#===============================================================================
# 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 {
#======== 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 = is a spare, 0 = is not a spare
spare 0
#======== Daemon connection timeout and down state limit =========
# timeout: how many seconds to consider a node don't answer
timeout 3
# data_timeout: how many second to consider a configuration transfert to be failed
# because the network brandwith is too small.
data_timeout 120
# max_check_attempts: how many fail check to consider this daemon as DEAD
max_check_attempts 3
# Check this daemon every X seconds
check_interval 60
core-broker-060340145ade11e5b703080027f08538
#===_SE_UUID_HASH 8e00136f9e61061e07ca0f4a63509b68
# End of Shinken Enterprise part
#======== ModulesDaemon toname enableand foraddress this daemon =========
# Available:
Daemon name. Must be #unique
- Simple-log broker_name : save all logs into a common file broker-master
# -IP/fqdn WebUIof this daemon (note: you MUST change it by the real ip/fqdn of this server)
: visualisationaddress interface
# - Graphite-Perfdata : save all metrics into a graphite databaselocalhost
# - sla Port (HTTP/HTTPS) exposed by this daemon
port : save sla into a database
# - Livestatus7772
# 0 = use HTTP, 1 = use :HTTPS
TCP API to queryuse_ssl element state, used by nagios external tools like NagVis or Thruk
# - event-manager-writer : save events for events manager (do not forget to activate the module in your webui to see data)
modules 0
#======== Master or spare selection =========
# 1 = is a spare, 0 = is not a spare
spare Simple-log, WebUI, Graphite-Perfdata, sla, event-manager-writer
0
#======== Realm and architecture settings =========
# Realm to set this daemon into
realm All
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
# 1 = take* data from the a spare_daemon realmcannot andhave its sub realmsa spare_daemon
# 0 = take* datathe onlyspare frommust thehave daemonmodules realm
with the same manage_sub_realms module_type as the master
# 1
#- Independing NATtedof environments,the youvalue declareof each satellite ip[:port] as seen by
# *this* broker (if port not set, the port declared by satellite itself
# is used)the broker__manage_spare__spare_must_have_the_same_list_of_module_type parameter
# Example: spare_daemon broker-spare
spare_daemon
#satellitemap scheduler-1=1.2.3.4:7768, poller-1=1.2.3.5:7771
#======== Memory protection =========
# Are the daemon module process and worker process are waiting for enough# 1 = (default) the spare defined with spare_daemon must have the same module_type as this master
# memory0 to= bethe availablespare beforemodule_type beingare launch. Default: 1 (enabled)
not checked
# broker__manage_brokspare__enablespare_must_subhave_processesthe_memorysame_usage_protection 1list_of_module_type 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)======== Daemon connection timeout and down state limit =========
# timeout: how many seconds to consider a node don't answer
timeout 3
# Exampledata_timeout: 10 (means 10% of the total memory is reserved for the system) how many second to consider a configuration transfer to be failed
# because the network bandwidth is too small.
broker__manage_brok__sub_process_memory_usage_system_reserved_memorydata_timeout 0
# If a sub process cannot be120
started because of the protection,# max_check_attempts: how many seconds
fail check to consider #this itdaemon willas beDEAD
retry and wait thatmax_check_attempts the system memory is freed until it fail3
to start
# Check #this Bydaemon default:every 5X (seconds)
broker__manage_brok__sub_processes_memory_usage_protection_max_retry_timecheck_interval 560
#======== Modules Brokto pusherenable worker ==for this daemon =========
# TheAvailable:
broker spawn broks pusher# sub- processWebUI to push to external modules (like WebUI)
# the broker will look at this worker execution: time,Visualisation andinterface
will kill if it# timeout
- Graphite-Perfdata # The broker will compute: theSave averageall executionmetrics timeinto ofa previousgraphite workers todatabase
# - sla decide about how many time this worker will take based on:
# number of broks to send /: pastSave averagesla sendinto speed (broks/s)a database
# If- thisLivestatus time is reach, it means that the pusher process is killed
: #TCP ForAPI smallto amountquery of broks to sendelement state, itused shouldby leadnagios toexternal ridicuslytools smalllike allowedNagVis executionor timeThruk
# and the fac to spawn the sub process can be higher than this value, so we are using a minimal
# execution timeout
# Default: 5 (second)
broker__manage_brok__sub_process_broks_pusher_min_execution_timeout 5
- 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)
# 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_ratioSimple-log : Save all logs into a common file, Use this module only if you need to have all the check results in one file.
modules WebUI, Graphite-Perfdata, sla, event-manager-writer
5
# At the broker start without stats, this valud will be used for the timeout
# Default: 240 (seconds)
broker__manage_brok__sub_process_broks_pusher_max_execution_timeout======== Realm and architecture settings =========
# Realm to set this daemon into
realm 240All
# If1 a= subtake processdata reachfrom athe timeout,daemon itrealm willand beits killedsub andrealms
relaunched. After max retry,
# the0 attached= moduletake willdata beonly restarted
from the # Default: 3daemon realm
broker__manage_brok__sub_process_broks_pusher_max_retryrealms 1
# In NATted environments, you declare each satellite ip[:port] as seen 3
by
#======== 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 ========= *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
# Exchange between brokers <- schedulers can be limited by packet size (in kB)
# 1 = Note: as compression is automatic, this is enabled, 0 = is disableda higher limit, and in real case the
enabled# packets will be lower than this value
# broks_packet_size 11024
}
#======== Memory protection =========
# Are the daemon module process and worker process are waiting for enough
# memory to be available before being launch. Default: 1 (enabled)
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
# 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
# By default: 5 (seconds)
broker__manage_brok__sub_processes_memory_usage_protection_max_retry_time 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
# decide about how many time this worker will take based on:
# number of broks to send / past average send speed (broks/s)
# 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
# Default: 5 (second)
broker__manage_brok__sub_process_broks_pusher_min_execution_timeout 5
# 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 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
}
|