7.2.9.2. Configuration / fichiers utiles

Se reporter au DIN, qui configure le cluster ElastciSearch de données.

Les fichiers de configuration sont définis sous /vitam/conf/elasticsearch-data.

7.2.9.2.1. Fichier log4j2.properties

status = error

# log action execution errors for easier debugging
logger.action.name = org.elasticsearch.action
logger.action.level = debug

appender.console.type = Console
appender.console.name = console
appender.console.layout.type = PatternLayout
appender.console.layout.pattern = [%d{ISO8601}][%-5p][%-25c{1.}] %marker%m%n

appender.syslog.type = Syslog
appender.syslog.name = syslog
appender.syslog.appName = {{ composant.cluster_name }}
appender.syslog.facility = {{ vitam_defaults.syslog_facility }}
appender.syslog.host = {{ inventory_hostname }}
appender.syslog.protocol = UDP
appender.syslog.port = 514
appender.syslog.layout.type = PatternLayout
# Note: rsyslog only parse RFC3195-formatted syslog messages by default ; AND, to make it work with log4j2, we need to start the layout by the app-name.
# IF we were in 5424, we wouldn't have to do this.
appender.syslog.layout.pattern = {{ composant.cluster_name }}: [%d{ISO8601}][%-5p][%-25c{1.}] %marker%m%n
# appender.syslog.format = RFC5424
# appender.syslog.mdcId = esdata

appender.rolling.type = RollingFile
appender.rolling.name = rolling
appender.rolling.fileName = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}.log
appender.rolling.layout.type = PatternLayout
appender.rolling.layout.pattern = [%d{ISO8601}][%-5p][%-25c{1.}] %marker%.-10000m%n
appender.rolling.filePattern = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}-%d{yyyy-MM-dd}.log
appender.rolling.policies.type = Policies
appender.rolling.policies.time.type = TimeBasedTriggeringPolicy
appender.rolling.policies.time.interval = 1
appender.rolling.policies.time.modulate = true

rootLogger.level = info
rootLogger.appenderRef.console.ref = console
rootLogger.appenderRef.rolling.ref = rolling
rootLogger.appenderRef.syslog.ref = syslog

appender.deprecation_rolling.type = RollingFile
appender.deprecation_rolling.name = deprecation_rolling
appender.deprecation_rolling.fileName = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_deprecation.log
appender.deprecation_rolling.layout.type = PatternLayout
appender.deprecation_rolling.layout.pattern = [%d{ISO8601}][%-5p][%-25c{1.}] %marker%.-10000m%n
appender.deprecation_rolling.filePattern = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_deprecation-%i.log.gz
appender.deprecation_rolling.policies.type = Policies
appender.deprecation_rolling.policies.size.type = SizeBasedTriggeringPolicy
appender.deprecation_rolling.policies.size.size = 1GB
appender.deprecation_rolling.strategy.type = DefaultRolloverStrategy
appender.deprecation_rolling.strategy.max = 4

logger.deprecation.name = org.elasticsearch.deprecation
logger.deprecation.level = warn
logger.deprecation.appenderRef.deprecation_rolling.ref = deprecation_rolling
logger.deprecation.additivity = false

appender.index_search_slowlog_rolling.type = RollingFile
appender.index_search_slowlog_rolling.name = index_search_slowlog_rolling
appender.index_search_slowlog_rolling.fileName = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_index_search_slowlog.log
appender.index_search_slowlog_rolling.layout.type = PatternLayout
appender.index_search_slowlog_rolling.layout.pattern = [%d{ISO8601}][%-5p][%-25c] %marker%.-10000m%n
appender.index_search_slowlog_rolling.filePattern = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_index_search_slowlog-%d{yyyy-MM-dd}.log
appender.index_search_slowlog_rolling.policies.type = Policies
appender.index_search_slowlog_rolling.policies.time.type = TimeBasedTriggeringPolicy
appender.index_search_slowlog_rolling.policies.time.interval = 1
appender.index_search_slowlog_rolling.policies.time.modulate = true

logger.index_search_slowlog_rolling.name = index.search.slowlog
logger.index_search_slowlog_rolling.level = trace
logger.index_search_slowlog_rolling.appenderRef.index_search_slowlog_rolling.ref = index_search_slowlog_rolling
logger.index_search_slowlog_rolling.additivity = false

appender.index_indexing_slowlog_rolling.type = RollingFile
appender.index_indexing_slowlog_rolling.name = index_indexing_slowlog_rolling
appender.index_indexing_slowlog_rolling.fileName = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_index_indexing_slowlog.log
appender.index_indexing_slowlog_rolling.layout.type = PatternLayout
appender.index_indexing_slowlog_rolling.layout.pattern = [%d{ISO8601}][%-5p][%-25c] %marker%.-10000m%n
appender.index_indexing_slowlog_rolling.filePattern = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_index_indexing_slowlog-%d{yyyy-MM-dd}.log
appender.index_indexing_slowlog_rolling.policies.type = Policies
appender.index_indexing_slowlog_rolling.policies.time.type = TimeBasedTriggeringPolicy
appender.index_indexing_slowlog_rolling.policies.time.interval = 1
appender.index_indexing_slowlog_rolling.policies.time.modulate = true

logger.index_indexing_slowlog.name = index.indexing.slowlog.index
logger.index_indexing_slowlog.level = trace
logger.index_indexing_slowlog.appenderRef.index_indexing_slowlog_rolling.ref = index_indexing_slowlog_rolling
logger.index_indexing_slowlog.additivity = false

