1150 lines
41 KiB
YAML
1150 lines
41 KiB
YAML
################### Youtubebeat Configuration Example #########################
|
|
|
|
############################# Youtubebeat ######################################
|
|
|
|
youtubebeat:
|
|
# Defines how often an event is sent to the output
|
|
parallelism: 5
|
|
max_depth: 10
|
|
start_url: "https://www.youtube.com"
|
|
|
|
output.elasticsearch.index: "youtubedata"
|
|
|
|
setup.template.name: "youtubedata"
|
|
setup.template.pattern: "youtubedata*"
|
|
|
|
#================================ 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.
|
|
# If this options is not defined, the hostname is used.
|
|
#name:
|
|
|
|
# The tags of the shipper are included in their own field with each
|
|
# transaction published. Tags make it easy to group servers by different
|
|
# logical properties.
|
|
#tags: ["service-X", "web-tier"]
|
|
|
|
# Optional fields that you can specify to add additional information to the
|
|
# output. Fields can be scalar values, arrays, dictionaries, or any nested
|
|
# combination of these.
|
|
#fields:
|
|
# env: staging
|
|
|
|
# If this option is set to true, the custom fields are stored as top-level
|
|
# fields in the output document instead of being grouped under a fields
|
|
# sub-dictionary. Default is false.
|
|
#fields_under_root: false
|
|
|
|
# Internal queue configuration for buffering events to be published.
|
|
#queue:
|
|
# Queue type by name (default 'mem')
|
|
# The memory queue will present all available events (up to the outputs
|
|
# bulk_max_size) to the output, the moment the output is ready to server
|
|
# another batch of events.
|
|
#mem:
|
|
# Max number of events the queue can buffer.
|
|
#events: 4096
|
|
|
|
# Hints the minimum number of events stored in the queue,
|
|
# before providing a batch of events to the outputs.
|
|
# The default value is set to 2048.
|
|
# A value of 0 ensures events are immediately available
|
|
# to be sent to the outputs.
|
|
#flush.min_events: 2048
|
|
|
|
# Maximum duration after which events are available to the outputs,
|
|
# if the number of events stored in the queue is < min_flush_events.
|
|
#flush.timeout: 1s
|
|
|
|
# The spool queue will store events in a local spool file, before
|
|
# forwarding the events to the outputs.
|
|
#
|
|
# Beta: spooling to disk is currently a beta feature. Use with care.
|
|
#
|
|
# The spool file is a circular buffer, which blocks once the file/buffer is full.
|
|
# Events are put into a write buffer and flushed once the write buffer
|
|
# is full or the flush_timeout is triggered.
|
|
# Once ACKed by the output, events are removed immediately from the queue,
|
|
# making space for new events to be persisted.
|
|
#spool:
|
|
# The file namespace configures the file path and the file creation settings.
|
|
# Once the file exists, the `size`, `page_size` and `prealloc` settings
|
|
# will have no more effect.
|
|
#file:
|
|
# Location of spool file. The default value is ${path.data}/spool.dat.
|
|
#path: "${path.data}/spool.dat"
|
|
|
|
# Configure file permissions if file is created. The default value is 0600.
|
|
#permissions: 0600
|
|
|
|
# File size hint. The spool blocks, once this limit is reached. The default value is 100 MiB.
|
|
#size: 100MiB
|
|
|
|
# The files page size. A file is split into multiple pages of the same size. The default value is 4KiB.
|
|
#page_size: 4KiB
|
|
|
|
# If prealloc is set, the required space for the file is reserved using
|
|
# truncate. The default value is true.
|
|
#prealloc: true
|
|
|
|
# Spool writer settings
|
|
# Events are serialized into a write buffer. The write buffer is flushed if:
|
|
# - The buffer limit has been reached.
|
|
# - The configured limit of buffered events is reached.
|
|
# - The flush timeout is triggered.
|
|
#write:
|
|
# Sets the write buffer size.
|
|
#buffer_size: 1MiB
|
|
|
|
# Maximum duration after which events are flushed, if the write buffer
|
|
# is not full yet. The default value is 1s.
|
|
#flush.timeout: 1s
|
|
|
|
# Number of maximum buffered events. The write buffer is flushed once the
|
|
# limit is reached.
|
|
#flush.events: 16384
|
|
|
|
# Configure the on-disk event encoding. The encoding can be changed
|
|
# between restarts.
|
|
# Valid encodings are: json, ubjson, and cbor.
|
|
#codec: cbor
|
|
#read:
|
|
# Reader flush timeout, waiting for more events to become available, so
|
|
# to fill a complete batch, as required by the outputs.
|
|
# If flush_timeout is 0, all available events are forwarded to the
|
|
# outputs immediately.
|
|
# The default value is 0s.
|
|
#flush.timeout: 0s
|
|
|
|
# Sets the maximum number of CPUs that can be executing simultaneously. The
|
|
# default is the number of logical CPUs available in the system.
|
|
#max_procs:
|
|
|
|
#================================ Processors ===================================
|
|
|
|
# Processors are used to reduce the number of fields in the exported event or to
|
|
# enhance the event with external metadata. This section defines a list of
|
|
# processors that are applied one by one and the first one receives the initial
|
|
# event:
|
|
#
|
|
# event -> filter1 -> event1 -> filter2 ->event2 ...
|
|
#
|
|
# The supported processors are drop_fields, drop_event, include_fields,
|
|
# decode_json_fields, and add_cloud_metadata.
|
|
#
|
|
# For example, you can use the following processors to keep the fields that
|
|
# contain CPU load percentages, but remove the fields that contain CPU ticks
|
|
# values:
|
|
#
|
|
#processors:
|
|
#- include_fields:
|
|
# fields: ["cpu"]
|
|
#- drop_fields:
|
|
# fields: ["cpu.user", "cpu.system"]
|
|
#
|
|
# The following example drops the events that have the HTTP response code 200:
|
|
#
|
|
#processors:
|
|
#- drop_event:
|
|
# when:
|
|
# equals:
|
|
# http.code: 200
|
|
#
|
|
# The following example renames the field a to b:
|
|
#
|
|
#processors:
|
|
#- rename:
|
|
# fields:
|
|
# - from: "a"
|
|
# to: "b"
|
|
#
|
|
# The following example tokenizes the string into fields:
|
|
#
|
|
#processors:
|
|
#- dissect:
|
|
# tokenizer: "%{key1} - %{key2}"
|
|
# field: "message"
|
|
# target_prefix: "dissect"
|
|
#
|
|
# The following example enriches each event with metadata from the cloud
|
|
# provider about the host machine. It works on EC2, GCE, DigitalOcean,
|
|
# Tencent Cloud, and Alibaba Cloud.
|
|
#
|
|
#processors:
|
|
#- add_cloud_metadata: ~
|
|
#
|
|
# The following example enriches each event with the machine's local time zone
|
|
# offset from UTC.
|
|
#
|
|
#processors:
|
|
#- add_locale:
|
|
# format: offset
|
|
#
|
|
# The following example enriches each event with docker metadata, it matches
|
|
# given fields to an existing container id and adds info from that container:
|
|
#
|
|
#processors:
|
|
#- add_docker_metadata:
|
|
# host: "unix:///var/run/docker.sock"
|
|
# match_fields: ["system.process.cgroup.id"]
|
|
# match_pids: ["process.pid", "process.ppid"]
|
|
# match_source: true
|
|
# match_source_index: 4
|
|
# match_short_id: false
|
|
# cleanup_timeout: 60
|
|
# # To connect to Docker over TLS you must specify a client and CA certificate.
|
|
# #ssl:
|
|
# # certificate_authority: "/etc/pki/root/ca.pem"
|
|
# # certificate: "/etc/pki/client/cert.pem"
|
|
# # key: "/etc/pki/client/cert.key"
|
|
#
|
|
# The following example enriches each event with docker metadata, it matches
|
|
# container id from log path available in `source` field (by default it expects
|
|
# it to be /var/lib/docker/containers/*/*.log).
|
|
#
|
|
#processors:
|
|
#- add_docker_metadata: ~
|
|
#
|
|
# The following example enriches each event with host metadata.
|
|
#
|
|
#processors:
|
|
#- add_host_metadata:
|
|
# netinfo.enabled: false
|
|
#
|
|
# The following example enriches each event with process metadata using
|
|
# process IDs included in the event.
|
|
#
|
|
#processors:
|
|
#- add_process_metadata:
|
|
# match_pids: ["system.process.ppid"]
|
|
# target: system.process.parent
|
|
#
|
|
# The following example decodes fields containing JSON strings
|
|
# and replaces the strings with valid JSON objects.
|
|
#
|
|
#processors:
|
|
#- decode_json_fields:
|
|
# fields: ["field1", "field2", ...]
|
|
# process_array: false
|
|
# max_depth: 1
|
|
# target: ""
|
|
# overwrite_keys: false
|
|
|
|
#============================= Elastic Cloud ==================================
|
|
|
|
# These settings simplify using youtubebeat 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:
|
|
# Boolean flag to enable or disable the output module.
|
|
#enabled: true
|
|
|
|
# Array of hosts to connect to.
|
|
# Scheme and port can be left out and will be set to the default (http and 9200)
|
|
# In case you specify and additional path, the scheme is required: http://localhost:9200/path
|
|
# IPv6 addresses should always be defined as: https://[2001:db8::1]:9200
|
|
hosts: ["localhost:9200"]
|
|
|
|
# Set gzip compression level.
|
|
#compression_level: 0
|
|
|
|
# Configure escaping html symbols in strings.
|
|
#escape_html: true
|
|
|
|
# Optional protocol and basic auth credentials.
|
|
#protocol: "https"
|
|
#username: "elastic"
|
|
#password: "changeme"
|
|
|
|
# Dictionary of HTTP parameters to pass within the url with index operations.
|
|
#parameters:
|
|
#param1: value1
|
|
#param2: value2
|
|
|
|
# Number of workers per Elasticsearch host.
|
|
#worker: 1
|
|
|
|
# Optional index name. The default is "youtubebeat" plus date
|
|
# and generates [youtubebeat-]YYYY.MM.DD keys.
|
|
# In case you modify this pattern you must update setup.template.name and setup.template.pattern accordingly.
|
|
#index: "youtubebeat-%{[beat.version]}-%{+yyyy.MM.dd}"
|
|
|
|
# Optional ingest node pipeline. By default no pipeline will be used.
|
|
#pipeline: ""
|
|
|
|
# Optional HTTP Path
|
|
#path: "/elasticsearch"
|
|
|
|
# Custom HTTP headers to add to each request
|
|
#headers:
