etc/nagios/nrpe.d/
+
+
View
21 nagios/files/pagerduty/pagerduty.cfg
@@ -0,0 +1,21 @@
+define contact {
+ contact_name pagerduty
+ alias PagerDuty Pseudo-Contact
+ service_notification_period 24x7
+ host_notification_period 24x7
+ service_notification_options w,u,c,r
+ host_notification_options d,r
+ service_notification_commands notify-service-by-pagerduty
+ host_notification_commands notify-host-by-pagerduty
+ pager XXXXXAPIKEYGOESHEREXXXXXXXXXXXXX
+}
+
+define command {
+ command_name notify-service-by-pagerduty
+ command_line /usr/local/bin/pagerduty_nagios.pl enqueue -f pd_nagios_object=service
+}
+
+define command {
+ command_name notify-host-by-pagerduty
+ command_line /usr/local/bin/pagerduty_nagios.pl enqueue -f pd_nagios_object=host
+}
View
251 nagios/files/pagerduty/pagerduty_nagios.pl
@@ -0,0 +1,251 @@
+#!/usr/bin/env perl
+
+use Pod::Usage;
+use Getopt::Long;
+use Sys::Syslog;
+use HTTP::Request::Common qw(POST);
+use HTTP::Status qw(is_client_error);
+use LWP::UserAgent;
+use File::Path;
+use Fcntl qw(:flock);
+
+
+=head1 NAME
+
+pagerduty_nagios -- Send Nagios events to the PagerDuty alert system
+
+=head1 SYNOPSIS
+
+pagerduty_nagios enqueue [options]
+
+pagerduty_nagios flush [options]
+
+=head1 DESCRIPTION
+
+ This script passes events from Nagios to the PagerDuty alert system. It's
+ meant to be run as a Nagios notification plugin. For more details, please see
+ the PagerDuty Nagios integration docs at:
+ http://www.pagerduty.com/docs/nagios-integration.
+
+ When called in the "enqueue" mode, the script loads a Nagios notification out
+ of the environment and into the event queue. It then tries to flush the
+ queue by sending any enqueued events to the PagerDuty server. The script is
+ typically invoked in this mode from a Nagios notification handler.
+
+ When called in the "flush" mode, the script simply tries to send any enqueued
+ events to the PagerDuty server. This mode is typically invoked by cron. The
+ purpose of this mode is to retry any events that couldn't be sent to the
+ PagerDuty server for whatever reason when they were initially enqueued.
+
+=head1 OPTIONS
+
+ --api-base URL
+ The base URL used to communicate with PagerDuty. The default option here
+ should be fine, but adjusting it may make sense if your firewall doesn't
+ pass HTTPS traffic for some reason. See the PagerDuty Nagios integration
+ docs for details.
+
+ --field KEY=VALUE
+ Add this key-value pair to the event being passed to PagerDuty. The script
+ automatically gathers Nagios macros out of the environment, so there's no
+ need to specify these explicitly. This option can be repeated as many
+ times as necessary to pass multiple key-value pairs. This option is only
+ useful when an event is being enqueued.0
+
+ --help
+ Display documentation for the script.
+
+ --queue-dir DIR
+ Path to the directory to use to store the event queue. By default, we use
+ /tmp/pagerduty_nagios.
+
+ --verbose
+ Turn on extra debugging information. Useful for debugging.
+
+=cut
+
+# This release tested on:
+# Debian Sarge (Perl 5.8.4)
+# Ubuntu 9.04 (Perl 5.10.0)
+
+my $opt_api_base = "http://events.pagerduty.com/nagios/2010-04-15";
+my %opt_fields;
+my $opt_help;
+my $opt_queue_dir = "/tmp/pagerduty_nagios";
+my $opt_verbose;
+
+
+sub get_queue_from_dir {
+ my $dh;
+
+ unless (opendir($dh, $opt_queue_dir)) {
+ syslog(LOG_ERR, "opendir %s failed: %s", $opt_queue_dir, $!);
+ die $!;
+ }
+
+ my @files;
+ while (my $f = readdir($dh)) {
+ next unless $f =~ /^pd_(\d+)_\d+\.txt$/;
+ push @files, [int($1), $f];
+ }
+
+ closedir($dh);
+
+ @files = sort { @{$a}[0] <=> @{$b}[0] } @files;
+ return map { @{$_}[1] } @files;
+}
+
+
+sub flush_queue {
+ my @files = get_queue_from_dir();
+ my $ua = LWP::UserAgent->new;
+
+ # It's not a big deal if we don't get the message through the first time.