7.2.9.2.2. Fichier elasticsearch.yml

# ======================== Elasticsearch Configuration =========================
#
# NOTE: Elasticsearch comes with reasonable defaults for most settings.
#       Before you set out to tweak and tune the configuration, make sure you
#       understand what are you trying to accomplish and the consequences.
#
# The primary way of configuring a node is via this file. This template lists
# the most important settings you may want to configure for a production cluster.
#
# Please see the documentation for further information on configuration options:
# <http://www.elastic.co/guide/en/elasticsearch/reference/current/setup-configuration.html>
#
# ---------------------------------- Cluster -----------------------------------
#
# Use a descriptive name for your cluster:
#
cluster.name: {{ composant.cluster_name }}
#
# ------------------------------------ Node ------------------------------------
#
# Use a descriptive name for the node:
#
node.name: {{ inventory_hostname }}
# TODO: Better handling of this as we have to modify wich nodes are requested by VITAM
node.master: {{ is_master|default('true') }}
node.data: {{ is_data|default('true') }}
#
# Add custom attributes to the node:
#
# node.rack: r1
#
# ----------------------------------- Paths ------------------------------------
#
# Path to directory where to store the data (separate multiple locations by comma):
#
path.data: {{ elasticsearch_data_dir }}
#
# Path to log files:
#
path.logs: {{ elasticsearch_log_dir }}
#
# ----------------------------------- Memory -----------------------------------
#
# Lock the memory on startup:
# = Disable swapping
bootstrap.memory_lock: true
#
# Make sure that the `ES_HEAP_SIZE` environment variable is set to about half the memory
# available on the system and that the owner of the process is allowed to use this limit.
#
# Elasticsearch performs poorly when the system is swapping the memory.
#
# ---------------------------------- Network -----------------------------------
#
# Set the bind address to a specific IP (IPv4 or IPv6):
#
# Note : if installing to localhost, notably a docker container, we need to bind larger than localhost
network.host: 0.0.0.0  # KWA : For now, keep 0.0.0.0 as vitam component use the service interface, but cerebro uses the admin interface
{% if inventory_hostname == "localhost" %}
http.cors.enabled: true
http.cors.allow-origin: "*"
{% else %}
## network.host: {{ ip_service }}
{% endif %}
#
# Set a custom port for HTTP:
#
http.port: {{ composant.port_http }}
transport.tcp.port: {{ composant.port_tcp }}
#
# For more information, see the documentation at:
# <http://www.elastic.co/guide/en/elasticsearch/reference/current/modules-network.html>
#
# --------------------------------- Discovery ----------------------------------
#
# Pass an initial list of hosts to perform discovery when new node is started:
# The default list of hosts is ["127.0.0.1", "[::1]"]
#
discovery.zen.ping.unicast.hosts: [ {% for host in groups['hosts-elasticsearch-data'] %}"{{ hostvars[host]['ip_admin'] }}"{% if not loop.last %},{% endif %}{% endfor %} ]
#
# Prevent the "split brain" by configuring the majority of nodes (total number of nodes / 2 + 1):
#
discovery.zen.minimum_master_nodes: {{ ((groups['hosts-elasticsearch-data']|length / 2)+1)| round (0, 'floor')| int }}
#
# For more information, see the documentation at:
# <http://www.elastic.co/guide/en/elasticsearch/reference/current/modules-discovery.html>
#
# ---------------------------------- Gateway -----------------------------------
#
# Block initial recovery after a full cluster restart until N nodes are started:
#
gateway.expected_nodes: {{ (groups['hosts-elasticsearch-data'] | length) }}
gateway.recover_after_nodes: {{ ((groups['hosts-elasticsearch-data']|length / 2)+1)| round (0, 'floor')| int }}
#
# For more information, see the documentation at:
# <http://www.elastic.co/guide/en/elasticsearch/reference/current/modules-gateway.html>
#
# ---------------------------------- Various -----------------------------------
#
# Disable starting multiple nodes on a single system:
#
# node.max_local_storage_nodes: 1
#
# Require explicit names when deleting indices:
#
action.destructive_requires_name: true

# For Vitam multiquery
indices.query.bool.max_clause_count: 10000

{% if composant.index_buffer_size_ratio is defined %}
# some perforamnce tuning ; see https://www.elastic.co/guide/en/elasticsearch/reference/6.4/tune-for-indexing-speed.html
# 0.1 may be enough, cots_vars declares {{ composant.index_buffer_size_ratio }} as ratio on total memory {{ elasticsearch_memory }}
indices.memory.index_buffer_size: {{ ((elasticsearch_memory_value|int)*(composant.index_buffer_size_ratio|float))|round (0, 'floor')| int }}{{ elasticsearch_memory_unit }}
{% endif %}

