Merge pull request #59 from dpavlos/nagios

ARGO-354 Added ncg and nagios configs.

roles/monitoring_engine/defaults/main.yml

@@ -18,4 +18,8 @@ check_hosts: "0"
 tenant: TENANT_A
 poem_root_url: http://localhost/poem
 include_proxy_checks: "0"
-include_msg_checks_recv: "0"
\ No newline at end of file
+include_msg_checks_recv: "0"
+ocsp_command: handle_service_check
+obsess_over_services: "1"
+enable_environment_macros: "1"
+backup_instance: "false"

roles/monitoring_engine/tasks/main.yml

 ---
 
 - name: Install Nagios
-  yum: name=nagios-4.0.8-1.el6.srce.x86_64.rpm state=present enablerepo=nagios
+  yum: name=nagios state=latest enablerepo=nagios
   
 - name: Install NCG and MSG conponents
   yum: name={{ item.name }} state=latest enablerepo={{ item.repo }}
-  with_items: nagios_components
\ No newline at end of file
+  with_items: nagios_components
+
+- name: Copy nagios.cfg file
+  template: src=nagios.cfg.j2
+            dest=/etc/nagios/nagios.cfg
+            owner=nagios group=nagios mode=0644
+
+- name: Copy ncg.conf file
+  template: src=ncg.conf.j2
+            dest=/etc/ncg/ncg.conf
+            owner=root group=root
+
+- name: Copy broker-list file
+  template: src=broker-list.j2
+            dest=/var/cache/msg/broker-cache-file/broker-list
+            owner=root group=root mode=0644
+
+- name: Enable nagios on boot and start service
+  service: name=nagios state=started enabled=yes
+

roles/monitoring_engine/templates/broker-list.j2

+{% if broker_host is defined %}
+stomp://{{ broker_host }}:6163
+{% endif %}
\ No newline at end of file

roles/monitoring_engine/templates/nagios.cfg.j2

+##############################################################################
+#
+# NAGIOS.CFG - Sample Main Config File for Nagios 4.0.8
+#
+# Read the documentation for more information on this configuration
+# file.  I've provided some comments here, but things may not be so
+# clear without further explanation.
+#
+#
+##############################################################################
+
+
+# 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/nagios/nagios.log
+
+
+
+# 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/nagios/objects/commands.cfg
+#cfg_file=/etc/nagios/objects/contacts.cfg
+#cfg_file=/etc/nagios/objects/timeperiods.cfg
+#cfg_file=/etc/nagios/objects/templates.cfg
+
+# Definitions for monitoring the local (Linux) host
+#cfg_file=/etc/nagios/objects/localhost.cfg
+
+# Definitions for monitoring a Windows machine
+#cfg_file=/etc/nagios/objects/windows.cfg
+
+# Definitions for monitoring a router/switch
+#cfg_file=/etc/nagios/objects/switch.cfg
+
+# Definitions for monitoring a network printer
+#cfg_file=/etc/nagios/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/nagios/conf.d
+cfg_dir=/etc/nagios/wlcg.d
+#cfg_dir=/etc/nagios/printers
+#cfg_dir=/etc/nagios/switches
+#cfg_dir=/etc/nagios/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/nagios/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/nagios/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/nagios/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/nagios/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 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.
+
+command_file=/var/nagios/rw/nagios.cmd
+
+
+
+# QUERY HANDLER INTERFACE
+# This is the socket that is created for the Query Handler interface
+
+#query_socket=/var/nagios/rw/nagios.qh
+
+
+
+# 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/nagios/nagios.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/nagios/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/nagios/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
+
+
+
+# CURRENT STATES LOGGING OPTION
+# If you don't want Nagios to log all current host and service states
+# after log has been rotated to the main log file, you can disable this
+# option by setting this value to 0. Default value is 1.
+
+log_current_states=1
+
+
+
+# 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=somecommand
+#global_service_event_handler=somecommand
+
+
+
+# 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/nagios/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
+
+
+
+# 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=60
+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 retain_state_information