telegraf 配置文件详解

Author: fupeng.li

date: 2020-05-14

关键字：监控系统，telegraf

#全局tag配置，采用key = "values"方式，这样在本机采集到的所有数据将都有这个标签
[global_tags]
  dc = "docker-test"
#agent配置
[agent]
  #默认的数据(input)采集间隔时间
  interval = "1s"
  #采用轮询时间间隔。默认是使用interval里面的值进行轮询，比如interval = "10s",那采集时间将是:00, :10, :20, 等
  round_interval = true
  #每次发送到output的度量大小不能超过metric_batch_size的值, 个数
  metric_batch_size = 1000
  #telegraf会为每一个output去缓存一份度量值，metric_buffer_limit为缓存的限制，并且刷新buffer以确定成功写入。如果达到这个限制了，老的数据会被第一时间丢弃
  #当然了，增加这个值能够容忍更多的数据连接，但是这也将会增加telegraf潜在的内存占用。这个值可以大于metric_batch_size但是必须小于它的两倍
  metric_buffer_limit = 10000
  #通过随机度量来对采集时间进行抖动。每个插件在采集数据之前将会有一个随机时间的休眠
  #这个设置是为了防止多个采集源数据同一时间都在队列
  collection_jitter = "0s"
  #默认所有数据flush到outputs的时间(在数据被flush到output之前，最大能到flush_interval + flush_jitter)。不能低于interval
  flush_interval = "10s"
  # 通过随机数来对flush间隔进行抖动。这个主要是为了避免当运行一个大的telegraf实例的时候有比较大的写入。(jitter=5s,flush_interval=10s意味着每10-15s会发生一次flush操作)
  flush_jitter = "0s"
  #默认这个值被设置相同的时间戳通过采集间隔排序。最大值为1s。这个指标一般不会用在service input(比如logparser和statsd)。单位(ns,us,ms,s)
  precision = ""
  #以debug模式运行
  debug = false
  #以安静模式运行
  quiet = false
  #这个将会覆盖默认的hostname，如果为空的话，将会采用os.Hostname()
  hostname = ""
  #如果设置为true，就不允许在telegraf agent里面设置"host"标签了 
  omit_hostname = false

###############################################################################
#                            INPUT PLUGINS                                    #
###############################################################################
# inputs插件全局参数:
#每一个input都可以配置的全局配置项
#name_override:覆盖默认的度量值名字(默认是input的名字)
#name_prefix:指定一个前缀并附加到度量值的名字(measuerments name)
#name_suffix:指定后缀
#interval：多久采集一次数据，默认可用使用全局配置中的参数

# 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", "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]]
  # no configuration

# # 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 = ":8125"
#
#   ## 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 = [90, 99]
#
#   ## separator to use between elements of a statsd metric
   metric_separator = "."

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

#输出插件，我们使用的是influxdb，得先进行安装配置
[[outputs.influxdb]]
  # influxdb 的地址
  urls = ["http://influxdb:8086", ] # required
  #默认需要连接的telegraf库，没有则自动创建
  database = "bytepower" # required
  precision = "s"
  #修改保留策略
  retention_policy = ""
  #持续写入，仅支持集群模式, can be: "any", "one", "quorum", "all"
  write_consistency = "any"
  #作为influxdb客户端，设置写超时时间，如果为空默认为5s超时，0s表示不设置超时时间(不建议)
  timeout = "5s"
  #设置bytepower的库的用户名和密码, 需要在 influxdb 进行配置
  username = "admin"
  password = "admin"

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


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