+ # It will get sent the next time cron fires.
+ $ua->timeout(15);
+
+ foreach (@files) {
+ my $filename = "$opt_queue_dir/$_";
+ my $fd;
+ my %event;
+
+ print STDERR "==== Now processing: $filename\n" if $opt_verbose;
+
+ unless (open($fd, "<", $filename)) {
+ syslog(LOG_ERR, "open %s for read failed: %s", $filename, $!);
+ die $!;
+ }
+
+ while (<$fd>) {
+ chomp;
+ my @fields = split("=", $_, 2);
+ $event{$fields[0]} = $fields[1];
+ }
+
+ close($fd);
+
+ my $req = POST("$opt_api_base/create_event", \%event);
+
+ if ($opt_verbose) {
+ my $s = $req->as_string;
+ print STDERR "Request:\n$s\n";
+ }
+
+ my $resp = $ua->request($req);
+
+ if ($opt_verbose) {
+ my $s = $resp->as_string;
+ print STDERR "Response:\n$s\n";
+ }
+
+ if ($resp->is_success) {
+ syslog(LOG_INFO, "Nagios event in file %s ACCEPTED by the PagerDuty server.", $filename);
+ unlink($filename);
+ }
+ elsif (is_client_error($resp->code)) {
+ syslog(LOG_WARNING, "Nagios event in file %s REJECTED by the PagerDuty server. Server says: %s", $filename, $resp->content);
+ unlink($filename);
+ }
+ else {
+ # Something else went wrong.
+ syslog(LOG_WARNING, "Nagios event in file %s DEFERRED due to network/server problems.", $filename);
+ return 0;
+ }
+ }
+
+ # Everything that needed to be sent was sent.
+ return 1;
+}
+
+
+sub lock_and_flush_queue {
+ # Serialize access to the queue directory while we flush.
+ # (We don't want more than one flush at once.)
+
+ my $lock_filename = "$opt_queue_dir/lockfile";
+ my $lock_fd;
+
+ unless (open($lock_fd, ">", $lock_filename)) {
+ syslog(LOG_ERR, "open %s for write failed: %s", $lock_filename, $!);
+ die $!;
+ }
+
+ unless (flock($lock_fd, LOCK_EX)) {
+ syslog(LOG_ERR, "flock %s failed: %s", $lock_filename, $!);
+ die $!;
+ }
+
+ my $ret = flush_queue();
+
+ close($lock_fd);
+
+ return $ret;
+}
+
+
+sub enqueue_event {
+ my %event;
+
+ # Scoop all the Nagios related stuff out of the environment.
+ while ((my $k, my $v) = each %ENV) {
+ next unless $k =~ /^NAGIOS_(.*)$/;
+ $event{$1} = $v;
+ }
+
+ # Apply any other variables that were passed in.
+ %event = (%event, %opt_fields);
+
+ $event{"pd_version"} = "1.0";
+
+ # Right off the bat, enqueue the event. Nothing tiem consuming should come
+ # before here (i.e. no locks or remote connections), because we want to
+ # make sure we get the event written out within the Nagios notification
+ # timeout. If we get killed off after that, it isn't a big deal.
+
+ my $filename = sprintf("$opt_queue_dir/pd_%u_%u.txt", time(), $$);
+ my $fd;
+
+ unless (open($fd, ">", $filename)) {
+ syslog(LOG_ERR, "open %s for write failed: %s", $filename, $!);
+ die $!;
+ }
+
+ while ((my $k, my $v) = each %event) {
+ # "=" can't occur in the keyname, and "\n" can't occur anywhere.
