telegraf config

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 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]
  # 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"


# 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.
  ## This controls the size of writes that Telegraf sends to output plugins.
  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.
  ## This buffer only fills when writes fail to output plugin(s).
  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"

  ## 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 = ""

  ## Logging configuration:
  ## Run telegraf with debug log messages.
  debug = false
  ## Run telegraf in quiet mode (error log messages only).
  quiet = false
  ## Specify the log file name. The empty string means to log to stderr.
  logfile = ""

  ## 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 Graphite server to send metrics to
[[outputs.graphite]]
#   ## TCP endpoint for your graphite instance.
#   ## If multiple endpoints are configured, output will be load balanced.
#   ## Only one of the endpoints will be written to with each iteration.
   servers = ["graphite:2003"]
#   ## Prefix metrics name
#   prefix = ""
#   ## Graphite output template
#   ## see https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_OUTPUT.md
#   template = "host.tags.measurement.field"
#   ## timeout in seconds for the write connection to graphite
#   timeout = 2
#
#   ## Optional SSL Config
#   # ssl_ca = "/etc/telegraf/ca.pem"
#   # ssl_cert = "/etc/telegraf/cert.pem"
#   # ssl_key = "/etc/telegraf/key.pem"
#   ## Use SSL but skip chain & host verification
#   # insecure_skip_verify = false

# # Configuration for Librato API to send metrics to.
# [[outputs.librato]]
#   ## Librator API Docs
#   ## http://dev.librato.com/v1/metrics-authentication
#   ## Librato API user
#   api_user = "telegraf@influxdb.com" # required.
#   ## Librato API token
#   api_token = "my-secret-token" # required.
#   ## Debug
#   # debug = false
#   ## Connection timeout.
#   # timeout = "5s"
#   ## Output source Template (same as graphite buckets)
#   ## see https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_OUTPUT.md#graphite
#   ## This template is used in librato's source (not metric's name)
#   template = "host"
#

###############################################################################
#                            PROCESSOR PLUGINS                                #
###############################################################################

# # Print all metrics that pass through this filter.
# [[processors.printer]]


###############################################################################
#                            AGGREGATOR PLUGINS                               #
###############################################################################

# # Keep the aggregate basicstats of each metric passing through.
# [[aggregators.basicstats]]
#   ## General Aggregator Arguments:
#   ## The period on which to flush & clear the aggregator.
#   period = "30s"
#   ## If true, the original metric will be dropped by the
#   ## aggregator and will not get sent to the output plugins.
#   drop_original = false


# # Create aggregate histograms.
# [[aggregators.histogram]]
#   ## The period in which to flush the aggregator.
#   period = "30s"
#
#   ## If true, the original metric will be dropped by the
#   ## aggregator and will not get sent to the output plugins.
#   drop_original = false
#
#   ## Example config that aggregates all fields of the metric.
#   # [[aggregators.histogram.config]]
#   #   ## The set of buckets.
#   #   buckets = [0.0, 15.6, 34.5, 49.1, 71.5, 80.5, 94.5, 100.0]
#   #   ## The name of metric.
#   #   measurement_name = "cpu"
#
#   ## Example config that aggregates only specific fields of the metric.
#   # [[aggregators.histogram.config]]
#   #   ## The set of buckets.
#   #   buckets = [0.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 70.0, 80.0, 90.0, 100.0]
#   #   ## The name of metric.
#   #   measurement_name = "diskio"
#   #   ## The concrete fields of metric
#   #   fields = ["io_time", "read_time", "write_time"]


# # Keep the aggregate min/max of each metric passing through.
# [[aggregators.minmax]]
#   ## General Aggregator Arguments:
#   ## The period on which to flush & clear the aggregator.
#   period = "30s"
#   ## If true, the original metric will be dropped by the
#   ## aggregator and will not get sent to the output plugins.
#   drop_original = false



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

# Read metrics about cpu usage
[[inputs.cpu]]
  ## Whether to report per-cpu stats or not
  percpu = false
  ## 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, 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", "devfs"]


# 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 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'
  # 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]]
  # no configuration

