Page History

#===============================================================================
# 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
#===============================================================================
# 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

    #======== Daemon name and address ========= 0 = use HTTP, 1 = use HTTPS
    #use_ssl	 Daemon name. Must be unique
    broker_name         0


    #======== Master broker-master

or spare selection  # IP/fqdn of this daemon (note: you MUST change it by the real ip/fqdn of this server)
    address=========
    # 1 = is a spare, 0 = is not a spare
    spare                     localhost0

    # Port (HTTP/HTTPS) exposed by spare_daemon: name of the daemon that will take this daemon job if it dies
    port# IMPORTANT:
    #   * a spare_daemon can only be the spare of 1 (and only one) master 7772
daemon
    #  0 =* use HTTP, 1 = use HTTPSa spare_daemon cannot have a spare_daemon
    use_ssl	#   * the spare must have modules with the same module_type as the    0


master
    #======== Master or spare selection =========
    # 1 = is a spare, 0 = is not a spare
    spare - depending of the value of the broker__manage_spare__spare_must_have_the_same_list_of_module_type parameter
    # Example: spare_daemon              broker-spare
    spare_daemon

    # 1  0

    #= (default) the spare defined with spare_daemon: name of the daemon that will take this daemon job if it dies
    # IMPORTANT: 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   * a spare_daemon can only be the spare of 1 (and only one) master daemon 1


    #======== Daemon connection timeout and down state limit =========
    # timeout:  *how many seconds to consider a spare_daemon cannot have a spare_daemon
node don't answer
    timeout    #   * the spare must have modules with the same module_type as the master3

    # data_timeout: how many second -to dependingconsider ofa theconfiguration valuetransfer ofto the broker__manage_spare__spare_must_have_the_same_list_of_module_type parameterbe failed
    # Example: spare_daemonbecause the network bandwidth is too small.
    data_timeout          broker-spare
    spare_daemon120

    # 1 = (default) the spare defined with spare_daemon must have the same module_type as this master max_check_attempts: how many fail check to consider this daemon as DEAD
    max_check_attempts        3

    # 0 = the spare module_type are not checked
    # broker__manage_spare__spare_must_have_the_same_list_of_module_type Check this daemon every X seconds
    check_interval            160


    #======== DaemonModules connectionto timeoutenable andfor downthis statedaemon limit =========
    # timeoutAvailable: how many seconds to consider a node don't answer
    timeout     
    # - WebUI                   : Visualisation interface
    # - Graphite-Perfdata       : Save all metrics into a graphite 3database

    # data_timeout: how many second to consider a configuration transfer to be failed
- sla              # because the network bandwidth is too small.
: Save sla into data_timeouta database
    # - Livestatus       120

    # max_check_attempts: how many: failTCP checkAPI to considerquery thiselement daemonstate, asused DEAD
by nagios external tools max_check_attemptslike NagVis or Thruk
     3

# - broker-module-livedata  : REST #API Checkto thisquery daemonall everymonitored Xelement seconds
data (host, cluster or check_interval)
    # - event-manager-writer    :  60


    #======== Modules to enable for this daemon =========
    # Available:Save events for events manager (do not forget to activate the module in your webui to see data)
    # - WebUISimple-log              : Save all logs into a common file, Use this module only if :you Visualisationneed interface
to have all the #check -results Graphite-Perfdatain one file.
    modules        : Save all metrics into a graphite database
   WebUI, # Graphite-Perfdata, sla, event-manager-writer
    

    #======== Realm and architecture     settings =========
    # Realm to set this daemon  : Save sla into a database
    #realm - Livestatus                  All

   : TCP# API1 to= querytake elementdata state,from usedthe bydaemon nagiosrealm externaland toolsits like NagVis or Thruksub realms
    # - broker-module-livedata         : REST API to query all monitored element data (host, cluster or check)0 = take data only from the daemon realm
    manage_sub_realms        1

    # - event-manager-writer           : Save events for events manager (do not forget to activate the module in your webui to see data)In NATted environments, you declare each satellite ip[:port] as seen by
    # *this* daemon (if port not set, the port declared by satellite itself
    # - Simple-logis used)
    #satellitemap    scheduler-1=1.2.3.4:7768, scheduler-2=1.2.3.5:7771

    # Exchange between brokers <- schedulers can be :limited Saveby allpacket logssize into a common file, Use this module only if you need to have all the check results in one file.(in kB)
    # Note: as compression is automatic, this is a higher limit, and in real case the
    modules#       packets will be lower than this value
     WebUI, Graphite-Perfdata, sla, event-manager-writer# broks_packet_size 1024


    #======== Realm and architectureMemory settingsprotection =========
    # RealmAre tothe set this daemon into
module process and worker realmprocess are waiting for enough
    # memory to be available before being launch. Default:    All
1 (enabled)
    # 1 = take data from the daemon realm and its sub realmsbroker__manage_brok__enable_sub_processes_memory_usage_protection   1

    # 0The =sub takeprocess datamemory onlyusage fromprotection thecan daemonhave realm
a system   manage_sub_realms        1


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 By default: 0 (no reserved memory)
    # Example: 10  (means 10% of the total memory is reserved for the system)
    #satellitemapbroker__manage_brok__sub_process_memory_usage_system_reserved_memory    scheduler-1=1.2.3.4:7768, poller-1=1.2.3.5:77710

    # ExchangeIf a betweensub Brokersprocess <-cannot Schedulersbe canstarted bebecause limitedof bythe packetprotection, sizehow (inmany kB)seconds
    # Note: as compression is automatic, this is a higher limit, it will be retry and inwait realthat case 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


    #======== Brok Memorypusher protectionworker =========
    # The broker Arespawn thebroks daemonpusher modulesub 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 launched
    # By default: 0 (no reserved memoryon:
    # 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




    # In order to manage the fact that the server can slow down during this send, you can setup a
    #======== 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 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

    # The Broker will compute At the averagebroker executionstart timewithout ofstats, previousthis workersvalid to
will be used for #the decidetimeout
 about how many time# thisDefault: worker will take based on:240 (seconds)
    # number of broks to send / past average send speed (broks/s)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: 5
 100000 (broks/batch)
    # broker__manage_brok__sub_process_broks_pusher_security_ratio      _queue_batch_size            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_timeout           240

serialization_time   100

    # Broks whose serialization time exceeds this threshold will generate an error
    # 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

}