# Telegraf Configuration
#
# Telegraf is entirely plugin driven. All metrics are gathered from the
# declared inputs, and sent to the declared outputs.
#
# Plugins must be declared in here to be active.
# To deactivate a plugin, comment out the name and any variables.
#
# Use 'telegraf -config telegraf.conf -test' to see what metrics a config
# file would generate.
#
# Environment variables can be used anywhere in this config file, simply surround
# them with ${}. For strings the variable must be within quotes (ie, "${STR_VAR}"),
# for numbers and booleans they should be plain (ie, ${INT_VAR}, ${BOOL_VAR})

# Configuration for telegraf agent
[agent]
  ## Default data collection interval for all inputs
  interval = "30s"
  ## Rounds collection interval to 'interval'
  ## ie, if interval="10s" then always collect on :00, :10, :20, etc.
  round_interval = true

  ## Telegraf will send metrics to outputs in batches of at most
  ## metric_batch_size metrics.
  ## This controls the size of writes that Telegraf sends to output plugins.
  metric_batch_size = 2500

  ## Maximum number of unwritten metrics per output.  Increasing this value
  ## allows for longer periods of output downtime without dropping metrics at the
  ## cost of higher maximum memory usage.
  metric_buffer_limit = 25000

  ## Collection jitter is used to jitter the collection by a random amount.
  ## Each plugin will sleep for a random time within jitter before collecting.
  ## This can be used to avoid many plugins querying things like sysfs at the
  ## same time, which can have a measurable effect on the system.
  collection_jitter = "0s"

  ## Default flushing interval for all outputs. Maximum flush_interval will be
  ## flush_interval + flush_jitter
  flush_interval = "30s"
  ## Jitter the flush interval by a random amount. This is primarily to avoid
  ## large write spikes for users running a large number of telegraf instances.
  ## ie, a jitter of 5s and interval 10s means flushes will happen every 10-15s
  flush_jitter = "0s"

  ## By default or when set to "0s", precision will be set to the same
  ## timestamp order as the collection interval, with the maximum being 1s.
  ##   ie, when interval = "10s", precision will be "1s"
  ##       when interval = "250ms", precision will be "1ms"
  ## Precision will NOT be used for service inputs. It is up to each individual
  ## service input to set the timestamp at the appropriate precision.
  ## Valid time units are "ns", "us" (or "µs"), "ms", "s".
  precision = ""

  ## Log at debug level.
  # debug = false
  ## Log only error level messages.
  quiet = false

  ## Log target controls the destination for logs and can be one of "file",
  ## "stderr" or, on Windows, "eventlog".  When set to "file", the output file
  ## is determined by the "logfile" setting.
  # logtarget = "file"

  ## Name of the file to be logged to when using the "file" logtarget.  If set to
  ## the empty string then logs are written to stderr.
  # logfile = ""

  ## The logfile will be rotated after the time interval specified.  When set
  ## to 0 no time based rotation is performed.  Logs are rotated only when
  ## written to, if there is no log activity rotation may be delayed.
  # logfile_rotation_interval = "0d"

  ## The logfile will be rotated when it becomes larger than the specified
  ## size.  When set to 0 no size based rotation is performed.
  # logfile_rotation_max_size = "0MB"

  ## Maximum number of rotated archives to keep, any older logs are deleted.
  ## If set to -1, no archives are removed.
  # logfile_rotation_max_archives = 5

  ## Pick a timezone to use when logging or type 'local' for local time.
  ## Example: America/Chicago
  # log_with_timezone = ""

  ## Override default hostname, if empty use os.Hostname()
  hostname = ""
  ## If set to true, do no set the "host" tag in the telegraf agent.
  omit_hostname = false

###############################################################################
#                            OUTPUT PLUGINS                                   #
###############################################################################

# # Configuration for DataDog API to send metrics to.
[[outputs.datadog]]
  ## Datadog API key
  apikey = "${DD_API_KEY}"

  ## Connection timeout.
  # timeout = "5s"

  ## Write URL override; useful for debugging.
  # url = "https://app.datadoghq.com/api/v1/series"

  ## Set http_proxy (telegraf uses the system wide proxy settings if it isn't set)
  # http_proxy_url = "http://localhost:8888"


###############################################################################
#                            INPUT PLUGINS                                    #
###############################################################################


# Read metrics about cpu usage
[[inputs.cpu]]
  ## Whether to report per-cpu stats or not
  percpu = true
  ## Whether to report total system cpu stats or not
  totalcpu = true
  ## If true, collect raw CPU time metrics
  collect_cpu_time = false
  ## If true, compute and report the sum of all non-idle CPU states
  report_active = false


# Read metrics about disk usage by mount point
[[inputs.disk]]
  ## By default stats will be gathered for all mount points.
  ## Set mount_points will restrict the stats to only the specified mount points.
  # mount_points = ["/"]