+ # (Nagios follows this already, so I think we're safe)
+ print $fd "$k=$v\n";
+ }
+
+ close($fd);
+}
+
+###########
+
+GetOptions("api-base=s" => \$opt_api_base,
+ "field=s%" => \%opt_fields,
+ "help" => \$opt_help,
+ "queue-dir=s" => \$opt_queue_dir,
+ "verbose" => \$opt_verbose
+ ) || pod2usage(2);
+
+pod2usage(2) if @ARGV < 1 ||
+ (($ARGV[0] ne "enqueue") && ($ARGV[0] ne "flush"));
+
+pod2usage(-verbose => 3) if $opt_help;
+
+my @log_mode = ("nofatal", "pid");
+push(@log_mode, "perror") if $opt_verbose;
+
+openlog("pagerduty_nagios", join(",", @log_mode), LOG_LOCAL0);
+
+# This function automatically terminates the program on things like permission
+# errors.
+mkpath($opt_queue_dir);
+
+if ($ARGV[0] eq "enqueue") {
+ enqueue_event();
+ lock_and_flush_queue();
+}
+elsif ($ARGV[0] eq "flush") {
+ lock_and_flush_queue();
+}
View
26 nagios/files/services-base.cfg
@@ -0,0 +1,26 @@
+define service {
+ name base-service
+ register 0
+
+ active_checks_enabled 1
+ check_freshness 0
+ check_period 24x7
+ contacts default
+ event_handler_enabled 1
+ failure_prediction_enabled 1
+ flap_detection_enabled 1
+ is_volatile 0
+ max_check_attempts 3
+ normal_check_interval 4
+ notification_interval 60
+ notification_options w,u,c
+ notification_period 24x7
+ notifications_enabled 1
+ obsess_over_service 1
+ parallelize_check 1
+ passive_checks_enabled 1
+ process_perf_data 1
+ retain_nonstatus_information 1
+ retain_status_information 1
+ retry_check_interval 2
+}
View
27 nagios/files/timeperiods.cfg
@@ -0,0 +1,27 @@
+define timeperiod {
+ timeperiod_name 24x7
+ alias 24x7
+ sunday 00:00-24:00
+ monday 00:00-24:00
+ tuesday 00:00-24:00
+ wednesday 00:00-24:00
+ thursday 00:00-24:00
+ friday 00:00-24:00
+ saturday 00:00-24:00
+}
+
+define timeperiod {
+ timeperiod_name daylight
+ alias daylight
+ # Times are in UTC (aka, time zone on the systems)
+ # 09:00-1800 Pacific
+ sunday 17:00-02:00
+ monday 17:00-02:00
+ tuesday 17:00-02:00
+ wednesday 17:00-02:00
+ thursday 17:00-02:00
+ friday 17:00-02:00
+ saturday 17:00-02:00
+}
+
+
View
53 nagios/manifests/check.pp
@@ -0,0 +1,53 @@
+# This vim modeline is needed because otherwise vim thinks this file is a bindzone.
+# vim:set ft=puppet:
+
+define nagios::check($command=undef, $host, $remote=false, $contacts="default",
+ $passive=false, $volatile=false, $max_failures=3) {
+ $safe_name = inline_template("<%= name.gsub(/[ '\"]/, ' ') %>")
+ $file = "/etc/nagios3/checks.d/check-$host-$safe_name.cfg"
+
+ if $command == undef and $passive == false {
+ fail("A command is required if passive false.")
+ }
+
+ if $remote {
+ include ::nagios::plugin::nrpe
+ $check_command = "remotecheck!$command"
+
+ Nagios_service <| title == $name |> {
+ require +> Class["nagios::plugin::nrpe"]
+ }
+ $notes = "NRPE: check_nrpe -H $fqdn -t 600 -c $command"
+ } elsif $passive {
+ $check_command = "noop"
+ $notes = "Passive check. No command."
