Kafka 和 Elasticsearch 集成

[[inputs.kafka_consumer]]
              ## Kafka brokers.
              brokers = ["localhost:9092"]

              ## Set the minimal supported Kafka version. Should be a string contains
              ## 4 digits in case if it is 0 version and 3 digits for versions starting
              ## from 1.0.0 separated by dot. This setting enables the use of new
              ## Kafka features and APIs.  Must be 0.10.2.0(used as default) or greater.
              ## Please, check the list of supported versions at
              ## https://pkg.go.dev/github.com/Shopify/sarama#SupportedVersions
              ##   ex: kafka_version = "2.6.0"
              ##   ex: kafka_version = "0.10.2.0"
              # kafka_version = "0.10.2.0"

              ## Topics to consume.
              topics = ["telegraf"]

              ## Topic regular expressions to consume.  Matches will be added to topics.
              ## Example: topic_regexps = [ "*test", "metric[0-9A-z]*" ]
              # topic_regexps = [ ]

              ## When set this tag will be added to all metrics with the topic as the value.
              # topic_tag = ""

              ## The list of Kafka message headers that should be pass as metric tags
              ## works only for Kafka version 0.11+, on lower versions the message headers
              ## are not available
              # msg_headers_as_tags = []

              ## The name of kafka message header which value should override the metric name.
              ## In case when the same header specified in current option and in msg_headers_as_tags
              ## option, it will be excluded from the msg_headers_as_tags list.
              # msg_header_as_metric_name = ""

              ## Set metric(s) timestamp using the given source.
              ## Available options are:
              ##   metric -- do not modify the metric timestamp
              ##   inner  -- use the inner message timestamp (Kafka v0.10+)
              ##   outer  -- use the outer (compressed) block timestamp (Kafka v0.10+)
              # timestamp_source = "metric"

              ## Optional Client id
              # client_id = "Telegraf"

              ## Optional TLS Config
              # enable_tls = false
              # 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

              ## Period between keep alive probes.
              ## Defaults to the OS configuration if not specified or zero.
              # keep_alive_period = "15s"

              ## SASL authentication credentials.  These settings should typically be used
              ## with TLS encryption enabled
              # sasl_username = "kafka"
              # sasl_password = "secret"

              ## Optional SASL:
              ## one of: OAUTHBEARER, PLAIN, SCRAM-SHA-256, SCRAM-SHA-512, GSSAPI
              ## (defaults to PLAIN)
              # sasl_mechanism = ""

              ## used if sasl_mechanism is GSSAPI
              # sasl_gssapi_service_name = ""
              # ## One of: KRB5_USER_AUTH and KRB5_KEYTAB_AUTH
              # sasl_gssapi_auth_type = "KRB5_USER_AUTH"
              # sasl_gssapi_kerberos_config_path = "/"
              # sasl_gssapi_realm = "realm"
              # sasl_gssapi_key_tab_path = ""
              # sasl_gssapi_disable_pafxfast = false

              ## used if sasl_mechanism is OAUTHBEARER
              # sasl_access_token = ""

              ## SASL protocol version.  When connecting to Azure EventHub set to 0.
              # sasl_version = 1

              # Disable Kafka metadata full fetch
              # metadata_full = false

              ## Name of the consumer group.
              # consumer_group = "telegraf_metrics_consumers"

              ## Compression codec represents the various compression codecs recognized by
              ## Kafka in messages.
              ##  0 : None
              ##  1 : Gzip
              ##  2 : Snappy
              ##  3 : LZ4
              ##  4 : ZSTD
              # compression_codec = 0
              ## Initial offset position; one of "oldest" or "newest".
              # offset = "oldest"

              ## Consumer group partition assignment strategy; one of "range", "roundrobin" or "sticky".
              # balance_strategy = "range"

              ## Maximum number of retries for metadata operations including
              ## connecting. Sets Sarama library's Metadata.Retry.Max config value. If 0 or
              ## unset, use the Sarama default of 3,
              # metadata_retry_max = 0

              ## Type of retry backoff. Valid options: "constant", "exponential"
              # metadata_retry_type = "constant"

              ## Amount of time to wait before retrying. When metadata_retry_type is
              ## "constant", each retry is delayed this amount. When "exponential", the
              ## first retry is delayed this amount, and subsequent delays are doubled. If 0
              ## or unset, use the Sarama default of 250 ms
              # metadata_retry_backoff = 0

              ## Maximum amount of time to wait before retrying when metadata_retry_type is
              ## "exponential". Ignored for other retry types. If 0, there is no backoff
              ## limit.
              # metadata_retry_max_duration = 0

              ## When set to true, this turns each bootstrap broker address into a set of
              ## IPs, then does a reverse lookup on each one to get its canonical hostname.
              ## This list of hostnames then replaces the original address list.
              ## resolve_canonical_bootstrap_servers_only = false

              ## Strategy for making connection to kafka brokers. Valid options: "startup",
              ## "defer". If set to "defer" the plugin is allowed to start before making a
              ## connection. This is useful if the broker may be down when telegraf is
              ## started, but if there are any typos in the broker setting, they will cause
              ## connection failures without warning at startup
              # connection_strategy = "startup"

              ## Maximum length of a message to consume, in bytes (default 0/unlimited);
              ## larger messages are dropped
              max_message_len = 1000000

              ## Max undelivered messages
              ## This plugin uses tracking metrics, which ensure messages are read to
              ## outputs before acknowledging them to the original broker to ensure data
              ## is not lost. This option sets the maximum messages to read from the
              ## broker that have not been written by an output.
              ##
              ## This value needs to be picked with awareness of the agent's
              ## metric_batch_size value as well. Setting max undelivered messages too high
              ## can result in a constant stream of data batches to the output. While
              ## setting it too low may never flush the broker's messages.
              # max_undelivered_messages = 1000

              ## Maximum amount of time the consumer should take to process messages. If
              ## the debug log prints messages from sarama about 'abandoning subscription
              ## to [topic] because consuming was taking too long', increase this value to
              ## longer than the time taken by the output plugin(s).
              ##
              ## Note that the effective timeout could be between 'max_processing_time' and
              ## '2 * max_processing_time'.
              # max_processing_time = "100ms"

              ## The default number of message bytes to fetch from the broker in each
              ## request (default 1MB). This should be larger than the majority of
              ## your messages, or else the consumer will spend a lot of time
              ## negotiating sizes and not actually consuming. Similar to the JVM's
              ## `fetch.message.max.bytes`.
              # consumer_fetch_default = "1MB"

              ## 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"

[[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"
  # }