# thread_pool configuration
thread_pool:
    index:
        size: {{ (ansible_processor_cores * ansible_processor_threads_per_core) | round (0, 'floor') | int }}
        queue_size: 5000
    get:
        size: {{ (ansible_processor_cores * ansible_processor_threads_per_core)| round (0, 'floor') | int }}
        queue_size: 5000
    search:
        size: {{ ((ansible_processor_cores * ansible_processor_threads_per_core * 3 / 2) + 1) | round (0, 'floor') | int }}
        min_queue_size: 1000
        queue_size: 5000
    write:
        size: {{ (ansible_processor_cores * ansible_processor_threads_per_core + 1)| round (0, 'floor') | int }}
        queue_size: 5000
    warmer:
        core: 1
        max: {{ ((ansible_processor_cores * ansible_processor_threads_per_core / 2) + 0.5) | round (0, 'floor') | int }}
        keep_alive: 2m

# Note : the 0.5 in the previous expression is for there is only 1 CPU (else the thread pool size would be zero) ! ; Note bis : max 10 threads #
# Note : in ES5 and further : the thread pool "refresh" is of type scaling with a keep-alive of 5m and a max of min(10, (# of available processors)/2)

7.2.9.2.3. Fichier sysconfig/elasticsearch

################################
# Elasticsearch
################################

# Elasticsearch home directory
#ES_HOME=/usr/share/elasticsearch

# Elasticsearch configuration directory
ES_PATH_CONF={{ vitam_defaults.folder.root_path }}/conf/{{ composant.cluster_name }}/elasticsearch.yml

# Elasticsearch data directory
#DATA_DIR={{ vitam_defaults.folder.root_path }}/data/{{ composant.cluster_name }}

# Elasticsearch logs directory
#LOG_DIR={{ vitam_defaults.folder.root_path }}/log/{{ composant.cluster_name }}

# Elasticsearch PID directory
#PID_DIR=/var/run/{{ composant.cluster_name }}

# Heap size defaults to 256m min, 1g max
# Set ES_HEAP_SIZE to 50% of available RAM, but no more than 31g
#ES_JAVA_OPTS=

################################
# Elasticsearch service
################################

# SysV init.d
#
# The number of seconds to wait before checking if Elasticsearch started successfully as a daemon process
ES_STARTUP_SLEEP_TIME=5


# Heap new generation
#ES_HEAP_NEWSIZE=

# Maximum direct memory
#ES_DIRECT_SIZE=

# Additional Java OPTS
ES_JAVA_OPTS="-XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=10 -XX:GCLogFileSize=10M -XX:+PrintGCDetails -XX:+PrintGCApplicationStoppedTime"

# Configure restart on package upgrade (true, every other setting will lead to not restarting)
#RESTART_ON_UPGRADE=true

# Path to the GC log file
#ES_GC_LOG_FILE={{ vitam_defaults.folder.root_path }}/log/{{ composant.cluster_name }}/gc.log

################################
# Elasticsearch service
################################

# SysV init.d
#
# When executing the init script, this user will be used to run the elasticsearch service.
# The default value is 'elasticsearch' and is declared in the init.d file.
# Note that this setting is only used by the init script. If changed, make sure that
# the configured user can read and write into the data, work, plugins and log directories.
# For systemd service, the user is usually configured in file /usr/lib/systemd/system/elasticsearch.service

# Note: useless for VITAM, as the startup is managed by systemd
ES_USER={{ vitam_defaults.users.vitamdb }}
ES_GROUP={{ vitam_defaults.users.group }}

# The number of seconds to wait before checking if Elasticsearch started successfully as a daemon process
ES_STARTUP_SLEEP_TIME=5

################################
# System properties
################################

# Specifies the maximum file descriptor number that can be opened by this process
# When using Systemd, this setting is ignored and the LimitNOFILE defined in
# /usr/lib/systemd/system/elasticsearch.service takes precedence
#MAX_OPEN_FILES=65536

# The maximum number of bytes of memory that may be locked into RAM
# Set to "unlimited" if you use the 'bootstrap.memory_lock: true' option
# in elasticsearch.yml (ES_HEAP_SIZE  must also be set).
# When using Systemd, the LimitMEMLOCK property must be set
# in /usr/lib/systemd/system/elasticsearch.service
#MAX_LOCKED_MEMORY=unlimited

# Maximum number of VMA (Virtual Memory Areas) a process can own
# When using Systemd, this setting is ignored and the 'vm.max_map_count'
# property is set at boot time in /usr/lib/sysctl.d/elasticsearch.conf
#MAX_MAP_COUNT=262144

7.2.9.2.4. Fichier /usr/lib/tmpfiles.d/elasticsearch-data.conf

d    /var/run/{{ composant.cluster_name }}   0755 {{ vitam_defaults.users.vitamdb }} {{ vitam_defaults.users.group }} - -