#==================================== Daemon name and address ===========================================
# 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
#============================================================
# 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
#======== Master or spare selection =========
# 1 = is a spare, 0 =
define broker { is not a spare
spare 0
#======== Daemon name and address ========= spare_daemon: name of the daemon that will take this daemon job if it dies
# IMPORTANT:
# Daemon name. Must * a spare_daemon can only be unique
the spare of broker_name 1 (and only one) master daemon
# * a spare_daemon cannot have broker-master
a spare_daemon
# IP/fqdn of this* daemonthe (note:spare youmust MUSThave change itmodules bywith the real ip/fqdn of this server)
same module_type as the master
# address - depending of the value of the broker__manage_spare__spare_must_have_the_same_list_of_module_type parameter
# Example: spare_daemon localhost
# Port (HTTP/HTTPS) exposed by this daemon
broker-spare
port spare_daemon
# 1 = (default) the spare defined with spare_daemon must have the same module_type as this 7772
master
# 0 = usethe HTTP, 1 = use HTTPSspare module_type are not checked
use_ssl # broker__manage_spare__spare_must_have_the_same_list_of_module_type 01
#======== Master or spare selection Daemon connection timeout and down state limit =========
# 1timeout: =how ismany aseconds spare,to 0consider =a isnode not a sparedon't answer
sparetimeout 03
# sparedata_daemontimeout: name of the daemon that will take this daemon job if it dieshow many second to consider a configuration transfer to be failed
# because IMPORTANT:
the network bandwidth is #too small.
* a sparedata_daemontimeout can only be the spare of 1 (and only one) master daemon120
# * a spare_daemon cannot have a spare_daemon
# * the spare must have modules with the same module_type as the mastermax_check_attempts: how many fail check to consider this daemon as DEAD
max_check_attempts 3
# Check this daemon every -X dependingseconds
of the value of the broker__manage_spare__spare_must_have_the_same_list_of_module_type parameter
check_interval # Example: spare_daemon 60
#======== Modules to enable for this broker-spare
daemon =========
# spare_daemonAvailable:
# 1- WebUI = (default) the spare defined with spare_daemon must have the same module_type as this master
# 0 = the spare module_type are: notVisualisation checkedinterface
# broker__manage_spare__spare_must_have_the_same_list_of_module_type - Graphite-Perfdata 1
#======== Daemon connection timeout and down state limit ========= : Save all metrics into a graphite database
# timeout: how many seconds to consider a node don't answer
- sla timeout : Save sla into a 3
database
# data_timeout: how many second to consider a configuration transfer to be failed
- Livestatus # because the network bandwidth is too small.
: data_timeoutTCP API to query element state, used by nagios external tools like NagVis or 120Thruk
# max_check_attempts: how many fail check to consider this daemon as DEAD
max_check_attempts 3
- broker-module-livedata : REST API to query all monitored element data (host, cluster or check)
# Check this daemon every X seconds
- event-manager-writer check_interval : Save events for events 60
#======== Modules to enable for this daemon =========
# Available:manager (do not forget to activate the module in your webui to see data)
# - WebUISimple-log : Save all logs : Visualisation interface
# - Graphite-Perfdata : Save all metrics into a graphite database
# - sla into a common file, Use this module only if you need to have all the check results in one file.
# - broker--module-report-builder : External module used by webui--module-report-handler to generate reports
modules WebUI, Graphite-Perfdata, : Save sla into a databasesla, event-manager-writer
# - Livestatus ======== Realm and architecture settings =========
# Realm to set this daemon into
realm : TCP API to query element state, used by nagios external tools like NagVis or ThrukAll
# - broker-module-livedata : REST API to query all monitored element data (host, cluster or check)
# - event-manager-writer 1 = take data from the daemon realm and its sub realms
# 0 = take data only from the daemon realm
manage_sub_realms : Save events for1
events manager (do not# forgetIn toNATted activateenvironments, theyou moduledeclare ineach your webui to see data)satellite ip[:port] as seen by
# - Simple-log *this* daemon (if port not set, the port declared by satellite itself
# is used)
#satellitemap : Save all logs into a common file, Use this module only if you need to have all the check results in one file. scheduler-1=1.2.3.4:7768, scheduler-2=1.2.3.5:7771
# Exchange between brokers <- schedulers can be limited by packet size (in kB)
# Note: - broker--module-report-builder : External module used by webui--module-report-handler to generate reports
modules as compression is automatic, this is a higher limit, and in real case the
# packets will be lower than this value
WebUI, Graphite-Perfdata, sla, event-manager-writer # broks_packet_size 1024
#======== RealmMemory andprotection architecture settings =========
# Realm to set this daemon into
realm All
