I am using Filebeat to ship logs from the server to Elastic. We use ingestNode pipelines to parse the files using Grok processor.
Please find my filebeat.yml file. I see the memory consumed by a single process is around 500MB.
###################### Filebeat Configuration Example #########################
# This file is an example configuration file highlighting only the most common
# options.
#=========================== Filebeat inputs =============================
filebeat.inputs:
- type: log
enabled: false
paths:
- /var/log/log.log
fields:
logtype: "xxxx"
exclude_lines: ['.*INFO.*']
pipeline: "yyyyyyy"
index: "%{[fields.logtype]}-%{[beat.version]}-%{+yyyy.MM.dd}"
multiline.pattern: '^([0-9]{4}-[0-9]{2}-[0-9]{2})'
multiline.negate: true
multiline.match: after
- type: log
enabled: true
paths:
- XXXXXXXXXXXXXXXXX
fields:
logtype: "xxxxxxx"
multiline.match: after
#multiline.pattern: '^[[:space:]]'
multiline.pattern: '^([0-9]{4}-[0-9]{2}-[0-9]{2})'
multiline.negate: true
multiline.match: after
#tail_files: true
#exclude_lines: ['.*INFO.*']
spool_size: 1
ignore_older: 48h
#include_lines: ['^ERR', '^WARN']
### 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
#multiline.pattern: '^\['
#multiline.negate: true
#multiline.match: after
#============================= 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
#==================== Elasticsearch template setting ==========================
setup.template.settings:
index.number_of_shards: 3
#index.codec: best_compression
#_source.enabled: false
setup.template.name: "zzzzzzzz"
setup.template.pattern: "yyyyyyy*"
setup.template.overwrite: 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 =====================================
# the dashboards is disabled by default and can be enabled either by setting the
# options here, or by using the `-setup` CLI flag or the `setup` command.
#setup.dashboards.enabled: false
# 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:
#============================== 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
#host: "localhost:5601"
# 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.
#-------------------------- Elasticsearch output ------------------------------
output.elasticsearch:
# Array of hosts to connect to.
hosts: ["localhost:9200"]
#index: "%{[fields.logtype]}-%{[beat.version]}-%{+yyyy.MM.dd}"
indices:
- index: "samplelog-%{[agent.version]}-%{+yyyy.MM.dd}"
when.contains:
message: "SAMPLE TEXT"
- index: "samplelog3-%{[agent.version]}-%{+yyyy.MM.dd}"
when.contains:
message: "ERROR"
- index: "samplelog2-%{[agent.version]}-%{+yyyy.MM.dd}"
when.contains:
message: "HIDDEN TEXT"
pipelines:
- pipeline: "xxxxxx"
when.contains:
message: "JSON"
- pipeline: "yyyyy"
when.contains:
message: "ERROR"
- pipeline: "zzzzzzz"
when.contains:
message: "HIDDEN TEXT:"
# Enabled ilm (beta) to use index lifecycle management instead daily indices.
#ilm.enabled: false
# Optional protocol and basic auth credentials.
protocol: "https"
#username: "elastic"
#password: "changeme"
#================================ Processors =====================================
processors:
- add_host_metadata: ~
- add_cloud_metadata: ~
#================================ Logging =====================================
logging.level: debug
logging.selectors: ["*"]
#xpack.monitoring.enabled: false
#xpack.monitoring.elasticsearch: