Influxdb/Telegraf/chronograf stack

docker-compose.yml

version: "3.0"

services:
  influxdb:
    image: influxdb:1.4
    ports:
      - "8086:8086"
    volumes:
      - influx:/var/lib/influxdb
  telegraf:
    image: telegraf:1.5
    network_mode: host
    volumes:
      - .:/etc/telegraf
  chronograf:
    image: chronograf:1.4
    ports:
      - "8888:8888"
    links:
      - influxdb
    volumes:
      - chronograf:/var/lib/chronograf
    command: --influxdb-url=http://influxdb:8086

volumes:
  influx:
  chronograf:

docker-compose_arm32v7.yml

version: "3.0"

services:
  influxdb:
    image: arm32v7/influxdb:1.4
    ports:
      - "8086:8086"
    volumes:
      - influx:/var/lib/influxdb
  telegraf:
    image: arm32v7/telegraf:1.5
    network_mode: host
    volumes:
      - .:/etc/telegraf
  chronograf:
    image: arm32v7/chronograf:1.4
    ports:
      - "8888:8888"
    links:
      - influxdb
    volumes:
      - chronograf:/var/lib/chronograf
    command: --influxdb-url=http://influxdb:8086

volumes:
  influx:
  chronograf:

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 = "1s"
  ## 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, precision will be set to the same timestamp order as the
  ## collection interval, with the maximum being 1s.
  ## Precision will NOT be used for service inputs, such as logparser and statsd.
  ## Valid values 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 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 = ["http://localhost:8086"] # required
  ## The target database for metrics (telegraf will create it if not exists).
  database = "telegraf" # required

  ## 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 = "5s"
  # username = "telegraf"
  # password = "metricsmetricsmetricsmetrics"
  ## Set the user agent for HTTP POSTs (can be useful for log differentiation)
  # user_agent = "telegraf"
  ## Set UDP payload size, defaults to InfluxDB UDP Client default (512 bytes)
  # udp_payload = 512

  ## 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




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

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



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

# # 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 = true
  ## Whether to report total system cpu stats or not
  totalcpu = true
  ## If true, collect raw CPU time metrics.
  collect_cpu_time = 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"]


# 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


# 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 from one or more commands that can output to stdout
# [[inputs.exec]]
#   ## Commands array
#   commands = [
#     "/tmp/test.sh",
#     "/usr/bin/mycollector --foo=bar",
#     "/tmp/collect_*.sh"
#   ]
#
#   ## Timeout for each command to complete.
#   timeout = "5s"
#
#   ## measurement name suffix (for separating different commands)
#   name_suffix = "_mycollector"
#
#   ## Data format to consume.
#   ## Each data format has it's 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"





# Read InfluxDB-formatted JSON metrics from one or more HTTP endpoints
[[inputs.influxdb]]
  ## Works with InfluxDB debug endpoints out of the box,
  ## but other services can use this format too.
  ## See the influxdb plugin's README for more details.
  ## Multiple URLs from which to read InfluxDB-formatted JSON
  ## Default is "http://localhost:8086/debug/vars".
  urls = [
    "http://localhost:8086/debug/vars"
  ]
  ## http request & header timeout
  timeout = "5s"



# 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