telegraf.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 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})


# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
#                            GLOBAL CONFIGURATION                             #
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #


# Global tags can be specified here in key="value" format.
[global_tags]
  machine_id = "$TELEGRAF_MACHINE"


# Configuration for telegraf agent
[agent]
  # Default data collection interval for all inputs
  interval = "5s"
  # Rounds collection interval to 'interval'
  # ie, if interval="10s" then always collect on :00, :10, :20, etc.
  round_interval = false

  # 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 = 1000

  # 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 = 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. Maximum flush_interval will be
  # flush_interval + flush_jitter
  flush_interval = "5s"

  # 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"

  ## Collected metrics are rounded to the precision specified. Precision is
  ## specified as an interval with an integer + unit (e.g. 0s, 10ms, 2us, 4s).
  ## Valid time units are "ns", "us" (or "µs"), "ms", "s".
  ##
  ## 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.
  precision = "0s"

  # Run telegraf with debug log messages.
  debug = false

  # Run telegraf in quiet mode (error log messages only).
  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

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


# Read metrics about system load & uptime.
[[inputs.system]]


# Read metrics about CPU usage.
[[inputs.cpu]]
  # Options:
  #   percpu: Whether to report per-CPU stats or not.
  #   totalcpu: Whether to report total system CPU stats or not.
  #   collect_cpu_time: Whether to collect raw CPU time metrics.
  percpu = true
  totalcpu = true
  collect_cpu_time = true


# 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"]

  # NOTE: tagpass and tagdrop parameters must be defined at the end of the
  # plugin definition, otherwise subsequent plugin config options will be
  # interpreted as part of the tagpass/tagdrop map.

  # Drop stats for LVM partitions and loop devices.
  [inputs.diskio.tagdrop]
    name = ["dm*", "loop*"]


# 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 = ["eth*", "vnet0", "virbr0", "docker0"]


# Read metrics about memory usage.
[[inputs.mem]]


# Read metrics about swap memory usage.
[[inputs.swap]]


# Get kernel statistics from /proc/stat.
[[inputs.kernel]]


# Get the number of processes and group them by status.
[[inputs.processes]]

# Read metrics about temperature
[[inputs.temp]]


# Executes the commands on every interval and parses metrics from their output.
[[inputs.exec]]
  # Commands array. Glob patterns are matched on every interval, so adding new
  # scripts that match the pattern will cause them to be picked up immediately.
  commands = ["/opt/mistio/mist-telegraf/custom/*"]

  # Timeout for each command to complete.
  timeout = "5s"

  # Measurement name suffix (for separating different commands),
  name_suffix = ""

  # Data format to consume. Each data format has its own unique set of
  # configuration settings.
  data_format = "influx"

# # The libvirt plugin collects statistics from virtualized guests using virtualization libvirt API.
# [[inputs.libvirt]]
#      ## Domain names from which libvirt gather statistics.
#      ## By default (empty or missing array) the plugin gather statistics from each domain registered in the host system.
#      # domains = []
#
#      ## Libvirt connection URI with hypervisor.
#      ## The plugin supports multiple transport protocols and approaches which are configurable via the URI.
#      ## The general URI form: driver[+transport]://[username@][hostname][:port]/[path][?extraparameters]
#      ## Supported transport protocols: ssh, tcp, tls, unix
#      ## URI examples for each type of transport protocol:
#      ## 1. SSH:  qemu+ssh://<USER@IP_OR_HOSTNAME>/system?keyfile=/<PATH_TO_PRIVATE_KEY>&known_hosts=/<PATH_TO_known_hosts>
#      ## 2. TCP:  qemu+tcp://<IP_OR_HOSTNAME>/system
#      ## 3. TLS:  qemu+tls://<HOSTNAME>/system?pkipath=/certs_dir/<COMMON_LOCATION_OF_CACERT_AND_SERVER_CLIENT_CERTS>
#      ## 4. UNIX: qemu+unix:///system?socket=/<PATH_TO_libvirt-sock>
#      ## Default URI is qemu:///system
#      # libvirt_uri = "qemu:///system"
#
#      ## Statistics groups for which libvirt plugin will gather statistics.
#      ## Supported statistics groups: state, cpu_total, balloon, vcpu, interface, block, perf, iothread, memory, dirtyrate
#      ## Empty array means no metrics for statistics groups will be exposed by the plugin.
#      ## By default the plugin will gather all available statistics.
#      # statistics_groups = ["state", "cpu_total", "balloon", "vcpu", "interface", "block", "perf", "iothread", "memory", "dirtyrate"]
#
#      ## A list containing additional statistics to be exposed by libvirt plugin.
#      ## Supported additional statistics: vcpu_mapping
#      ## By default (empty or missing array) the plugin will not collect additional statistics.
#      # additional_statistics = []

# # Pulls statistics from nvidia GPUs attached to the host
# [[inputs.nvidia_smi]]
#   ## Optional: path to nvidia-smi binary, defaults "/usr/bin/nvidia-smi"
#   ## We will first try to locate the nvidia-smi binary with the explicitly specified value (or default value),
#   ## if it is not found, we will try to locate it on PATH(exec.LookPath), if it is still not found, an error will be returned
#   # bin_path = "/usr/bin/nvidia-smi"
#
#   ## Optional: timeout for GPU polling
#   # timeout = "5s"


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


[[outputs.influxdb]]
  # The HTTP or UDP URL for your InfluxDB instance.
  # Each item should be of the form: scheme "://" host [ ":" port]
  #
  # Multiple URLs can be specified as part of the same cluster.
  # Only ONE of the URLs will be written to each interval.
  urls = ["$TELEGRAF_HOST"]
  # The target database for metrics (telegraf will create it if not exists).
  database = "$TELEGRAF_DB"

  # Retention policy to write to. Empty string writes to the default RP.
  retention_policy = ""
  # Write consistency (clusters only), can be: "any", "one", "quorum", "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 = "3s"

  username = "$TELEGRAF_MACHINE"
  password = "$TELEGRAF_PASSWORD"

  # Set the user agent for HTTP POSTs (can be useful for log differentiation).
  user_agent = "telegraf-$TELEGRAF_MACHINE"

  # Optional SSL settings.
  #ssl_ca = "/etc/telegraf/ca.pem"
  #ssl_key = "/etc/telegraf/key.pem"
  #ssl_cert = "/etc/telegraf/cert.pem"
  #insecure_skip_verify = false