|
|
# X-My-Header: Contents of the header
|
|
|
|
# Proxy server url
|
|
#proxy_url: http://proxy:3128
|
|
|
|
# The number of times a particular Elasticsearch index operation is attempted. If
|
|
# the indexing operation doesn't succeed after this many retries, the events are
|
|
# dropped. The default is 3.
|
|
#max_retries: 3
|
|
|
|
# The maximum number of events to bulk in a single Elasticsearch bulk API index request.
|
|
# The default is 50.
|
|
#bulk_max_size: 50
|
|
|
|
# The number of seconds to wait before trying to reconnect to Elasticsearch
|
|
# after a network error. After waiting backoff.init seconds, the Beat
|
|
# tries to reconnect. If the attempt fails, the backoff timer is increased
|
|
# exponentially up to backoff.max. After a successful connection, the backoff
|
|
# timer is reset. The default is 1s.
|
|
#backoff.init: 1s
|
|
|
|
# The maximum number of seconds to wait before attempting to connect to
|
|
# Elasticsearch after a network error. The default is 60s.
|
|
#backoff.max: 60s
|
|
|
|
# Configure http request timeout before failing a request to Elasticsearch.
|
|
#timeout: 90
|
|
|
|
# Use SSL settings for HTTPS.
|
|
#ssl.enabled: true
|
|
|
|
# Configure SSL verification mode. If `none` is configured, all server hosts
|
|
# and certificates will be accepted. In this mode, SSL based connections are
|
|
# susceptible to man-in-the-middle attacks. Use only for testing. Default is
|
|
# `full`.
|
|
#ssl.verification_mode: full
|
|
|
|
# List of supported/valid TLS versions. By default all TLS versions 1.0 up to
|
|
# 1.2 are enabled.
|
|
#ssl.supported_protocols: [TLSv1.0, TLSv1.1, TLSv1.2]
|
|
|
|
# SSL configuration. 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"
|
|
|
|
# Optional passphrase for decrypting the Certificate Key.
|
|
#ssl.key_passphrase: ''
|
|
|
|
# Configure cipher suites to be used for SSL connections
|
|
#ssl.cipher_suites: []
|
|
|
|
# Configure curve types for ECDHE based cipher suites
|
|
#ssl.curve_types: []
|
|
|
|
# Configure what types of renegotiation are supported. Valid options are
|
|
# never, once, and freely. Default is never.
|
|
#ssl.renegotiation: never
|
|
|
|
|
|
#----------------------------- Logstash output ---------------------------------
|
|
#output.logstash:
|
|
# Boolean flag to enable or disable the output module.
|
|
#enabled: true
|
|
|
|
# The Logstash hosts
|
|
#hosts: ["localhost:5044"]
|
|
|
|
# Number of workers per Logstash host.
|
|
#worker: 1
|
|
|
|
# Set gzip compression level.
|
|
#compression_level: 3
|
|
|
|
# Configure escaping html symbols in strings.
|
|
#escape_html: true
|
|
|
|
# Optional maximum time to live for a connection to Logstash, after which the
|
|
# connection will be re-established. A value of `0s` (the default) will
|
|
# disable this feature.
|
|
#
|
|
# Not yet supported for async connections (i.e. with the "pipelining" option set)
|
|
#ttl: 30s
|
|
|
|
# Optional load balance the events between the Logstash hosts. Default is false.
|
|
#loadbalance: false
|
|
|
|
# Number of batches to be sent asynchronously to Logstash while processing
|
|
# new batches.
|
|
#pipelining: 2
|
|
|
|
# If enabled only a subset of events in a batch of events is transferred per
|
|
# transaction. The number of events to be sent increases up to `bulk_max_size`
|
|
# if no error is encountered.
|
|
#slow_start: false
|
|
|
|
# The number of seconds to wait before trying to reconnect to Logstash
|
|
# after a network error. After waiting backoff.init seconds, the Beat
|
|
# tries to reconnect. If the attempt fails, the backoff timer is increased
|
|
# exponentially up to backoff.max. After a successful connection, the backoff
|
|
# timer is reset. The default is 1s.
|
|
#backoff.init: 1s
|
|
|
|
# The maximum number of seconds to wait before attempting to connect to
|
|
# Logstash after a network error. The default is 60s.
|
|
#backoff.max: 60s
|
|
|
|
# Optional index name. The default index name is set to youtubebeat
|
|
# in all lowercase.
|
|
#index: 'youtubebeat'
|
|
|
|
# SOCKS5 proxy server URL
|
|
#proxy_url: socks5://user:password@socks5-server:2233
|
|
|
|
# Resolve names locally when using a proxy server. Defaults to false.
|
|
#proxy_use_local_resolver: false
|
|
|
|
# Enable SSL support. SSL is automatically enabled, if any SSL setting is set.
|
|
#ssl.enabled: true
|
|
|
|
# Configure SSL verification mode. If `none` is configured, all server hosts
|
|
# and certificates will be accepted. In this mode, SSL based connections are
|
|
# susceptible to man-in-the-middle attacks. Use only for testing. Default is
|
|
# `full`.
|
|
#ssl.verification_mode: full
|
|
|
|
# List of supported/valid TLS versions. By default all TLS versions 1.0 up to
|
|
# 1.2 are enabled.
|
|
#ssl.supported_protocols: [TLSv1.0, TLSv1.1, TLSv1.2]
|
|
|
|
# Optional SSL configuration options. SSL is off by default.
|
|
# 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"
|
|
|
|
# Optional passphrase for decrypting the Certificate Key.
|
|
#ssl.key_passphrase: ''
|
|
|
|
# Configure cipher suites to be used for SSL connections
|
|
#ssl.cipher_suites: []
|
|
|
|
# Configure curve types for ECDHE based cipher suites
|
|
#ssl.curve_types: []
|
|
|
|
# Configure what types of renegotiation are supported. Valid options are
|
|
# never, once, and freely. Default is never.
|
|
#ssl.renegotiation: never
|
|
|
|
# The number of times to retry publishing an event after a publishing failure.
|
|
# After the specified number of retries, the events are typically dropped.
|
|
# Some Beats, such as Filebeat and Winlogbeat, ignore the max_retries setting
|
|
# and retry until all events are published. Set max_retries to a value less
|
|
# than 0 to retry until all events are published. The default is 3.
|
|
#max_retries: 3
|
|
|
|
# The maximum number of events to bulk in a single Logstash request. The
|
|
# default is 2048.
|
|
#bulk_max_size: 2048
|
|
|
|
# The number of seconds to wait for responses from the Logstash server before
|
|
# timing out. The default is 30s.
|
|
#timeout: 30s
|
|
|
|
#------------------------------- Kafka output ----------------------------------
|
|
#output.kafka:
|
|
# Boolean flag to enable or disable the output module.
|
|
#enabled: true
|
|
|
|
# The list of Kafka broker addresses from where to fetch the cluster metadata.
|
|
# The cluster metadata contain the actual Kafka brokers events are published
|
|
# to.
|
|
#hosts: ["localhost:9092"]
|
|
|
|
# The Kafka topic used for produced events. The setting can be a format string
|
|
# using any event field. To set the topic from document type use `%{[type]}`.
|
|
#topic: beats
|
|
|
|
# The Kafka event key setting. Use format string to create unique event key.
|
|
# By default no event key will be generated.
|
|
#key: ''
|
|
|
|
# The Kafka event partitioning strategy. Default hashing strategy is `hash`
|
|
# using the `output.kafka.key` setting or randomly distributes events if
|
|
# `output.kafka.key` is not configured.
|
|
#partition.hash:
|
|
# If enabled, events will only be published to partitions with reachable
|
|
# leaders. Default is false.
|
|
#reachable_only: false
|
|
|
|
# Configure alternative event field names used to compute the hash value.
|
|
# If empty `output.kafka.key` setting will be used.
|
|
# Default value is empty list.
|
|
#hash: []
|
|
|
|
# Authentication details. Password is required if username is set.
|
|
#username: ''
|
|
#password: ''
|
|
|
|
# Kafka version youtubebeat is assumed to run against. Defaults to the "1.0.0".
|
|
#version: '1.0.0'
|
|
|
|
# Configure JSON encoding
|
|
#codec.json:
|
|
# Pretty print json event
|
|
#pretty: false
|
|
|
|
# Configure escaping html symbols in strings.
|
|
#escape_html: true
|
|
|
|
# Metadata update configuration. Metadata do contain leader information
|
|
# deciding which broker to use when publishing.
|
|
#metadata:
|
|
# Max metadata request retry attempts when cluster is in middle of leader
|
|
# election. Defaults to 3 retries.
|
|
#retry.max: 3
|
|
|
|
# Waiting time between retries during leader elections. Default is 250ms.
|
|
#retry.backoff: 250ms
|
|
|
|
# Refresh metadata interval. Defaults to every 10 minutes.
|
|
#refresh_frequency: 10m
|
|
|
|
# The number of concurrent load-balanced Kafka output workers.
|
|
#worker: 1
|
|
|
|
# The number of times to retry publishing an event after a publishing failure.
|
|
# After the specified number of retries, the events are typically dropped.
|
|
# Some Beats, such as Filebeat, ignore the max_retries setting and retry until
|
|
# all events are published. Set max_retries to a value less than 0 to retry
|
|
# until all events are published. The default is 3.
|
|
#max_retries: 3
|
|
|
|
# The maximum number of events to bulk in a single Kafka request. The default
|
|
# is 2048.
|
|
#bulk_max_size: 2048
|
|
|
|
# The number of seconds to wait for responses from the Kafka brokers before
|
|
# timing out. The default is 30s.
|
|
#timeout: 30s
|
|
|
|
# The maximum duration a broker will wait for number of required ACKs. The
|
|
# default is 10s.
|
|
#broker_timeout: 10s
|
|
|
|
# The number of messages buffered for each Kafka broker. The default is 256.
|
|
#channel_buffer_size: 256
|
|
|
|
# The keep-alive period for an active network connection. If 0s, keep-alives
|
|
# are disabled. The default is 0 seconds.
|
|
#keep_alive: 0
|
|
|
|
# Sets the output compression codec. Must be one of none, snappy and gzip. The
|
|
# default is gzip.
|
|
#compression: gzip
|
|
|
|
# Set the compression level. Currently only gzip provides a compression level
|
|
# between 0 and 9. The default value is chosen by the compression algorithm.
|
|
#compression_level: 4
|
|
|
|
# The maximum permitted size of JSON-encoded messages. Bigger messages will be
|
|
# dropped. The default value is 1000000 (bytes). This value should be equal to
|
|
# or less than the broker's message.max.bytes.
|
|
#max_message_bytes: 1000000
|
|
|
|
# The ACK reliability level required from broker. 0=no response, 1=wait for
|
|
# local commit, -1=wait for all replicas to commit. The default is 1. Note:
|
|
# If set to 0, no ACKs are returned by Kafka. Messages might be lost silently
|
|
# on error.
|
|
#required_acks: 1
|
|
|
|
# The configurable ClientID used for logging, debugging, and auditing
|
|
# purposes. The default is "beats".
|
|
#client_id: beats
|
|
|
|
# Enable SSL support. SSL is automatically enabled, if any SSL setting is set.
|
|
#ssl.enabled: true
|
|
|
|
# Optional SSL configuration options. SSL is off by default.
|
|
# List of root certificates for HTTPS server verifications
|
|
#ssl.certificate_authorities: ["/etc/pki/root/ca.pem"]
|
|
|
|
# Configure SSL verification mode. If `none` is configured, all server hosts
|
|
# and certificates will be accepted. In this mode, SSL based connections are
|
|
# susceptible to man-in-the-middle attacks. Use only for testing. Default is
|
|
# `full`.
|
|
#ssl.verification_mode: full
|
|
|
|
# List of supported/valid TLS versions. By default all TLS versions 1.0 up to
|
|
# 1.2 are enabled.
|
|
#ssl.supported_protocols: [TLSv1.0, TLSv1.1, TLSv1.2]
|
|
|
|
# Certificate for SSL client authentication
|
|
#ssl.certificate: "/etc/pki/client/cert.pem"
|
|
|
|
# Client Certificate Key
|
|
#ssl.key: "/etc/pki/client/cert.key"
|
|
|
|
# Optional passphrase for decrypting the Certificate Key.
|
|
#ssl.key_passphrase: ''
|
|
|
|
# Configure cipher suites to be used for SSL connections
|
|
#ssl.cipher_suites: []
|
|
|
|
# Configure curve types for ECDHE based cipher suites
|
|
#ssl.curve_types: []
|
|
|
|
# Configure what types of renegotiation are supported. Valid options are
|
|
# never, once, and freely. Default is never.
|
|
#ssl.renegotiation: never
|
|
|
|
#------------------------------- Redis output ----------------------------------
|
|
#output.redis:
|
|
# Boolean flag to enable or disable the output module.
|
|
#enabled: true
|
|
|
|
# Configure JSON encoding
|
|
#codec.json:
|
|
# Pretty print json event
|
|
#pretty: false
|
|
|
|
# Configure escaping html symbols in strings.
|
|
#escape_html: true
|
|
|
|
# The list of Redis servers to connect to. If load balancing is enabled, the
|
|
# events are distributed to the servers in the list. If one server becomes
|
|
# unreachable, the events are distributed to the reachable servers only.
|
|
#hosts: ["localhost:6379"]
|
|
|
|
# The Redis port to use if hosts does not contain a port number. The default
|
|
# is 6379.
|
|
#port: 6379
|
|
|
|
# The name of the Redis list or channel the events are published to. The
|
|
# default is youtubebeat.
|
|
#key: youtubebeat
|
|
|
|
# The password to authenticate with. The default is no authentication.
|
|
#password:
|
|
|
|
# The Redis database number where the events are published. The default is 0.
|
|
#db: 0
|
|
|
|
# The Redis data type to use for publishing events. If the data type is list,
|
|
# the Redis RPUSH command is used. If the data type is channel, the Redis
|
|
# PUBLISH command is used. The default value is list.
|
|
#datatype: list
|
|
|
|
# The number of workers to use for each host configured to publish events to
|
|
# Redis. Use this setting along with the loadbalance option. For example, if
|
|
# you have 2 hosts and 3 workers, in total 6 workers are started (3 for each
|
|
# host).
|
|
#worker: 1
|
|
|
|
# If set to true and multiple hosts or workers are configured, the output
|
|
# plugin load balances published events onto all Redis hosts. If set to false,
|
|
# the output plugin sends all events to only one host (determined at random)
|
|
# and will switch to another host if the currently selected one becomes
|
|
# unreachable. The default value is true.
|
|
#loadbalance: true
|
|
|
|
# The Redis connection timeout in seconds. The default is 5 seconds.
|
|
#timeout: 5s
|
|
|
|
# The number of times to retry publishing an event after a publishing failure.
|
|
# After the specified number of retries, the events are typically dropped.
|
|
# Some Beats, such as Filebeat, ignore the max_retries setting and retry until
|
|
# all events are published. Set max_retries to a value less than 0 to retry
|
|
# until all events are published. The default is 3.
|
|
#max_retries: 3
|
|
|
|
# The number of seconds to wait before trying to reconnect to Redis
|
|
# after a network error. After waiting backoff.init seconds, the Beat
|
|
# tries to reconnect. If the attempt fails, the backoff timer is increased
|
|
# exponentially up to backoff.max. After a successful connection, the backoff
|
|
# timer is reset. The default is 1s.
|
|
#backoff.init: 1s
|
|
|
|
# The maximum number of seconds to wait before attempting to connect to
|
|
# Redis after a network error. The default is 60s.
|
|
#backoff.max: 60s
|
|
|
|
# The maximum number of events to bulk in a single Redis request or pipeline.
|
|
# The default is 2048.
|
|
#bulk_max_size: 2048
|
|
|
|
# The URL of the SOCKS5 proxy to use when connecting to the Redis servers. The
|
|
# value must be a URL with a scheme of socks5://.
|
|
#proxy_url:
|
|
|
|
# This option determines whether Redis hostnames are resolved locally when
|
|
# using a proxy. The default value is false, which means that name resolution
|
|
# occurs on the proxy server.
|
|
#proxy_use_local_resolver: false
|
|
|
|
# Enable SSL support. SSL is automatically enabled, if any SSL setting is set.
|
|
#ssl.enabled: true
|
|
|
|
# Configure SSL verification mode. If `none` is configured, all server hosts
|
|
# and certificates will be accepted. In this mode, SSL based connections are
|
|
# susceptible to man-in-the-middle attacks. Use only for testing. Default is
|
|
# `full`.
|
|
#ssl.verification_mode: full
|
|
|
|
# List of supported/valid TLS versions. By default all TLS versions 1.0 up to
|
|
# 1.2 are enabled.
|
|
#ssl.supported_protocols: [TLSv1.0, TLSv1.1, TLSv1.2]
|
|
|
|
# Optional SSL configuration options. SSL is off by default.
|
|
# 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"
|
|
|
|
# Optional passphrase for decrypting the Certificate Key.
|
|
#ssl.key_passphrase: ''
|
|
|
|
# Configure cipher suites to be used for SSL connections
|
|
#ssl.cipher_suites: []
|
|
|
|
# Configure curve types for ECDHE based cipher suites
|
|
#ssl.curve_types: []
|
|
|
|
# Configure what types of renegotiation are supported. Valid options are
|
|
# never, once, and freely. Default is never.
|
|
#ssl.renegotiation: never
|
|
|
|
#------------------------------- File output -----------------------------------
|
|
#output.file:
|
|
# Boolean flag to enable or disable the output module.
|
|
#enabled: true
|
|
|
|
# Configure JSON encoding
|
|
#codec.json:
|
|
# Pretty print json event
|
|
#pretty: false
|
|
|
|
# Configure escaping html symbols in strings.
|
|
#escape_html: true
|
|
|
|
# Path to the directory where to save the generated files. The option is
|
|
# mandatory.
|
|
#path: "/tmp/youtubebeat"
|
|
|
|
# Name of the generated files. The default is `youtubebeat` and it generates
|
|
# files: `youtubebeat`, `youtubebeat.1`, `youtubebeat.2`, etc.
|
|
#filename: youtubebeat
|
|
|
|
# Maximum size in kilobytes of each file. When this size is reached, and on
|
|
# every youtubebeat restart, the files are rotated. The default value is 10240
|
|
# kB.
|
|
#rotate_every_kb: 10000
|
|
|
|
# Maximum number of files under path. When this number of files is reached,
|
|
# the oldest file is deleted and the rest are shifted from last to first. The
|
|
# default is 7 files.
|
|
#number_of_files: 7
|
|
|
|
# Permissions to use for file creation. The default is 0600.
|
|
#permissions: 0600
|
|
|
|
|
|
#----------------------------- Console output ---------------------------------
|
|
#output.console:
|
|
# Boolean flag to enable or disable the output module.
|
|
#enabled: true
|
|
|
|
# Configure JSON encoding
|
|
#codec.json:
|
|
# Pretty print json event
|
|
#pretty: false
|
|
|
|
# Configure escaping html symbols in strings.
|
|
#escape_html: true
|
|
|
|
#================================= Paths ======================================
|
|
|
|
# The home path for the youtubebeat installation. This is the default base path
|
|
# for all other path settings and for miscellaneous files that come with the
|
|
# distribution (for example, the sample dashboards).
|
|
# If not set by a CLI flag or in the configuration file, the default for the
|
|
# home path is the location of the binary.
|
|
#path.home:
|
|
|
|
# The configuration path for the youtubebeat installation. This is the default
|
|
# base path for configuration files, including the main YAML configuration file
|
|
# and the Elasticsearch template file. If not set by a CLI flag or in the
|
|
# configuration file, the default for the configuration path is the home path.
|
|
#path.config: ${path.home}
|
|
|
|
# The data path for the youtubebeat installation. This is the default base path
|
|
# for all the files in which youtubebeat needs to store its data. If not set by a
|
|
# CLI flag or in the configuration file, the default for the data path is a data
|
|
# subdirectory inside the home path.
|
|
#path.data: ${path.home}/data
|
|
|
|
# The logs path for a youtubebeat installation. This is the default location for
|
|
# the Beat's log files. If not set by a CLI flag or in the configuration file,
|
|
# the default for the logs path is a logs subdirectory inside the home path.
|
|
#path.logs: ${path.home}/logs
|
|
|
|
#================================ Keystore ==========================================
|
|
# Location of the Keystore containing the keys and their sensitive values.
|
|
#keystore.path: "${path.config}/beats.keystore"
|
|
|
|
#============================== Dashboards =====================================
|
|
# These settings control loading the sample dashboards to the Kibana index. Loading
|
|
# the dashboards are 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 directory from where to read the dashboards. The default is the `kibana`
|
|
# folder in the home path.
|
|
#setup.dashboards.directory: ${path.home}/kibana
|
|
|
|
# The URL from where to download the dashboards archive. It is used instead of
|
|
# the directory if it has a value.
|
|
#setup.dashboards.url:
|
|
|
|
# The file archive (zip file) from where to read the dashboards. It is used instead
|
|
# of the directory when it has a value.
|
|
#setup.dashboards.file:
|
|
|
|
# In case the archive contains the dashboards from multiple Beats, this lets you
|
|
# select which one to load. You can load all the dashboards in the archive by
|
|
# setting this to the empty string.
|
|
#setup.dashboards.beat: youtubebeat
|
|
|
|
# The name of the Kibana index to use for setting the configuration. Default is ".kibana"
|
|
#setup.dashboards.kibana_index: .kibana
|
|
|
|
# The Elasticsearch index name. This overwrites the index name defined in the
|
|
# dashboards and index pattern. Example: testbeat-*
|
|
#setup.dashboards.index:
|
|
|
|
# Always use the Kibana API for loading the dashboards instead of autodetecting
|
|
# how to install the dashboards by first querying Elasticsearch.
|
|
#setup.dashboards.always_kibana: false
|
|
|
|
# If true and Kibana is not reachable at the time when dashboards are loaded,
|
|
# it will retry to reconnect to Kibana instead of exiting with an error.
|
|
#setup.dashboards.retry.enabled: false
|
|
|
|
# Duration interval between Kibana connection retries.
|
|
#setup.dashboards.retry.interval: 1s
|
|
|
|
# Maximum number of retries before exiting with an error, 0 for unlimited retrying.
|
|
#setup.dashboards.retry.maximum: 0
|
|
|
|
|
|
#============================== Template =====================================
|
|
|
|
# A template is used to set the mapping in Elasticsearch
|
|
# By default template loading is enabled and the template is loaded.
|
|
# These settings can be adjusted to load your own template or overwrite existing ones.
|
|
|
|
# Set to false to disable template loading.
|
|
#setup.template.enabled: true
|
|
|
|
# Template name. By default the template name is "youtubebeat-%{[beat.version]}"
|
|
# The template name and pattern has to be set in case the elasticsearch index pattern is modified.
|
|
#setup.template.name: "youtubebeat-%{[beat.version]}"
|
|
|
|
# Template pattern. By default the template pattern is "-%{[beat.version]}-*" to apply to the default index settings.
|
|
# The first part is the version of the beat and then -* is used to match all daily indices.
|
|
# The template name and pattern has to be set in case the elasticsearch index pattern is modified.
|
|
#setup.template.pattern: "youtubebeat-%{[beat.version]}-*"
|
|
|
|
# Path to fields.yml file to generate the template
|
|
#setup.template.fields: "${path.config}/fields.yml"
|
|
|
|
# A list of fields to be added to the template and Kibana index pattern. Also
|
|
# specify setup.template.overwrite: true to overwrite the existing template.
|
|
# This setting is experimental.
|
|
#setup.template.append_fields:
|
|
#- name: field_name
|
|
# type: field_type
|
|
|
|
# Enable json template loading. If this is enabled, the fields.yml is ignored.
|
|
#setup.template.json.enabled: false
|
|
|
|
# Path to the json template file
|
|
#setup.template.json.path: "${path.config}/template.json"
|
|
|
|
# Name under which the template is stored in Elasticsearch
|
|
#setup.template.json.name: ""
|
|
|
|
# Overwrite existing template
|
|
#setup.template.overwrite: false
|
|
|
|
# Elasticsearch template settings
|
|
setup.template.settings:
|
|
|
|
# A dictionary of settings to place into the settings.index dictionary
|
|
# of the Elasticsearch template. For more details, please check
|
|
# https://www.elastic.co/guide/en/elasticsearch/reference/current/mapping.html
|
|
#index:
|
|
#number_of_shards: 1
|
|
#codec: best_compression
|
|
#number_of_routing_shards: 30
|
|
|
|
# A dictionary of settings for the _source field. For more details, please check
|
|
# https://www.elastic.co/guide/en/elasticsearch/reference/current/mapping-source-field.html
|
|
#_source:
|
|
#enabled: 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
|
|
#host: "localhost:5601"
|
|
|
|
# Optional protocol and basic auth credentials.
|
|
#protocol: "https"
|
|
#username: "elastic"
|
|
#password: "changeme"
|
|
|
|
# Optional HTTP Path
|
|
#path: ""
|
|
|
|
# Use SSL settings for HTTPS. Default is true.
|
|
#ssl.enabled: true
|
|
|
|
# Configure SSL verification mode. If `none` is configured, all server hosts
|
|
# and certificates will be accepted. In this mode, SSL based connections are
|
|
# susceptible to man-in-the-middle attacks. Use only for testing. Default is
|
|
# `full`.
|
|
#ssl.verification_mode: full
|
|
|
|
# List of supported/valid TLS versions. By default all TLS versions 1.0 up to
|
|
# 1.2 are enabled.
|
|
#ssl.supported_protocols: [TLSv1.0, TLSv1.1, TLSv1.2]
|
|
|
|
# SSL configuration. 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"
|
|
|
|
# Optional passphrase for decrypting the Certificate Key.
|
|
#ssl.key_passphrase: ''
|
|
|
|
# Configure cipher suites to be used for SSL connections
|
|
#ssl.cipher_suites: []
|
|
|
|
# Configure curve types for ECDHE based cipher suites
|
|
#ssl.curve_types: []
|
|
|
|
|
|
|
|
#================================ Logging ======================================
|
|
# There are four options for the log output: file, stderr, syslog, eventlog
|
|
# The file output is the default.
|
|
|
|
# Sets log level. The default log level is info.
|
|
# Available log levels are: error, warning, info, debug
|
|
#logging.level: info
|
|
|
|
# Enable debug output for selected components. To enable all selectors use ["*"]
|
|
# Other available selectors are "beat", "publish", "service"
|
|
# Multiple selectors can be chained.
|
|
#logging.selectors: [ ]
|
|
|
|
# Send all logging output to syslog. The default is false.
|
|
#logging.to_syslog: false
|
|
|
|
# Send all logging output to Windows Event Logs. The default is false.
|
|
#logging.to_eventlog: false
|
|
|
|
# If enabled, youtubebeat periodically logs its internal metrics that have changed
|
|
# in the last period. For each metric that changed, the delta from the value at
|
|
# the beginning of the period is logged. Also, the total values for
|
|
# all non-zero internal metrics are logged on shutdown. The default is true.
|
|
#logging.metrics.enabled: true
|
|
|
|
# The period after which to log the internal metrics. The default is 30s.
|
|
#logging.metrics.period: 30s
|
|
|
|
# Logging to rotating files. Set logging.to_files to false to disable logging to
|
|
# files.
|
|
logging.to_files: true
|
|
logging.files:
