#===============================================================================
# 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
#===============================================================
# 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 {
# 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 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 =======================
define broker { is a spare, 0 = 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 be unique
broker_name * a spare_daemon can only be the spare of 1 (and only one) master daemon
# * a spare_daemon cannot have broker-master
a spare_daemon
# IP/fqdn of this daemon (note: you MUST change it by the real ip/fqdn of this server)
* the spare must have modules with the 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 daemonbroker-spare
portspare_daemon
# 1 = (default) the spare defined with spare_daemon must have the same module_type as this 7772master
# 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 0 = is not consider a spare
spare node don't answer
timeout 0
# spare_daemon: name of the daemon that will take this daemon job if it dies3
# IMPORTANTdata_timeout:
how many second #to *consider a spare_daemonconfiguration cantransfer onlyto be the spare of 1 (and only one) master daemonfailed
# because * a spare_daemon cannot have a spare_daemonthe network bandwidth is too small.
# data_timeout * the spare must have modules with the same module_type as the master120
# max_check_attempts: how many fail check -to dependingconsider ofthis thedaemon valueas ofDEAD
the broker__manage_spare__spare_must_have_the_same_list_of_module_type parameter max_check_attempts 3
# Check Example:this spare_daemon daemon every X seconds
check_interval broker-spare
spare_daemon
60
#======== Modules to enable for this daemon =========
# 1Available:
= (default) the spare# defined- withWebUI spare_daemon must have the same 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 : Visualisation 1
interface
#======== Daemon connection timeout and down state limit =========
- Graphite-Perfdata # timeout: howSave manyall secondsmetrics tointo consider a node don't answergraphite database
timeout# - sla 3
# data_timeout: how many second to consider a: configurationSave transfersla tointo bea faileddatabase
# because- theLivestatus network bandwidth is too small.
data_timeout : TCP 120
API to query element # max_check_attempts: how many fail check to consider this daemon as DEAD
max_check_attemptsstate, used by nagios external tools like NagVis or Thruk
# - broker-module-livedata 3
: REST API #to Checkquery thisall daemonmonitored everyelement X seconds
check_intervaldata (host, cluster or check)
# - event-manager-writer 60
#======== Modules to enable for this daemon =========
# Available:
# - WebUI : Save events for events manager (do not forget to activate the module in your webui to see data)
# - Simple-log : VisualisationSave interface
all logs into a #common - Graphite-Perfdata : Save all metrics into a graphite database
# - sla 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, : Save sla into a databaseGraphite-Perfdata, sla, event-manager-writer
# - Livestatus ======== Realm and architecture settings =========
# : TCP API to query element state, used by nagios external tools like NagVis or Thruk
Realm to set this daemon into
realm # - broker-module-livedata All
# 1 = take :data RESTfrom APIthe todaemon queryrealm alland monitoredits elementsub datarealms
(host, cluster or check)
# 0 = take #data - event-manager-writer 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)
# - broker--module-report-builder : External module used by webui--module-report-handler to generate reports
modules Note: 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 and architectureprotection settings =========
# RealmAre tothe set this daemon into
module process and worker realmprocess are waiting All
for enough
# 1memory =to takebe dataavailable frombefore thebeing daemonlaunch. realmDefault: and its sub realms
1 (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 used)
#satellitemap scheduler-1=1.2.3.4:7768, poller-1=1.2.3.5:7771By 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
# ExchangeIf betweena Brokerssub <-process Schedulerscannot can be limitedstarted bybecause packetof sizethe (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 1024protection, 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 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: 1 (enabled)
broker__manage_brok__enable_sub_processes_memory_usage_protection 1
execution 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 launched
# By default: 0 (no reserved memoryon:
# number of broks to send / past average send speed (broks/s)
# Example: 10 (means 10% of If this time is reach, it means that the totalpusher memoryprocess is reservedkilled
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# 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 ========= In order to manage the fact that the server can slow down during this send, you can setup a
# 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 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 Thethe broker Brokerstart willwithout computestats, thethis averagevalid executionwill timebe ofused previousfor workersthe totimeout
# decideDefault: about how many time this worker will take based on:
# number of broks to send / past average send speed (broks/s)240 (seconds)
broker__manage_brok__sub_process_broks_pusher_max_execution_timeout 240
# If thisa timesub isprocess reach a timeout, it means that the pusher process is killed
# For small amount of broks to send, it should lead to ridiculously small allowed execution timewill be killed and relaunched. After max retry,
# the attached module will be restarted
# 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_timeoutbatch_size:
# * defines the maximum number of broks 5
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
# At theBroks Brokerwhose startserialization withouttime stats,exceeds this validthreshold will begenerate used for the timeouta warning
# Default: 240100 (secondsmilliseconds)
# broker__manage_brok__suboversized_processdata_brokswarning_pusherthreshold_max_executionserialization_timeouttime 240100
# Broks whose Ifserialization atime subexceeds processthis reachthreshold awill timeout,generate itan willerror
be killed and relaunched.# AfterDefault: max retry,500 (milliseconds)
# the attached module will be restartedbroker__manage_brok__oversized_data_error_threshold__serialization_time 500
# Default: 3
broker__manage_brok__sub_process_broks_pusher_max_retry ======== VMWare / ESXi ==========
# 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
}
|