Tail 和 AWS Timestream 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.timestream]]
  ## Amazon Region
  region = "us-east-1"

  ## Amazon Credentials
  ## Credentials are loaded in the following order:
  ## 1) Web identity provider credentials via STS if role_arn and web_identity_token_file are specified
  ## 2) Assumed credentials via STS if role_arn is specified
  ## 3) explicit credentials from 'access_key' and 'secret_key'
  ## 4) shared profile from 'profile'
  ## 5) environment variables
  ## 6) shared credentials file
  ## 7) EC2 Instance Profile
  #access_key = ""
  #secret_key = ""
  #token = ""
  #role_arn = ""
  #web_identity_token_file = ""
  #role_session_name = ""
  #profile = ""
  #shared_credential_file = ""

  ## Endpoint to make request against, the correct endpoint is automatically
  ## determined and this option should only be set if you wish to override the
  ## default.
  ##   ex: endpoint_url = "http://localhost:8000"
  # endpoint_url = ""

  ## Timestream database where the metrics will be inserted.
  ## The database must exist prior to starting Telegraf.
  database_name = "yourDatabaseNameHere"

  ## Specifies if the plugin should describe the Timestream database upon starting
  ## to validate if it has access necessary permissions, connection, etc., as a safety check.
  ## If the describe operation fails, the plugin will not start
  ## and therefore the Telegraf agent will not start.
  describe_database_on_start = false

  ## Specifies how the data is organized in Timestream.
  ## Valid values are: single-table, multi-table.
  ## When mapping_mode is set to single-table, all of the data is stored in a single table.
  ## When mapping_mode is set to multi-table, the data is organized and stored in multiple tables.
  ## The default is multi-table.
  mapping_mode = "multi-table"

  ## Specifies if the plugin should create the table, if the table does not exist.
  create_table_if_not_exists = true

  ## Specifies the Timestream table magnetic store retention period in days.
  ## Check Timestream documentation for more details.
  ## NOTE: This property is valid when create_table_if_not_exists = true.
  create_table_magnetic_store_retention_period_in_days = 365

  ## Specifies the Timestream table memory store retention period in hours.
  ## Check Timestream documentation for more details.
  ## NOTE: This property is valid when create_table_if_not_exists = true.
  create_table_memory_store_retention_period_in_hours = 24

  ## Specifies how the data is written into Timestream.
  ## Valid values are: true, false
  ## When use_multi_measure_records is set to true, all of the tags and fields are stored
  ## as a single row in a Timestream table.
  ## When use_multi_measure_record is set to false, Timestream stores each field in a
  ## separate table row, thereby storing the tags multiple times (once for each field).
  ## The recommended setting is true.
  ## The default is false.
  use_multi_measure_records = "false"

  ## Specifies the measure_name to use when sending multi-measure records.
  ## NOTE: This property is valid when use_multi_measure_records=true and mapping_mode=multi-table
  measure_name_for_multi_measure_records = "telegraf_measure"

  ## Specifies the name of the table to write data into
  ## NOTE: This property is valid when mapping_mode=single-table.
  # single_table_name = ""

  ## Specifies the name of dimension when all of the data is being stored in a single table
  ## and the measurement name is transformed into the dimension value
  ## (see Mapping data from Influx to Timestream for details)
  ## NOTE: This property is valid when mapping_mode=single-table.
  # single_table_dimension_name_for_telegraf_measurement_name = "namespace"

  ## Only valid and optional if create_table_if_not_exists = true
  ## Specifies the Timestream table tags.
  ## Check Timestream documentation for more details
  # create_table_tags = { "foo" = "bar", "environment" = "dev"}

  ## Specify the maximum number of parallel go routines to ingest/write data
  ## If not specified, defaulted to 1 go routines
  max_write_go_routines = 25

  ## Please see README.md to know how line protocol data is mapped to Timestream
  ##