|
|
# Configure the path where the logs are written. The default is the logs directory
|
|
# under the home path (the binary location).
|
|
#path: /var/log/youtubebeat
|
|
|
|
# The name of the files where the logs are written to.
|
|
#name: youtubebeat
|
|
|
|
# Configure log file size limit. If limit is reached, log file will be
|
|
# automatically rotated
|
|
#rotateeverybytes: 10485760 # = 10MB
|
|
|
|
# Number of rotated log files to keep. Oldest files will be deleted first.
|
|
#keepfiles: 7
|
|
|
|
# The permissions mask to apply when rotating log files. The default value is 0600.
|
|
# Must be a valid Unix-style file permissions mask expressed in octal notation.
|
|
#permissions: 0600
|
|
|
|
# Enable log file rotation on time intervals in addition to size-based rotation.
|
|
# Intervals must be at least 1s. Values of 1m, 1h, 24h, 7*24h, 30*24h, and 365*24h
|
|
# are boundary-aligned with minutes, hours, days, weeks, months, and years as
|
|
# reported by the local system clock. All other intervals are calculated from the
|
|
# unix epoch. Defaults to disabled.
|
|
#interval: 0
|
|
|
|
# Set to true to log messages in json format.
|
|
#logging.json: false
|
|
|
|
|
|
#============================== Xpack Monitoring =====================================
|
|
# youtubebeat 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.
|
|
#xpack.monitoring.enabled: false
|
|
|
|
# Uncomment to send the metrics to Elasticsearch. Most settings from the
|
|
# Elasticsearch output are accepted here as well. Any setting that is not set is
|
|
# automatically inherited from the Elasticsearch output configuration, so if you
|
|
# have the Elasticsearch output configured, you can simply uncomment the
|
|
# following line, and leave the rest commented out.
|
|
#xpack.monitoring.elasticsearch:
|
|
|
|
# Array of hosts to connect to.
|
|
# Scheme and port can be left out and will be set to the default (http and 9200)
|
|
# In case you specify and additional path, the scheme is required: http://localhost:9200/path
|
|
# IPv6 addresses should always be defined as: https://[2001:db8::1]:9200
|
|
#hosts: ["localhost:9200"]
|
|
|
|
# Set gzip compression level.
|
|
#compression_level: 0
|
|
|
|
# Optional protocol and basic auth credentials.
|
|
#protocol: "https"
|
|
#username: "beats_system"
|
|
#password: "changeme"
|
|
|
|
# Dictionary of HTTP parameters to pass within the url with index operations.
|
|
#parameters:
|
|
#param1: value1
|
|
#param2: value2
|
|
|
|
# Custom HTTP headers to add to each request
|
|
#headers:
|
|
# X-My-Header: Contents of the header
|
|
|
|
# Proxy server url
|
|
#proxy_url: http://proxy:3128
|
|
|
|
# The number of times a particular Elasticsearch index operation is attempted. If
|
|
# the indexing operation doesn't succeed after this many retries, the events are
|
|
# dropped. The default is 3.
|
|
#max_retries: 3
|
|
|
|
# The maximum number of events to bulk in a single Elasticsearch bulk API index request.
|
|
# The default is 50.
|
|
#bulk_max_size: 50
|
|
|
|
# The number of seconds to wait before trying to reconnect to Elasticsearch
|
|
# after a network error. After waiting backoff.init seconds, the Beat
|
|
# tries to reconnect. If the attempt fails, the backoff timer is increased
|
|
# exponentially up to backoff.max. After a successful connection, the backoff
|
|
# timer is reset. The default is 1s.
|
|
#backoff.init: 1s
|
|
|
|
# The maximum number of seconds to wait before attempting to connect to
|
|
# Elasticsearch after a network error. The default is 60s.
|
|
#backoff.max: 60s
|
|
|
|
# Configure http request timeout before failing an request to Elasticsearch.
|
|
#timeout: 90
|
|
|
|
# Use SSL settings for HTTPS.
|
|
#ssl.enabled: true
|
|
|
|
# Configure SSL verification mode. If `none` is configured, all server hosts
|
|
# and certificates will be accepted. In this mode, SSL based connections are
|
|
# susceptible to man-in-the-middle attacks. Use only for testing. Default is
|
|
# `full`.
|
|
#ssl.verification_mode: full
|
|
|
|
# List of supported/valid TLS versions. By default all TLS versions 1.0 up to
|
|
# 1.2 are enabled.
|
|
#ssl.supported_protocols: [TLSv1.0, TLSv1.1, TLSv1.2]
|
|
|
|
# SSL configuration. 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"
|
|
|
|
# Optional passphrase for decrypting the Certificate Key.
|
|
#ssl.key_passphrase: ''
|
|
|
|
# Configure cipher suites to be used for SSL connections
|
|
#ssl.cipher_suites: []
|
|
|
|
# Configure curve types for ECDHE based cipher suites
|
|
#ssl.curve_types: []
|
|
|
|
# Configure what types of renegotiation are supported. Valid options are
|
|
# never, once, and freely. Default is never.
|
|
#ssl.renegotiation: never
|
|
|
|
#metrics.period: 10s
|
|
#state.period: 1m
|
|
|
|
#================================ HTTP Endpoint ======================================
|
|
# Each beat can expose internal metrics through a HTTP endpoint. For security
|
|
# reasons the endpoint is disabled by default. This feature is currently experimental.
|
|
# Stats can be access through http://localhost:5066/stats . For pretty JSON output
|
|
# append ?pretty to the URL.
|
|
|
|
# Defines if the HTTP endpoint is enabled.
|
|
#http.enabled: false
|
|
|
|
# The HTTP endpoint will bind to this hostname or IP address. It is recommended to use only localhost.
|
|
#http.host: localhost
|
|
|
|
# Port on which the HTTP endpoint will bind. Default is 5066.
|
|
#http.port: 5066
|
|
|
|
#============================= Process Security ================================
|
|
|
|
# Enable or disable seccomp system call filtering on Linux. Default is enabled.
|
|
#seccomp.enabled: true
|