infra/roles/telegraf/templates/telegraf.conf.j2

333 lines
11 KiB
Django/Jinja

[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"
shortname = "{{ inventory_hostname.split('.')[0] }}"
{% for key, val in sudo_tags.items() -%}
{{ key }} = "{{ val }}"
{% endfor %}
[agent]
interval = "{{ telegraf_interval | default('60s') }}"
## 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
## 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 = "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 = ""
## Log at debug level.
# debug = false
## Log only error level messages.
quiet = false
## Log target controls the destination for logs and can be one of "file",
## "stderr" or, on Windows, "eventlog". When set to "file", the output file
## is determined by the "logfile" setting.
logtarget = "file"
## Name of the file to be logged to when using the "file" logtarget. If set to
## the empty string then logs are written to stderr.
logfile = "/var/log/telegraf/telegraf.log"
## The logfile will be rotated after the time interval specified. When set
## to 0 no time based rotation is performed. Logs are rotated only when
## written to, if there is no log activity rotation may be delayed.
#logfile_rotation_interval = "1d"
## The logfile will be rotated when it becomes larger than the specified
## size. When set to 0 no size based rotation is performed.
# logfile_rotation_max_size = "0MB"
## Maximum number of rotated archives to keep, any older logs are deleted.
## If set to -1, no archives are removed.
# logfile_rotation_max_archives = 5
## 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
[[outputs.influxdb]]
## The full HTTP or UDP URL for your InfluxDB instance.
##
## Multiple URLs can be specified for a single cluster, only ONE of the
## urls will be written to each interval.
# urls = ["unix:///var/run/influxdb.sock"]
# urls = ["udp://127.0.0.1:8089"]
urls = ["https://{{ ingest }}"]
## The target database for metrics; will be created as needed.
## For UDP url endpoint database needs to be configured on server side.
database = "telegraf"
## The value of this tag will be used to determine the database. If this
## tag is not set the 'database' option is used as the default.
# database_tag = ""
## If true, the 'database_tag' will not be included in the written metric.
# exclude_database_tag = false
## If true, no CREATE DATABASE queries will be sent. Set to true when using
## Telegraf with a user without permissions to create databases or when the
## database already exists.
skip_database_creation = true
## Name of existing retention policy to write to. Empty string writes to
## the default retention policy. Only takes effect when using HTTP.
# retention_policy = ""
## The value of this tag will be used to determine the retention policy. If this
## tag is not set the 'retention_policy' option is used as the default.
# retention_policy_tag = ""
## If true, the 'retention_policy_tag' will not be included in the written metric.
# exclude_retention_policy_tag = false
## Write consistency (clusters only), can be: "any", "one", "quorum", "all".
## Only takes effect when using HTTP.
# write_consistency = "any"
## Timeout for HTTP messages.
timeout = "5s"
## HTTP Basic Auth
username = "{{ telegraf_user }}"
password = "{{ telegraf_password }}"
## HTTP User-Agent
user_agent = "telegraf"
## UDP payload size is the maximum packet size to send.
# udp_payload = "512B"
## Optional TLS Config for use on HTTP connections.
# tls_ca = "/etc/telegraf/ca.pem"
# tls_cert = "/etc/telegraf/cert.pem"
# tls_key = "/etc/telegraf/key.pem"
## Use TLS but skip chain & host verification
# insecure_skip_verify = false
## HTTP Proxy override, if unset values the standard proxy environment
## variables are consulted to determine which proxy, if any, should be used.
# http_proxy = "http://corporate.proxy:3128"
## Additional HTTP headers
# http_headers = {"X-Special-Header" = "Special-Value"}
## HTTP Content-Encoding for write request body, can be set to "gzip" to
## compress body or "identity" to apply no encoding.
# content_encoding = "identity"
## When true, Telegraf will output unsigned integers as unsigned values,
## i.e.: "42u". You will need a version of InfluxDB supporting unsigned
## integer values. Enabling this option will result in field type errors if
## existing data has been written.
# influx_uint_support = false
{% if telegraf_sensors == true %}
[[inputs.sensors]]
{% endif %}
[[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
[[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", "iso9660", "overlay", "aufs", "squashfs", "nsfs", "securityfs", "debugfs", "tracefs", "configfs"]
[[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"]
[[inputs.kernel]]
# no configuration
[[inputs.mem]]
# no configuration
[[inputs.processes]]
# no configuration
[[inputs.swap]]
# no configuration
[[inputs.system]]
## Uncomment to remove deprecated metrics.
# fielddrop = ["uptime_format"]
{% if 'servers' in group_names and not telegraf_disable_docker|default(false) %}
{% if telegraf_docker|default(true) %}
[[inputs.docker]]
timeout = "5s"
{% endif %}
{% endif %}
#[[inputs.ethtool]]
{% if 'monitoring' in group_names %}
[[inputs.influxdb]]
{% endif %}
[[inputs.net]]
{% if telegraf_smart_disks %}
[[inputs.smart]]
use_sudo = true
[[processors.enum]]
[[processors.enum.mapping]]
field = "health_ok"
dest = "health_ok_int"
[processors.enum.mapping.value_mappings]
false = 0
true = 1
{% endif %}
{% if 'openldap' in group_names and False%}
[[inputs.openldap]]
host = "{{ openldap_url }}"
port = 636
# ldaps, starttls, or no encryption. default is an empty string, disabling all encryption.
# note that port will likely need to be changed to 636 for ldaps
# valid options: "" | "starttls" | "ldaps"
tls = "ldaps"
# skip peer certificate verification. Default is false.
insecure_skip_verify = false
# Path to PEM-encoded Root certificate to use to verify server certificate
#tls_ca = "/etc/ssl/certs.pem"
# dn/password to bind with. If bind_dn is empty, an anonymous bind is performed.
bind_dn = ""
bind_password = ""
# reverse metric names so they sort more naturally
# Defaults to false if unset, but is set to true when generating a new config
reverse_metric_names = true
{% endif %}
{% if 'bear' in group_names %}
# [[inputs.exec]]
# commands = ["/usr/local/bin/farmertelegraf.sh"]
# timeout = "5s"
# data_format = "influx"
{% endif %}
{% if 'backupservers' in group_names %}
[[inputs.filestat]]
## These accept standard unix glob matching rules, but with the addition of
## ** as a "super asterisk". See https://github.com/gobwas/glob.
files = ["/deadspace/backups/rsnapshot"]
{% endif %}
{# {% if 'deadspace' in group_names %}
# [[inputs.filestat]]
# ## These accept standard unix glob matching rules, but with the addition of
# ## ** as a "super asterisk". See https://github.com/gobwas/glob.
#
# files = [
# {% for origin in deadspace %}
# {% for ds in deadspace[origin] %}
# {% if inventory_hostname in ds['replicas'] %}
# "{{ ds.path }}",
# {% endif %}
# {% endfor %}
# {% endfor %}
#
# ]
#
# ## If true, read the entire file and calculate an md5 checksum.
# md5 = false
# {% endif %} #}
[[inputs.exec]]
commands = ["/usr/local/bin/telegraf-vnstat.py"]
timeout = "2s"
data_format = "influx"