Are the daemon module process and worker process are waiting for enough
# 1memory =to takebe dataavailable frombefore thebeing daemonlaunch. realmDefault: and its sub realms1 (enabled)
# 0 = take data only from the daemon realm
manage_sub_realms 1
broker__manage_brok__enable_sub_processes_memory_usage_protection 1
# The sub process memory usage protection can have a system reserved memory
# Inthat NATted environments, you declare each satellite ip[:port] as seen bywon't be used by theses sub process when launched
# *this* Broker (if port not set, the port declared by satellite itself
# is usedBy default: 0 (no reserved memory)
# Example: 10 (means 10% of the total memory is reserved for the system)
#satellitemap scheduler-1=1.2.3.4:7768, poller-1=1.2.3.5:7771broker__manage_brok__sub_process_memory_usage_system_reserved_memory 0
# If Exchangea betweensub Brokersprocess <-cannot Schedulersbe canstarted bebecause limitedof bythe packetprotection, sizehow (inmany kB)seconds
# Note:it aswill compression is automatic, this is a higher limit,be retry and inwait real casethat the
system memory is #freed until it fail to start
packets will be# lowerBy thandefault: this5 value(seconds)
# broks_packet_size 1024broker__manage_brok__sub_processes_memory_usage_protection_max_retry_time 5
#======== MemoryBrok pusher protectionworker =========
# Are the daemon moduleThe broker spawn broks pusher sub process andto workerpush processto areexternal waitingmodules for(like enoughWebUI)
# memorythe tobroker bewill availablelook beforeat beingthis launch.worker Default:execution 1 (enabled)
broker__manage_brok__enable_sub_processes_memory_usage_protection 1
time, and will kill if it timeout
# The subbroker processwill memorycompute usagethe protectionaverage canexecution havetime aof systemprevious reservedworkers memoryto
# decide thatabout won'thow bemany usedtime bythis thesesworker subwill processtake whenbased launchedon:
# By default: 0 (no reserved memory number of broks to send / past average send speed (broks/s)
# Example: 10 (means 10% of the total memory is reserved for the system)
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 If this time is reach, it means that the pusher process is killed
# 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
# By defaultDefault: 5 (secondssecond)
broker__manage_brok__sub_processesprocess_memorybroks_usagepusher_protectionmin_max_retry_timeexecution_timeout 5
#======== Brok pusher worker =========
# The Broker spawn broks pusher sub process to push to external modules (like WebUI)
# the Broker will look at this worker execution time, and will kill if it timeout
# The Broker will compute the average execution time of previous workers to # In order to manage the fact that the server can slow down during this send, you can setup a
# ratio that will be used to increase the allowed timeout by multiply it
# Default: 5
broker__manage_brok__sub_process_broks_pusher_security_ratio 5
# At decidethe aboutbroker howstart manywithout timestats, this worker will take based on:valid will be used for the timeout
# numberDefault: of broks to send / past average send speed (broks/s)
240 (seconds)
broker__manage_brok__sub_process_broks_pusher_max_execution_timeout # If this time240
is reach, it means# thatIf thea pushersub process is killed
reach a timeout, it #will Forbe smallkilled amountand ofrelaunched. broksAfter tomax sendretry,
it should lead# tothe ridiculouslyattached smallmodule allowedwill executionbe timerestarted
# andDefault: the3
fac to spawn the sub process can be higher than this value, so we are using a minimal
broker__manage_brok__sub_process_broks_pusher_max_retry # execution timeout
# Default: 5 (second)3
# broker__manage_brok__sub_process_broks_pusher_minqueue_execution_timeout 5
batch_size:
# * defines the maximum number of broks the "queue brok pusher"
# In order to manage the fact that the server can slow down during this send, you can setup a process will handle per send to external module ( like WebUI ) .
# * Remaining broks will be handled in next send.
# ratio that* willIMPORTANT: beincrease usedthis tovalue increasecan thelead allowedto timeouterror byon multiplythe itsocket
# Default: 5100000 (broks/batch)
# broker__manage_brok__sub_process_broks_pusher_queue_securitybatch_ratiosize 5100000
# AtBroks thewhose Brokerserialization starttime withoutexceeds stats, this validthreshold will begenerate used for the timeouta warning
# Default: 240100 (secondsmilliseconds)
# broker__manage_brok__suboversized_processdata_brokswarning_pusherthreshold_max_execution_timeoutserialization_time 100
# Broks whose serialization time exceeds this threshold will generate an 240error
# IfDefault: a sub process reach a timeout, it will be killed and relaunched. After max retry,500 (milliseconds)
# broker__manage_brok__oversized_data_error_threshold__serialization_time 500
# the attached module will be restarted======== VMWare / ESXi ==========
# Default: 3
broker__manage_brok__sub_process_broks_pusher_max_retry 1 (default) = if vmware get the ESXi CPU stats value, 0 = do not get value
vmware__statistics_compute_enable 31
#======== Enable or not this daemon =========
# 1 = is enabled, 0 = is disabled
enabled 1
}
|