+ } else {
+ $check_command = $command
+ $notes = "Command: $command"
+ }
+
+ nagios_service {
+ "$name":
+ target => "$file",
+ check_command => $check_command,
+ host_name => "$host",
+ require => File["/etc/nagios3/checks.d"],
+ notes => $notes,
+ contacts => $contacts,
+ service_description => "$name",
+ notification_period => extlookup("nagios/notificationperiod", "24x7"),
+ active_checks_enabled => $passive ? { true => 0, false => 1 },
+ passive_checks_enabled => $passive ? { true => 1, false => 0 },
+ is_volatile => $volatile ? { true => 1, false => 0 },
+ max_check_attempts => $max_failures,
+ use => "base-service";
+ }
+
+ file {
+ "$file":
+ ensure => file,
+ require => Nagios_service[$name],
+ owner => nagios,
+ mode => 644;
+ }
+}
View
45 nagios/manifests/check/log.pp
@@ -0,0 +1,45 @@
+define nagios::check::log($files, $patterns, $user="logwatcher",
+ $contacts=undef, $ensure="present") {
+ include ::nagios::nsca
+ include ::nagios::user::logwatcher
+ include ::grok::package
+ include ::ruby::gem::eventmachine-tail
+
+ $host = $fqdn
+ $monitor_host = "monitor"
+ $check_name = "$name on $fqdn"
+
+ $safename = regsubst($name, " ", "-", "G")
+ $grok_config = "/etc/grok.d/${safename}.grok"
+ $procname = "monitor-$safename"
+
+ file {
+ # TODO(sissel): Safe to remove after 2011/01/01
+ "/etc/grok.d/${name}.grok":
+ ensure => absent;
+ $grok_config:
+ ensure => $ensure ? { "present" => "file", "absent" => "absent" },
+ notify => Supervisor::Program[$procname],
+ content => template("nagios/check/log.grok.erb");
+ }
+
+ if ($ensure == "present") {
+ @@nagios::check {
+ $check_name:
+ passive => true,
+ volatile => true,
+ contacts => $contacts,
+ max_failures => 1,
+ host => $fqdn,
+ tag => "deployment::$deployment";
+ }
+ }
+
+ supervisor::program {
+ $procname:
+ ensure => $ensure,
+ command => "grok -f '$grok_config'",
+ user => $user,
+ require => [File[$grok_config], Class["grok::package", "nagios::nsca"]];
+ }
+}
View
38 nagios/manifests/command.pp
@@ -0,0 +1,38 @@
+define nagios::command($command, $remote, $ensure="present") {
+ if ($ensure == "present") {
+ $file_ensure = "file"
+ } else {
+ $file_ensure = "absent"
+ }
+
+
+ if $remote {
+ # Use NRPE
+ include ::nagios::nrpe::package
+ include ::nagios::nrpe::server
+
+ file {
+ "/etc/nagios/nrpe.d/$name.cfg":
+ ensure => $file_ensure,
+ require => Class["nagios::nrpe::package"],
+ notify => Class["nagios::nrpe::server"],
+ content => "command[$name]=$command\n";
+ }
+ } else {
+ # Not remote, we're a nagios server so add a specific command.
+
+ $command_template = "
+ # Generated by puppet from Nagios::Command[$name]
+ define command {
+ command_name <%= name %>
+ command_line <%= command %>
+ }
+ "
+
+ nagios::config {
+ "command-$name":
+ ensure => $ensure,
+ content => inline_template($command_template);
+ }
+ }
+}
View
22 nagios/manifests/config.pp
@@ -0,0 +1,22 @@
+define nagios::config($source = undef, $content = undef, $ensure = "present") {
+ include ::nagios::server
+ include ::nagios::package
+
+ if ($ensure != "absent") {
+ if ($content == undef and $source == undef) {
+ error("You must specify only one of 'content' or 'source' for $class[$name]")
+ }
+ if ($content != undef and $source != undef) {
+ error("You must specify only one of 'content' or 'source' for $class[$name]")
+ }
+ }
+
+ file {
+ "/etc/nagios3/conf.d/$name.cfg":
+ ensure => $ensure ? { "present" => file, default => absent },
+ source => $source,
+ content => $content,
+ require => Class["nagios::package"],
+ notify => Class["nagios::server"];
+ }
+}
View
19 nagios/manifests/host.pp
@@ -0,0 +1,19 @@
+define nagios::host($address) {
+ $file = "/etc/nagios3/hosts.d/$name.cfg"
+ nagios_host {
+ "$name":
+ target => $file,
+ use => "base-host",
+ require => File["/etc/nagios3/hosts.d"],
+ address => "$address",
+ alias => "$name ($address)",
+ }
+
+ file {
+ $file:
+ ensure => file,
+ require => Nagios_host[$name],
+ owner => nagios,
+ mode => 644;
+ }
+}
View
56 nagios/manifests/init.pp