tele.conf

# 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 prepend
# 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)


# Global tags can be specified here in key="value" format.
[global_tags]
  my_tag = "load-testing"

# Configuration for telegraf agent
[agent]
  ## Default data collection interval for all inputs
  interval = "10s"
  ## 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.
  metric_batch_size = 1000
  ## For failed writes, telegraf will cache metric_buffer_limit metrics for each
  ## output, and will flush this buffer on a successful write. Oldest metrics
  ## are dropped first when this buffer fills.
  metric_buffer_limit = 10000

  ## 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. You shouldn't set this below
  ## interval. Maximum flush_interval will be flush_interval + flush_jitter
  flush_interval = "10s"
  ## 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"

  ## Run telegraf in debug mode
  debug = true
  ## Run telegraf in quiet mode
  quiet = false
  ## 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 influxdb server to send metrics to
[[outputs.influxdb]]
  ## The full HTTP or UDP endpoint URL for your InfluxDB 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 = ["udp://localhost:8089"] # UDP endpoint example
  urls = ["$INFLUXDB_HOST"] # required
  username = "$INFLUXDB_USERNAME"
  password = "$INFLUXDB_PASSWORD"

  ## The target database for metrics (telegraf will create it if not exists).
  database = "telegraf" # required
  ## Precision of writes, valid values are "ns", "us" (or "µs"), "ms", "s", "m", "h".
  ## note: using "s" precision greatly improves InfluxDB compression.
  precision = "s"

  ## Retention policy to write to.
  retention_policy = "autogen"
  ## Write consistency (clusters only), can be: "any", "one", "quorom", "all"
  write_consistency = "any"

  ## Write timeout (for the InfluxDB client), formatted as a string.
  ## If not provided, will default to 5s. 0s means no timeout (not recommended).
  timeout = "10s"


###############################################################################
#                            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
  ## Comment this line if you want the raw CPU time metrics
  fielddrop = ["time_*"]

# Read metrics about disk usage by mount point
[[inputs.disk]]
  ## By default, telegraf gather stats for all mountpoints.
  ## Setting mountpoints will restrict the stats to the specified mountpoints.
  # mount_points = ["/"]

  ## Ignore some mountpoints by filesystem type. For example (dev)tmpfs (usually
  ## present on /run, /var/run, /dev/shm or /dev).
  ignore_fs = ["tmpfs", "devtmpfs"]


# 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"]
  ## Uncomment the following line if you do not need disk serial numbers.
  # skip_serial_number = true

# 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]]
  # no configuration

# # Read metrics about network interface usage
[[inputs.net]]
#   ## By default, telegraf gathers stats from any up interface (excluding loopback)
#   ## Setting interfaces will tell it to gather these explicit interfaces,
#   ## regardless of status.
#   ##
#   # interfaces = ["eth0"]

# # Read TCP metrics such as established, time wait and sockets counts.
[[inputs.netstat]]
#   # no configuration

# # Read metrics about docker containers
 [[inputs.docker]]
#   ## Docker Endpoint
#   ##   To use TCP, set endpoint = "tcp://[ip]:[port]"
#   ##   To use environment variables (ie, docker-machine), set endpoint = "ENV"
   endpoint = "unix:///var/run/docker.sock"
#   ## Only collect metrics for these containers, collect all if empty
#   container_names = []
#   ## Timeout for docker list, info, and stats commands
   timeout = "5s"

###############################################################################
#                            SERVICE INPUT PLUGINS                            #
###############################################################################

# Statsd Server
[[inputs.statsd]]
  ## Address and port to host UDP listener on
  service_address = ":8125"
  ## Delete gauges every interval (default=false)
  delete_gauges = false
  ## Delete counters every interval (default=false)
  delete_counters = false
  ## Delete sets every interval (default=false)
  delete_sets = false
  ## Delete timings & histograms every interval (default=true)
  delete_timings = false
  ## Percentiles to calculate for timing & histogram stats
  percentiles = [90]

  ## separator to use between elements of a statsd metric
  metric_separator = "_"

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

  ## Statsd data translation templates, more info can be read here:
  ## https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md#graphite
  # 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