#===============================================================================
# BROKER
#===============================================================================
# Description: The Broker is responsible for:
# - Exporting centralized logs of all Shinken daemon processes
# - Exporting status data
# - Exporting performance data
# - Exposing Shinken APIs:
# - Status data
# - Performance data
# - Command interface
#===============================================================================
define broker {
## BROKER
#============================ Daemon name and address ====================
# Daemon name. Must be unique
broker_name broker-master
# IP/fqdn of this daemon (note: you MUST change it by the real ip/fqdn of this server)
address localhost
# Port (HTTP/HTTPS) exposed by this daemon
port 7772
# 0 = use HTTP, 1 = use HTTPS
use_ssl 0
#===============================
# Description: The broker is responsible for:
# - Exporting centralized logs of all Shinken daemon processes
# - Exporting status data
# - Exporting performance data
# - Exposing Shinken APIs:
# - Status data
# - Performance data
# - Command interface
#====================================== Master or spare selection =========
# 1 = is a spare, 0 = is not a spare
spare 0
# spare_daemon: name of the daemon that will take this daemon job if it dies
# IMPORTANT:
# * a spare_daemon can only be the spare of 1 (and only one) master daemon
# * a spare_daemon cannot have a spare_daemon===============================
define broker {
# Shinken Enterprise. Lines added by import core. Do not remove it, it's used by Shinken Enterprise to update your objects if you re-import them.
_SE_UUID core-broker-060340145ade11e5b703080027f08538
_SE_UUID_HASH 8e00136f9e61061e07ca0f4a63509b68
# End of Shinken Enterprise part
#======== Daemon name and address =========
# Daemon name. *Must thebe spareunique
must have modules withbroker_name the same module_type as the master
# broker-master
depending of the# valueIP/fqdn of this daemon (note: you MUST change it by the broker__manage_spare__spare_must_have_the_same_list_of_module_type parameter real ip/fqdn of this server)
#address Example: spare_daemon broker-spare
spare_daemonlocalhost
# 1Port = (defaultHTTP/HTTPS) theexposed spareby definedthis with spare_daemon
must have the sameport module_type as this master
# 0 = the spare module_type are not checked
# broker__manage_spare__spare_must_have_the_same_list_of_module_type 7772
1
# 0 = #======== Daemon connection timeout and down state limit =========use HTTP, 1 = use HTTPS
# timeout: how many seconds to consider a node don't answer
use_ssl timeout 0
#======== Master or spare 3
selection =========
# data_timeout: how many second to consider a configuration transfer to be failed1 = is a spare, 0 = is not a spare
#spare because the network bandwidth is too small.
data_timeout 1200
# maxspare_check_attemptsdaemon: howname manyof failthe checkdaemon tothat will considertake this daemon job asif it DEADdies
max_check_attempts# IMPORTANT:
# * 3
# Check this daemon every X seconds
check_interval 60
#======== Modules to enable for this daemon =========
# Available:a spare_daemon can only be the spare of 1 (and only one) master daemon
# * a spare_daemon cannot have a spare_daemon
# * the spare must have modules with the same module_type as the master
# - WebUI - depending of the value of the broker__manage_spare__spare_must_have_the_same_list_of_module_type parameter
# Example: Visualisationspare_daemon interface
# - Graphite-Perfdata broker-spare
spare_daemon
: Save# all1 metrics= into(default) athe graphitespare database
defined with spare_daemon must #have -the slasame module_type as this master
# 0 = the spare module_type are not checked
# broker__manage_spare__spare_must_have_the_same_list_of_module_type : Save sla into a database1
# - Livestatus ======== Daemon connection timeout and down state limit =========
# timeout: how many seconds to consider a node : TCP API to query element state, used by nagios external tools like NagVis or Thruk
don't answer
timeout # - broker-module-livedata 3
# data_timeout: :how RESTmany APIsecond to queryconsider a allconfiguration monitoredtransfer elementto data (host, cluster or check)be failed
# - event-manager-writer because the network bandwidth is too small.
data_timeout : Save events for events manager (do not forget to activate the module in your webui to see data) 120
# - Simple-log max_check_attempts: how many fail check to consider this daemon as DEAD
max_check_attempts : Save all logs into a common file, Use this module only if you need to have all the check results in one file.3
# Check this daemon every X seconds
check_interval 60
# - broker--module-report-builder : External module used by webui--module-report-handler to generate reports======== Modules to enable for this daemon =========
# Available:
modules# - WebUI WebUI, Graphite-Perfdata, sla, event-manager-writer
: Visualisation interface
#======== Realm and architecture settings =========
# Realm to set this daemon into
realm - Graphite-Perfdata : Save all metrics into a graphite database
# - sla All
: Save sla #into 1a =database
take data from the# daemon- realmLivestatus and its sub realms
# 0 = take data only from: theTCP daemonAPI realm
to query manage_sub_realms 1
element state, used by nagios external tools like NagVis or Thruk
# In NATted environments, you declare each satellite ip[:port] as seen by
# *this* Broker (if port not set, the port declared by satellite itself
# is used)
#satellitemap scheduler-1=1.2.3.4:7768, poller-1=1.2.3.5:7771
- broker-module-livedata : REST API to query all monitored element data (host, cluster or check)
# - event-manager-writer : Save events for events manager (do not forget to activate the module in your webui to see data)
# Exchange- Simple-log between Brokers <- Schedulers can be limited by packet size (in kB)
: Save #all Note:logs asinto compressiona iscommon automaticfile, Use this ismodule aonly higherif limit,you andneed into realhave caseall the check results in one file.
