filebeat.yml.j2

#jinja2: lstrip_blocks: True
# {{ ansible_managed }}
###################### Filebeat Configuration File #######################

# The filebeat.reference.yml file from the same directory contains all
# supported options with more comments. You can use it as a reference.
#
# You can find the full configuration reference here:
# https://www.elastic.co/guide/en/beats/filebeat/index.html

#=========================== Filebeat inputs =============================

filebeat.inputs:

# Each - is an input. Most options can be set at the input level, so
# you can use different inputs for various configurations.
# Below are the input specific configurations.

#--- Common group ---
- type: log
  enabled: true
  {% if specification.common_input.multiline is defined %}
  multiline:
    {% for k, v in specification.common_input.multiline.items() %}
    {{ k }}: {{ v }}
    {% endfor %}
  {% endif %}

  # Paths that should be crawled and fetched. Glob based paths.
  paths:
#   - /var/log/audit/audit.log
    - /var/log/auth.log
    - /var/log/firewalld
    {% if 'haproxy' in group_names %}
    - /var/log/haproxy.log
    {% endif %}
    {% if 'kafka' in group_names %}
    - /var/log/kafka/server.log
    {% endif %}
    - /var/log/messages
    - /var/log/secure
    - /var/log/syslog

 # Exclude lines. A list of regular expressions to match. It drops the lines that are
  # matching any regular expression from the list.
  #exclude_lines: ['^DBG']

  # Include lines. A list of regular expressions to match. It exports the lines that are
  # matching any regular expression from the list.
  #include_lines: ['^ERR', '^WARN']

  # Exclude files. A list of regular expressions to match. Filebeat drops the files that
  # are matching any regular expression from the list. By default, no files are dropped.
  #exclude_files: ['.gz$']

  # Optional additional fields. These fields can be freely picked
  # to add additional information to the crawled log files for filtering
  #fields:
  #  level: debug
  #  review: 1

  ### Multiline options

  # Multiline can be used for log messages spanning multiple lines. This is common
  # for Java Stack Traces or C-Line Continuation

  # The regexp Pattern that has to be matched. The example pattern matches all lines starting with [
  #multiline.pattern: ^\[

  # Defines if the pattern set under pattern should be negated or not. Default is false.
  #multiline.negate: false

  # Match can be set to "after" or "before". It is used to define if lines should be append to a pattern
  # that was (not) matched before or after or as long as a pattern is not matched based on negate.
  # Note: After is the equivalent to previous and before is the equivalent to to next in Logstash
  #multiline.match: after

{% if 'postgresql' in group_names %}

# -------------------------- PostgreSQL input --------------------------

# Filebeat postgresql module doesn't support custom log_line_prefix (without patching), see https://discuss.elastic.co/t/filebeats-with-postgresql-module-custom-log-line-prefix/204457
# Dedicated configuration to handle log messages spanning multiple lines.

{# postgresql only #}
- type: log
  enabled: true
  paths:
    - /var/log/postgresql/postgresql*.log*
  exclude_files: [".gz$"]
  {% if specification.postgresql_input.multiline is defined %}
  multiline:
    {% for k, v in specification.postgresql_input.multiline.items() %}
    {{ k }}: {{ v }}
    {% endfor %}
  {% endif %}

{# postgresql extensions - logs without multiline entries #}
- type: log
  enabled: true
  paths:
    - /var/log/postgresql/repmgr.log*
  exclude_files: [".gz$"]
{% endif %}

{% if 'kubernetes_master' in group_names or 'kubernetes_node' in group_names %}

# -------------------------- Kubernetes input --------------------------

# K8s metadata are fetched from Docker labels to not make Filebeat on worker nodes dependent on K8s master
# since Filebeat should start even if K8s master is not available.

- type: container
  enabled: true
  paths:
    - /var/lib/docker/containers/*/*.log
  {% if specification.container_input.multiline is defined %}
  multiline:
    {% for k, v in specification.container_input.multiline.items() %}
    {{ k }}: {{ v }}
    {% endfor %}
  {% endif %}

  processors:
    - add_docker_metadata:
        labels.dedot: false
    - rename:
        fields:
          - from: container.labels.io.kubernetes.container.name
            to: kubernetes.container.name
          - from: container.labels.io.kubernetes.pod.name
            to: kubernetes.pod.name
          - from: container.labels.io.kubernetes.pod.namespace
            to: kubernetes.namespace
        ignore_missing: true
        fail_on_error: true
    - drop_fields:
        fields:
          - container # Drop all fields added by 'add_docker_metadata' that were not renamed
{% endif %}

