Page History

conteneurs de données échangées entre les Schedulers et les Brokers. Il y a plusieurs

types de Broks :

• Des évènements ( comme un Scheduler qui vient de démarrer ).
• La configuration des éléments supervisés ( hôtes, checks, période de temps, utilisateurs ).
• L'état des hôtes, clusters et checks après chaque vérification.

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

 #   

* the spare must have modules with the same module_type as the master
    # 

- 

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 = 

(default) the spare defined with 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     1


    #========

 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 transfer 

to 

be failed
    # 

because 

the network bandwidth 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


    #

======== Modules to enable for this daemon =========
    # Available:
    # - 

WebUI           

: 

Visualisation interface
    # - 

Graphite-

Perfdata              : Save all metrics into a graphite 

database
 

# 

- 

sla 

: 

Save sla into a database
    

# - Livestatus                 

 : TCP API to query element state, used by nagios external tools like NagVis or Thruk
    # - 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)
    # - Simple-log                     : Save all logs 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, sla, event-manager-writer
    

    #======== Realm and 

architecture 

settings =========
    # 

Realm 

to 

set 

this 

daemon 

into
 

realm 

All

    # 

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
    

# *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)
    # 

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 1024


    #======== 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

}