#modules packets will be lower than this value
# broks_packet_size 1024
WebUI, Graphite-Perfdata, sla, event-manager-writer
#======== Realm and Memoryarchitecture protectionsettings =========
# Are theRealm to set this daemon moduleinto
process andrealm worker process are waiting for enough
# memory to be available before being launch. Default: 1 (enabled)All
broker__manage_brok__enable_sub_processes_memory_usage_protection 1
# The sub process memory usage protection can have a system reserved memory
# that won't be used by theses sub process when launched
# By default: 0 (no reserved memory)
# Example: 10 (means 10% of the total memory is reserved for the system)
broker__manage_brok__sub_process_memory_usage_system_reserved_memory 0# 1 = take data from the daemon realm and its sub realms
# 0 = take data only from the daemon realm
manage_sub_realms 1
# In NATted environments, you declare each satellite ip[:port] as seen by
# *this* daemon (if port not set, the port declared by satellite itself
# is used)
#satellitemap scheduler-1=1.2.3.4:7768, scheduler-2=1.2.3.5:7771
# IfExchange between abrokers sub<- processschedulers cannotcan be startedlimited becauseby of the protection, how many seconds
# it will be retry and wait that the system memory is freed until it fail to start
# By default: 5 (seconds)
broker__manage_brok__sub_processes_memory_usage_protection_max_retry_time 5packet size (in kB)
# Note: as compression is automatic, this is a higher limit, and in real case the
# packets will be lower than this value
# broks_packet_size 1024
#======== BrokMemory pusherprotection worker =========
# TheAre Brokerthe spawndaemon broksmodule pusher sub process toand pushworker toprocess externalare moduleswaiting (likefor WebUI)enough
# thememory Brokerto willbe lookavailable atbefore thisbeing worker execution time, and will kill if it timeoutlaunch. Default: 1 (enabled)
broker__manage_brok__enable_sub_processes_memory_usage_protection 1
# The Brokersub willprocess computememory theusage averageprotection executioncan timehave ofa previoussystem workersreserved tomemory
# decidethat aboutwon't howbe manyused timeby thistheses workersub willprocess take based on:when launched
# numberBy ofdefault: broks0 to(no send / past average send speed (broks/sreserved memory)
# IfExample: this10 time is(means reach,10% itof means that the pushertotal processmemory is killed
reserved for the system)
# For small amount of broks to send, it should lead to ridiculously small allowed execution time
# and the fac to spawn the sub process can be higher than this value, so we are using a minimal
# execution timeout broker__manage_brok__sub_process_memory_usage_system_reserved_memory 0
# If a sub process cannot be started because of the protection, how many seconds
# it will be retry and wait that the system memory is freed until it fail to start
# DefaultBy default: 5 (secondseconds)
broker__manage_brok__sub_processprocesses_memory_broksusage_pusherprotection_minmax_executionretry_timeouttime 5
#======== Brok pusher 5
worker =========
# InThe orderbroker tospawn managebroks thepusher factsub thatprocess theto serverpush canto slowexternal downmodules during this send, you can setup a(like WebUI)
# ratiothe thatbroker will belook at usedthis toworker increaseexecution thetime, allowedand timeoutwill bykill multiplyif it timeout
# Default: 5
broker__manage_brok__sub_process_broks_pusher_security_ratio The broker will compute the average execution time of previous workers to
# decide about how many time this worker will take based 5on:
# Atnumber theof Brokerbroks startto withoutsend stats,/ thispast validaverage willsend be used for the timeoutspeed (broks/s)
# If Default:this 240 (seconds)
broker__manage_brok__sub_process_broks_pusher_max_execution_timeout 240time is reach, it means that the pusher process is killed
# IfFor asmall subamount processof reachbroks ato timeoutsend, it willshould belead killedto andridiculously relaunched.small Afterallowed maxexecution retry,time
# and the attached module will be restartedfac to spawn the sub process can be higher than this value, so we are using a minimal
# execution timeout
# Default: 35 (second)
broker__manage_brok__sub_process_broks_pusher_maxmin_execution_retrytimeout 5
# In order to manage the fact that 3
the server can #======== Enable or not this daemon =========slow down during this send, you can setup a
# 1ratio =that iswill enabled,be 0used =to isincrease disabled
the allowed timeout by enabledmultiply it
# Default: 5
broker__manage_brok__sub_process_broks_pusher_security_ratio 1
}
5
# At the broker start without stats, this valid will be used for the timeout
# Default: 240 (seconds)
broker__manage_brok__sub_process_broks_pusher_max_execution_timeout 240
# If a sub process reach a timeout, it will be killed and relaunched. After max retry,
# the attached module will be restarted
# Default: 3
broker__manage_brok__sub_process_broks_pusher_max_retry 3
# broker__manage_brok__sub_process_broks_pusher_queue_batch_size:
# * defines the maximum number of broks the "queue brok pusher"
# process will handle per send to external module ( like WebUI ) .
# * Remaining broks will be handled in next send.
# * IMPORTANT: increase this value can lead to error on the socket
# Default: 100000 (broks/batch)
# broker__manage_brok__sub_process_broks_pusher_queue_batch_size 100000
# Broks whose serialization time exceeds this threshold will generate a warning
# Default: 100 (milliseconds)
# broker__manage_brok__oversized_data_warning_threshold__serialization_time 100
# Broks whose serialization time exceeds this threshold will generate an error
# Default: 500 (milliseconds)
# broker__manage_brok__oversized_data_error_threshold__serialization_time 500
#======== VMWare / ESXi ==========
# 1 (default) = if vmware get the ESXi CPU stats value, 0 = do not get value
vmware__statistics_compute_enable 1
#======== Enable or not this daemon =========
# 1 = is enabled, 0 = is disabled
enabled 1
}
|