# ============================== Filebeat modules ==============================

filebeat.config.modules:
  # Glob pattern for configuration loading
  path: ${path.config}/modules.d/*.yml

  # Set to true to enable config reloading
  reload.enabled: false

  # Period on which files under path should be checked for changes
  #reload.period: 10s

# ======================= Elasticsearch template setting =======================

setup.template.settings:
  index.number_of_shards: 3
  #index.codec: best_compression
  #_source.enabled: false

# ================================== General ===================================

# The name of the shipper that publishes the network data. It can be used to group
# all the transactions sent by a single shipper in the web interface.
#name:

# The tags of the shipper are included in their own field with each
# transaction published.
#tags: ["service-X", "web-tier"]

# Optional fields that you can specify to add additional information to the
# output.
#fields:
#  env: staging


# ================================= Dashboards =================================
# These settings control loading the sample dashboards to the Kibana index. Loading
# the dashboards is disabled by default and can be enabled either by setting the
# options here or by using the `setup` command.
{% set dashboards_enabled = is_upgrade_run | ternary(existing_setup_dashboards.enabled, specification.kibana.dashboards.enabled) %}
{% if dashboards_enabled | lower == 'auto' %}
  {% if group_names | intersect(['kibana', 'logging']) | count == 2 %}
setup.dashboards.enabled: true
  {% else %}
setup.dashboards.enabled: false
  {% endif %}
{% else %}
setup.dashboards.enabled: {{ dashboards_enabled | lower }}
{% endif %}

# The Elasticsearch index name.
# This setting overwrites the index name defined in the dashboards and index pattern.
# Example: "testbeat-*"
{% if is_upgrade_run %}
  {% set dashboards_index = 'filebeat-*' if (existing_setup_dashboards.index == 'null') else existing_setup_dashboards.index %}
{% else %}
  {% set dashboards_index = specification.kibana.dashboards.index %}
{% endif %}
setup.dashboards.index: "{{ dashboards_index }}"

# The URL from where to download the dashboards archive. By default this URL
# has a value which is computed based on the Beat name and version. For released
# versions, this URL points to the dashboard archive on the artifacts.elastic.co
# website.
#setup.dashboards.url:

# ====================== Index Lifecycle Management (ILM) ======================

# Configure index lifecycle management (ILM). These settings create a write
# alias and add additional settings to the index template. When ILM is enabled,
# output.elasticsearch.index is ignored, and the write alias is used to set the
# index name.

# Enable ILM support. Valid values are true, false, and auto. When set to auto
# (the default), the Beat uses index lifecycle management when it connects to a
# cluster that supports ILM; otherwise, it creates daily indices.
# Disabled because ILM is not enabled by default in Epiphany
setup.ilm.enabled: false

# Set the prefix used in the index lifecycle write alias name. The default alias
# name is 'filebeat-%{[agent.version]}'.
#setup.ilm.rollover_alias: 'filebeat'

# Set the rollover index pattern. The default is "%{now/d}-000001".
#setup.ilm.pattern: "{now/d}-000001"

# Set the lifecycle policy name. The default policy name is
# 'beatname'.
#setup.ilm.policy_name: "mypolicy"

# The path to a JSON file that contains a lifecycle policy configuration. Used
# to load your own lifecycle policy.
#setup.ilm.policy_file:

# Disable the check for an existing lifecycle policy. The default is true. If
# you disable this check, set setup.ilm.overwrite: true so the lifecycle policy
# can be installed.
#setup.ilm.check_exists: true

# Overwrite the lifecycle policy at startup. The default is false.
#setup.ilm.overwrite: false

#============================== Kibana =====================================

# Starting with Beats version 6.0.0, the dashboards are loaded via the Kibana API.
# This requires a Kibana endpoint configuration.
setup.kibana:

  # Kibana Host
  # Scheme and port can be left out and will be set to the default (http and 5601)
  # In case you specify and additional path, the scheme is required: http://localhost:5601/path
  # IPv6 addresses should always be defined as: https://[2001:db8::1]:5601
{% if not is_upgrade_run %}
  {# mode: apply #}
  {% if setup_kibana_host is defined %}
  host: {{ setup_kibana_host }}
  username: kibanaserver
  password: {{ "'%s'" % opendistro_for_logging_vars.specification.kibanaserver_password | replace("'","''") }}
  {% else %}
  #host: "localhost:5601"
  {% endif %}
{% else %}
  {# mode: upgrade #}
  {% if existing_setup_kibana.host is defined %}
  host: {{ existing_setup_kibana.host }}
  {% else %}
    {% if groups.kibana is defined and groups.logging is defined and (groups.kibana | intersect(groups.logging) | count > 0) %}
  host: {{ hostvars[groups.kibana | intersect(groups.logging) | first].ansible_hostname }}
    {% else %}
  #host: "localhost:5601"
    {% endif %}
  {% endif %}
  {% if existing_setup_kibana.username is defined %}
  username: {{ existing_setup_kibana.username }}
  {% endif %}
  {% if existing_setup_kibana.password is defined %}
  password: {{ "'%s'" % existing_setup_kibana.password | replace("'","''") }}
  {% endif %}
{% endif %}