# # Read metrics of bcache from stats_total and dirty_data
# [[inputs.bcache]]
#   ## Bcache sets path
#   ## If not specified, then default is:
#   bcachePath = "/sys/fs/bcache"
#
#   ## By default, telegraf gather stats for all bcache devices
#   ## Setting devices will restrict the stats to the specified
#   ## bcache devices.
#   bcacheDevs = ["bcache0"]


# # Collect bond interface status, slaves statuses and failures count
# [[inputs.bond]]
#   ## Sets 'proc' directory path
#   ## If not specified, then default is /proc
#   # host_proc = "/proc"
#
#   ## By default, telegraf gather stats for all bond interfaces
#   ## Setting interfaces will restrict the stats to the specified
#   ## bond interfaces.
#   # bond_interfaces = ["bond0"]

# # 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"
#
#   ## Set to true to collect Swarm metrics(desired_replicas, running_replicas)
#   gather_services = false
#
#   ## Only collect metrics for these containers, collect all if empty
#   container_names = []
#
#   ## Containers to include and exclude. Globs accepted.
#   ## Note that an empty array for both will include all containers
#   container_name_include = []
#   container_name_exclude = ["telegraf"]
#
#   ## Timeout for docker list, info, and stats commands
#   timeout = "5s"
#
#   ## Whether to report for each container per-device blkio (8:0, 8:1...) and
#   ## network (eth0, eth1, ...) stats or not
#   perdevice = true
#   ## Whether to report for each container total blkio and network stats or not
#   total = false
#   ## Which environment variables should we use as a tag
#   ##tag_env = ["JAVA_HOME", "HEAP_SIZE"]
#
#   ## docker labels to include and exclude as tags.  Globs accepted.
#   ## Note that an empty array for both will include all labels as tags
#   docker_label_include = []
#   docker_label_exclude = []
#
#   ## Optional SSL Config
#   # ssl_ca = "/etc/telegraf/ca.pem"
#   # ssl_cert = "/etc/telegraf/cert.pem"
#   # ssl_key = "/etc/telegraf/key.pem"
#   ## Use SSL but skip chain & host verification
#   # insecure_skip_verify = false

# # 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"]


# # Collect kernel snmp counters and network interface statistics
# [[inputs.nstat]]
#   ## file paths for proc files. If empty default paths will be used:
#   ##    /proc/net/netstat, /proc/net/snmp, /proc/net/snmp6
#   ## These can also be overridden with env variables, see README.
#   proc_net_netstat = "/proc/net/netstat"
#   proc_net_snmp = "/proc/net/snmp"
#   proc_net_snmp6 = "/proc/net/snmp6"
#   ## dump metrics with 0 values too
#   dump_zeros       = true


# # Monitor sensors, requires lm-sensors package
[[inputs.sensors]]
#   ## Remove numbers from field names.
#   ## If true, a field name like 'temp1_input' will be changed to 'temp_input'.
#   # remove_numbers = true

# [[inputs.nvidia_smi]]

# # Read metrics from storage devices supporting S.M.A.R.T.
# [[inputs.smart]]
#   ## Optionally specify the path to the smartctl executable
#   # path = "/usr/bin/smartctl"
#   #
#   ## On most platforms smartctl requires root access.
#   ## Setting 'use_sudo' to true will make use of sudo to run smartctl.
#   ## Sudo must be configured to to allow the telegraf user to run smartctl
#   ## with out password.
#   # use_sudo = false
#   #
#   ## Skip checking disks in this power mode. Defaults to
#   ## "standby" to not wake up disks that have stoped rotating.
#   ## See --nocheck in the man pages for smartctl.
#   ## smartctl version 5.41 and 5.42 have faulty detection of
#   ## power mode and might require changing this value to
#   ## "never" depending on your disks.
#   # nocheck = "standby"
#   #
#   ## Gather detailed metrics for each SMART Attribute.
#   ## Defaults to "false"
#   ##
#   # attributes = false
#   #
#   ## Optionally specify devices to exclude from reporting.
#   # excludes = [ "/dev/pass6" ]
#   #
#   ## Optionally specify devices and device type, if unset
#   ## a scan (smartctl --scan) for S.M.A.R.T. devices will
#   ## done and all found will be included except for the
#   ## excluded in excludes.
#   # devices = [ "/dev/ada0 -d atacam" ]