172 lines
6.2 KiB
Plaintext
172 lines
6.2 KiB
Plaintext
|
# 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]
|
||
|
|
host="k8s"
|
||
|
|
|
||
|
|
# 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. 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 = ""
|
||
|
|
omit_hostname = true
|
||
|
|
|
||
|
|
|
||
|
|
###############################################################################
|
||
|
|
# OUTPUT PLUGINS #
|
||
|
|
###############################################################################
|
||
|
|
|
||
|
|
# Configuration for sending metrics to InfluxDB
|
||
|
|
[[outputs.influxdb]]
|
||
|
|
urls = ["http://influxdb:8086"]
|
||
|
|
database = "telegraf"
|
||
|
|
|
||
|
|
|
||
|
|
# 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'
|
||
|
|
# 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
|
||
|
|
|
||
|
|
# Collect TCP connections state and UDP socket counts
|
||
|
|
[[inputs.netstat]]
|
||
|
|
# no configuration
|
||
|
|
|
||
|
|
# Gather metrics about network interfaces
|
||
|
|
[[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. When specifying an interface, glob-style
|
||
|
|
## patterns are also supported.
|
||
|
|
##
|
||
|
|
interfaces = ["eth*", "enp0s[0-1]", "lo"]
|
||
|
|
##
|
||
|
|
## On linux systems telegraf also collects protocol stats.
|
||
|
|
## Setting ignore_protocol_stats to true will skip reporting of protocol metrics.
|
||
|
|
##
|
||
|
|
# ignore_protocol_stats = false
|
||
|
|
##
|
||
|
|
|
||
|
|
[[inputs.kube_inventory]]
|
||
|
|
namespace = ""
|
||
|
|
url = "https://kubernetes.default.svc:443"
|
||
|
|
bearer_token = "/var/run/secrets/kubernetes.io/serviceaccount/token"
|
||
|
|
tls_ca = "/var/run/secrets/kubernetes.io/serviceaccount/ca.crt"
|