  # Kibana Space ID
  # ID of the Kibana Space into which the dashboards should be loaded. By default,
  # the Default Space will be used.
  #space.id:

# =============================== Elastic Cloud ================================

# These settings simplify using Filebeat with the Elastic Cloud (https://cloud.elastic.co/).

# The cloud.id setting overwrites the `output.elasticsearch.hosts` and
# `setup.kibana.host` options.
# You can find the `cloud.id` in the Elastic Cloud web UI.
#cloud.id:

# The cloud.auth setting overwrites the `output.elasticsearch.username` and
# `output.elasticsearch.password` settings. The format is `<user>:<pass>`.
#cloud.auth:

#================================ Outputs =====================================

# Configure what output to use when sending the data collected by the beat.
# Default Elasticsearch output is array of 'logging' hosts. If not exist, 'hosts' remains empty to manual configuration.

# ---------------------------- Elasticsearch Output ----------------------------
output.elasticsearch:
  # Array of hosts to connect to.
{% if groups.logging is defined %}
  hosts:
  {% for host in groups.logging %}
    - "https://{{ hostvars[host]['ansible_hostname'] }}:9200"
  {% endfor %}

  # Authentication credentials - either API key or username/password.
  username: logstash
  {% if not is_upgrade_run %}
  password: {{ "'%s'" % opendistro_for_logging_vars.specification.logstash_password | replace("'","''") }}
  {% else %}
  password: {{ "'%s'" % existing_output_es_password | replace("'","''") }}
  {% endif %}

  # Controls the verification of certificates.
  ssl.verification_mode: none
{% else %}
  hosts: []

  # Protocol - either `http` (default) or `https`.
  #protocol: "https"

  # Authentication credentials - either API key or username/password.
  #api_key: "id:api_key"
  #username: "elastic"
  #password: "changeme"
{% endif %}

# ------------------------------ Logstash Output -------------------------------
#output.logstash:
  # The Logstash hosts
  #hosts: ["localhost:5044"]

  # Optional SSL. By default is off.
  # List of root certificates for HTTPS server verifications
  #ssl.certificate_authorities: ["/etc/pki/root/ca.pem"]

  # Certificate for SSL client authentication
  #ssl.certificate: "/etc/pki/client/cert.pem"

  # Client Certificate Key
  #ssl.key: "/etc/pki/client/cert.key"

# ================================= Processors =================================

# Configure processors to enhance or manipulate events generated by the beat.

processors:
  #- add_host_metadata: ~
  - add_cloud_metadata: ~
  #- add_docker_metadata: ~
  #- add_kubernetes_metadata: ~

# ================================== Logging ===================================

# Sets log level. The default log level is info.
# Available log levels are: error, warning, info, debug
#logging.level: debug

# At debug level, you can selectively enable logging only for some components.
# To enable all selectors use ["*"]. Examples of other selectors are "beat",
# "publish", "service".
#logging.selectors: ["*"]

# ============================= X-Pack Monitoring ==============================
# Filebeat can export internal metrics to a central Elasticsearch monitoring
# cluster.  This requires xpack monitoring to be enabled in Elasticsearch.  The
# reporting is disabled by default.

# Set to true to enable the monitoring reporter.
#monitoring.enabled: false

# Sets the UUID of the Elasticsearch cluster under which monitoring data for this
# Filebeat instance will appear in the Stack Monitoring UI. If output.elasticsearch
# is enabled, the UUID is derived from the Elasticsearch cluster referenced by output.elasticsearch.
#monitoring.cluster_uuid:

# Uncomment to send the metrics to Elasticsearch. Most settings from the
# Elasticsearch output are accepted here as well.
# Note that the settings should point to your Elasticsearch *monitoring* cluster.
# Any setting that is not set is automatically inherited from the Elasticsearch
# output configuration, so if you have the Elasticsearch output configured such
# that it is pointing to your Elasticsearch monitoring cluster, you can simply
# uncomment the following line.
#monitoring.elasticsearch:

# ================================= Migration ==================================

# Enable the compatibility layer for Elastic Common Schema (ECS) fields.
# This allows to enable 6 > 7 migration aliases.
#migration.6_to_7.enabled: true