  ## Ignore mount points by filesystem type.
  ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]


# Read metrics about disk IO by device
[[inputs.diskio]]
  ## By default, telegraf will gather stats for all devices including
  ## disk partitions.
  ## Setting devices will restrict the stats to the specified devices.
  # devices = ["sda", "sdb", "vd*"]
  ## Uncomment the following line if you need disk serial numbers.
  # skip_serial_number = false
  #
  ## On systems which support it, device metadata can be added in the form of
  ## tags.
  ## Currently only Linux is supported via udev properties. You can view
  ## available properties for a device by running:
  ## 'udevadm info -q property -n /dev/sda'
  ## Note: Most, but not all, udev properties can be accessed this way. Properties
  ## that are currently inaccessible include DEVTYPE, DEVNAME, and DEVPATH.
  # device_tags = ["ID_FS_TYPE", "ID_FS_USAGE"]
  #
  ## Using the same metadata source as device_tags, you can also customize the
  ## name of the device via templates.
  ## The 'name_templates' parameter is a list of templates to try and apply to
  ## the device. The template may contain variables in the form of '$PROPERTY' or
  ## '${PROPERTY}'. The first template which does not contain any variables not
  ## present for the device is used as the device name tag.
  ## The typical use case is for LVM volumes, to get the VG/LV name instead of
  ## the near-meaningless DM-0 name.
  # name_templates = ["$ID_FS_LABEL","$DM_VG_NAME/$DM_LV_NAME"]


# Get kernel statistics from /proc/stat
[[inputs.kernel]]
  # no configuration


# Read metrics about memory usage
[[inputs.mem]]
  # no configuration


# Get the number of processes and group them by status
[[inputs.processes]]
  # no configuration


# Read metrics about swap memory usage
[[inputs.swap]]
  # no configuration


# Read metrics about system load & uptime
[[inputs.system]]
  ## Uncomment to remove deprecated metrics.
  # fielddrop = ["uptime_format"]


# Read metrics about ECS containers
[[inputs.ecs]]
  ## ECS metadata url.
  ## Metadata v2 API is used if set explicitly. Otherwise,
  ## v3 metadata endpoint API is used if available.
  # endpoint_url = ""

  ## Containers to include and exclude. Globs accepted.
  ## Note that an empty array for both will include all containers
  # container_name_include = []
  # container_name_exclude = []

  ## Container states to include and exclude. Globs accepted.
  ## When empty only containers in the "RUNNING" state will be captured.
  ## Possible values are "NONE", "PULLED", "CREATED", "RUNNING",
  ## "RESOURCES_PROVISIONED", "STOPPED".
  # container_status_include = []
  # container_status_exclude = []

  ## ecs labels to include and exclude as tags.  Globs accepted.
  ## Note that an empty array for both will include all labels as tags
  ecs_label_include = [ "com.amazonaws.ecs.*" ]
  ecs_label_exclude = []

  ## Timeout for queries.
  # timeout = "5s"

###############################################################################
#                            service input plugins                            #
###############################################################################

# Statsd UDP/TCP Server
[[inputs.statsd]]
  ## Protocol, must be "tcp", "udp", "udp4" or "udp6" (default=udp)
  protocol = "udp"

  ## MaxTCPConnection - applicable when protocol is set to tcp (default=250)
  max_tcp_connections = 250

  ## Enable TCP keep alive probes (default=false)
  tcp_keep_alive = false

  ## Specifies the keep-alive period for an active network connection.
  ## Only applies to TCP sockets and will be ignored if tcp_keep_alive is false.
  ## Defaults to the OS configuration.
  # tcp_keep_alive_period = "2h"

  ## Address and port to host UDP listener on
  service_address = ":${TELEGRAF_AGENT_PORT}"

  ## The following configuration options control when telegraf clears it's cache
  ## of previous values. If set to false, then telegraf will only clear it's
  ## cache when the daemon is restarted.
  ## Reset gauges every interval (default=true)
  delete_gauges = true
  ## Reset counters every interval (default=true)
  delete_counters = true
  ## Reset sets every interval (default=true)
  delete_sets = true
  ## Reset timings & histograms every interval (default=true)
  delete_timings = true

  ## Percentiles to calculate for timing & histogram stats
  percentiles = [50.0, 90.0, 99.0, 99.9, 99.95, 100.0]

  ## separator to use between elements of a statsd metric
  ## DO NOT CHANGE THIS
  metric_separator = "."

  ## Parses tags in the datadog statsd format
  ## http://docs.datadoghq.com/guides/dogstatsd/
  parse_data_dog_tags = true

  ## Parses datadog extensions to the statsd format
  datadog_extensions = true

  ## Parses distributions metric as specified in the datadog statsd format
  ## https://docs.datadoghq.com/developers/metrics/types/?tab=distribution#definition
  datadog_distributions = true

  ## Statsd data translation templates, more info can be read here:
  ## https://github.com/influxdata/telegraf/blob/master/docs/TEMPLATE_PATTERN.md
  # templates = [
  #     "cpu.* measurement*"
  # ]

  ## Number of UDP messages allowed to queue up, once filled,
  ## the statsd server will start dropping packets
  allowed_pending_messages = 10000

  ## Number of timing/histogram values to track per-measurement in the
  ## calculation of percentiles. Raising this limit increases the accuracy
  ## of percentiles but also increases the memory usage and cpu time.
  percentile_limit = 1000

  ## Max duration (TTL) for each metric to stay cached/reported without being updated.
  #max_ttl = "1000h"

# Global tags can be specified here in key="value" format.
[global_tags]
  # dc = "us-east-1" # will tag all metrics with dc=us-east-1
  # rack = "1a"
  ## Environment variables can be used as tags, and throughout the config file
  # user = "$USER"