Tail 和 Elasticsearch 集成

[[inputs.tail]]
  ## File names or a pattern to tail.
  ## These accept standard unix glob matching rules, but with the addition of
  ## ** as a "super asterisk". ie:
  ##   "/var/log/**.log"  -> recursively find all .log files in /var/log
  ##   "/var/log/*/*.log" -> find all .log files with a parent dir in /var/log
  ##   "/var/log/apache.log" -> just tail the apache log file
  ##   "/var/log/log[!1-2]*  -> tail files without 1-2
  ##   "/var/log/log[^1-2]*  -> identical behavior as above
  ## See https://github.com/gobwas/glob for more examples
  ##
  files = ["/var/mymetrics.out"]

  ## Read file from beginning.
  # from_beginning = false

  ## Whether file is a named pipe
  # pipe = false

  ## Method used to watch for file updates.  Can be either "inotify" or "poll".
  ## inotify is supported on linux, *bsd, and macOS, while Windows requires
  ## using poll. Poll checks for changes every 250ms.
  # watch_method = "inotify"

  ## Maximum lines of the file to process that have not yet be written by the
  ## output.  For best throughput set based on the number of metrics on each
  ## line and the size of the output's metric_batch_size.
  # max_undelivered_lines = 1000

  ## Character encoding to use when interpreting the file contents.  Invalid
  ## characters are replaced using the unicode replacement character.  When set
  ## to the empty string the data is not decoded to text.
  ##   ex: character_encoding = "utf-8"
  ##       character_encoding = "utf-16le"
  ##       character_encoding = "utf-16be"
  ##       character_encoding = ""
  # character_encoding = ""

  ## Data format to consume.
  ## Each data format has its own unique set of configuration options, read
  ## more about them here:
  ## https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md
  data_format = "influx"

  ## Set the tag that will contain the path of the tailed file. If you don't want this tag, set it to an empty string.
  # path_tag = "path"

  ## Filters to apply to files before generating metrics
  ## "ansi_color" removes ANSI colors
  # filters = []

  ## multiline parser/codec
  ## https://elastic.ac.cn/guide/en/logstash/2.4/plugins-filters-multiline.html
  #[inputs.tail.multiline]
    ## The pattern should be a regexp which matches what you believe to be an indicator that the field is part of an event consisting of multiple lines of log data.
    #pattern = "^\s"

    ## The field's value must be previous or next and indicates the relation to the
    ## multi-line event.
    #match_which_line = "previous"

    ## The invert_match can be true or false (defaults to false).
    ## If true, a message not matching the pattern will constitute a match of the multiline filter and the what will be applied. (vice-versa is also true)
    #invert_match = false

    ## The handling method for quoted text (defaults to 'ignore').
    ## The following methods are available:
    ##   ignore  -- do not consider quotation (default)
    ##   single-quotes -- consider text quoted by single quotes (')
    ##   double-quotes -- consider text quoted by double quotes (")
    ##   backticks     -- consider text quoted by backticks (`)
    ## When handling quotes, escaped quotes (e.g. \") are handled correctly.
    #quotation = "ignore"

    ## The preserve_newline option can be true or false (defaults to false).
    ## If true, the newline character is preserved for multiline elements,
    ## this is useful to preserve message-structure e.g. for logging outputs.
    #preserve_newline = false

    #After the specified timeout, this plugin sends the multiline event even if no new pattern is found to start a new event. The default is 5s.
    #timeout = 5s

[[outputs.elasticsearch]]
  ## The full HTTP endpoint URL for your Elasticsearch instance
  ## Multiple urls can be specified as part of the same cluster,
  ## this means that only ONE of the urls will be written to each interval
  urls = [ "http://node1.es.example.com:9200" ] # required.
  ## Elasticsearch client timeout, defaults to "5s" if not set.
  timeout = "5s"
  ## Set to true to ask Elasticsearch a list of all cluster nodes,
  ## thus it is not necessary to list all nodes in the urls config option
  enable_sniffer = false
  ## Set to true to enable gzip compression
  enable_gzip = false
  ## Set the interval to check if the Elasticsearch nodes are available
  ## Setting to "0s" will disable the health check (not recommended in production)
  health_check_interval = "10s"
  ## Set the timeout for periodic health checks.
  # health_check_timeout = "1s"
  ## HTTP basic authentication details.
  ## HTTP basic authentication details
  # username = "telegraf"
  # password = "mypassword"
  ## HTTP bearer token authentication details
  # auth_bearer_token = "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9"

  ## Index Config
  ## The target index for metrics (Elasticsearch will create if it not exists).
  ## You can use the date specifiers below to create indexes per time frame.
  ## The metric timestamp will be used to decide the destination index name
  # %Y - year (2016)
  # %y - last two digits of year (00..99)
  # %m - month (01..12)
  # %d - day of month (e.g., 01)
  # %H - hour (00..23)
  # %V - week of the year (ISO week) (01..53)
  ## Additionally, you can specify a tag name using the notation {{tag_name}}
  ## which will be used as part of the index name. If the tag does not exist,
  ## the default tag value will be used.
  # index_name = "telegraf-{{host}}-%Y.%m.%d"
  # default_tag_value = "none"
  index_name = "telegraf-%Y.%m.%d" # required.

  ## Optional Index Config
  ## Set to true if Telegraf should use the "create" OpType while indexing
  # use_optype_create = false

  ## Optional TLS Config
  # tls_ca = "/etc/telegraf/ca.pem"
  # tls_cert = "/etc/telegraf/cert.pem"
  # tls_key = "/etc/telegraf/key.pem"
  ## Use TLS but skip chain & host verification
  # insecure_skip_verify = false

  ## Template Config
  ## Set to true if you want telegraf to manage its index template.
  ## If enabled it will create a recommended index template for telegraf indexes
  manage_template = true
  ## The template name used for telegraf indexes
  template_name = "telegraf"
  ## Set to true if you want telegraf to overwrite an existing template
  overwrite_template = false
  ## If set to true a unique ID hash will be sent as sha256(concat(timestamp,measurement,series-hash)) string
  ## it will enable data resend and update metric points avoiding duplicated metrics with different id's
  force_document_id = false

  ## Specifies the handling of NaN and Inf values.
  ## This option can have the following values:
  ##    none    -- do not modify field-values (default); will produce an error if NaNs or infs are encountered
  ##    drop    -- drop fields containing NaNs or infs
  ##    replace -- replace with the value in "float_replacement_value" (default: 0.0)
  ##               NaNs and inf will be replaced with the given number, -inf with the negative of that number
  # float_handling = "none"
  # float_replacement_value = 0.0

  ## Pipeline Config
  ## To use a ingest pipeline, set this to the name of the pipeline you want to use.
  # use_pipeline = "my_pipeline"
  ## Additionally, you can specify a tag name using the notation {{tag_name}}
  ## which will be used as part of the pipeline name. If the tag does not exist,
  ## the default pipeline will be used as the pipeline. If no default pipeline is set,
  ## no pipeline is used for the metric.
  # use_pipeline = "{{es_pipeline}}"
  # default_pipeline = "my_pipeline"
  #
  # Custom HTTP headers
  # To pass custom HTTP headers please define it in a given below section
  # [outputs.elasticsearch.headers]
  #    "X-Custom-Header" = "custom-value"

  ## Template Index Settings
  ## Overrides the template settings.index section with any provided options.
  ## Defaults provided here in the config
  # template_index_settings = {
  #   refresh_interval = "10s",
  #   mapping.total_fields.limit = 5000,
  #   auto_expand_replicas = "0-1",
  #   codec = "best_compression"
  # }