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
#

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

    # 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 {

    #======== Daemon name *and the spare must have modules with the same module_type as the masteraddress =========
    # Daemon name. Must be unique
    # Example: spare_daemonbroker_name               broker-sparemaster

    # IP/fqdn of spare_this daemon

 (note: you  #======== Daemon connection timeout and down state limit =========
MUST change it by the real ip/fqdn of this server)
    address      # timeout: how many seconds to consider a node don't answer
   localhost

 timeout   # Port (HTTP/HTTPS) exposed by this daemon
    port      3

    # data_timeout: how many second to consider a configuration transfert to be failed7772

    # because the network brandwith is too small.
0 = use HTTP, 1 = use HTTPS
    use_ssl	    data_timeout              1200


    # 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======== Master or spare selection =========
    # 1 = is a spare, 0 = is not a spare
    spare                      600



    #======== Modules to enable for spare_daemon: name of the daemon that will take this daemon =========job if it dies
    # AvailableIMPORTANT:
    # - Simple-log * a spare_daemon can only be the spare of 1 (and :only saveone) all logs into a common filemaster daemon
    # - WebUI * a spare_daemon cannot have a spare_daemon
    #   * the spare :must visualisation interface
    # - Graphite-Perfdata     : save all metrics into a graphite database
have modules with the same module_type as the master
    # Example: spare_daemon     # - sla       broker-spare
    spare_daemon

    #======== Daemon connection timeout :and savedown slastate into a databaselimit =========
    # -timeout: Livestatushow many seconds to consider a node don't answer
    :timeout TCP API to query element state, used by nagios external tools like NagVis or Thruk
    modules3

    # data_timeout: how many second to consider a configuration transfert to be failed
   Simple-log, WebUI, Graphite-Perfdata, sla, event-manager-writer
    

    #======== Realm and architecture settings =========
    # Realm to set this daemon into
    realm             # 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        All3

    # 1Check =this takedaemon dataevery fromX theseconds
 daemon realm and itscheck_interval sub realms
    # 0 = take data only from the daemon realm 60



    manage_sub_realms        1


#======== Modules to enable for this daemon =========
    # 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)Available:
    # - Simple-log            : save all logs into a common file
    #satellitemap# - WebUI  scheduler-1=1.2.3.4:7768, poller-1=1.2.3.5:7771

    # Exchange between brokers <- schedulers can be limited by packet size: (invisualisation kB)interface
    # Note: as compression is automatic, this is a higher limit, and in real case the- Graphite-Perfdata     : save all metrics into a graphite database
    # - sla     packets will be lower than this value
    # broks_packet_size 1024


  :  #======== Memory protection =========save sla into a database
    # - Livestatus  Are the daemon module process and worker process are waiting for: enough
TCP API to query #element memorystate, toused beby availablenagios beforeexternal beingtools launch.like Default:NagVis 1or (enabled)Thruk
    broker__manage_brok__enable_sub_processes_memory_usage_protectionmodules       1

    # The sub process memory usage protection can have a system reserved memorySimple-log, WebUI, Graphite-Perfdata, sla, event-manager-writer
    #

 that won't be used by theses sub process when launched #======== Realm and architecture settings =========
    # ByRealm default:to 0set (nothis reserveddaemon memory)into
    #realm Example: 10  (means 10% of the total memory is reserved for the system)
    broker__manage_brok__sub_process_memory_usage_system_reserved_memory    0All

    # 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 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
    # By default: 5 (seconds)
    broker__manage_brok__sub_processes_memory_usage_protection_max_retry_time   5


    #======== Brok pusher worker =========*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

    # The brokerExchange spawnbetween broksbrokers pusher<- subschedulers processcan tobe pushlimited toby externalpacket modulessize (likein WebUIkB)
    # theNote: brokeras willcompression lookis atautomatic, this workeris a executionhigher timelimit, and willin killreal ifcase it timeoutthe
    #   The    brokerpackets will be lower computethan thethis averagevalue
 execution time of previous workers to# broks_packet_size 1024


    # 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======== 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

    # ForThe sub smallprocess amountmemory ofusage broksprotection tocan send,have ita shouldsystem leadreserved tomemory
 ridicusly small allowed execution# time
that won't be used #by andtheses thesub facprocess towhen spawnlaunched
 the sub process can# beBy higherdefault: than0 this(no value, so we are using a minimal
    # execution timeout
    # Default: 5 (secondreserved memory)
    # Example: 10  (means 10% of the total memory is reserved for the system)
    broker__manage_brok__sub_process_broksmemory_pusherusage_minsystem_executionreserved_timeoutmemory           50

    # In order to manage the fact that the server can slow down during this send, you can setup aIf a sub process cannot be started because of the protection, how many seconds
    # ratio thatit will be retry usedand towait increasethat the allowedsystem memory timeoutis byfreed multiplyuntil it fail to start
    # DefaultBy default: 5 (seconds)
    broker__manage_brok__sub_processes_memory_processusage_broksprotection_pushermax_securityretry_ratio time                 55


    # At the broker start without stats, this valud will be used for the timeout
    # Default: 240 (seconds======== Brok pusher worker =========
    # The broker spawn broks pusher sub process to push to external modules (like WebUI)
    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 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
    # the attached moduledecide about how many time this worker will be restartedtake based on:
    # Default:number 3
of broks   broker__manage_brok__sub_process_broks_pusher_max_retry      to send / past average send speed (broks/s)
    # If this time is reach, it means that the pusher process is 3
killed

    #======== Brok getter in modules =========
    # These parameters allow some internal tuning in broks management in modules
 
    # Take the lock as soon as reader thread has some broks to manage For small amount of broks to send, it should lead to ridicusly small allowed execution time
    # and the fac to spawn the sub process can be higher than this value, so we are using a minimal
    # inexecution ordertimeout
 to attempt to reduce# concurrent usage of CPUDefault: 5 (second)
    # broker__manage_brok__sub_moduleprocess_broks_getterpusher_min_earlyexecution_locktimeout           5

    # In order to manage the fact that the server can slow down 1
during 
this send, you can # Take extra broks sets to manage if more than this parameter sets are waiting
    #  0 special value disable managing of late broks setssetup a
    # ratio that will be used to increase the allowed timeout by multiply it
    # Default: 5
    # broker__manage_brok__sub_moduleprocess_broks_getterpusher_latesecurity_sets_allowedratio                     105
 
    # At Whenthe enabledbroker withstart previouswithout parameterstats, stopthis takingvalud extrawill broks setsbe whenused wefor alreadythe havetimeout
    # thisDefault: parameter broks to manage240 (seconds)
    # broker__manage_brok__sub_moduleprocess_broks_getterpusher_max_late_broks_managedexecution_timeout           240

    #  200000
 
    # After we have managed some broks, if more than broker__manage_brok_module_broks_getter_late_sets_allowed
    # broks sets are waiting, continue late sets managing
    #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_module_brokssub_getterprocess_loopbroks_onpusher_late_broksmax_retry                       03


    #======== Enable or not this daemon =========
    # 1 = is enabled, 0 = is disabled
    enabled                  1

}