mirror of
https://github.com/natelandau/ansible-homelab-config.git
synced 2025-11-18 18:03:40 -05:00
235 lines
10 KiB
Django/Jinja
235 lines
10 KiB
Django/Jinja
# 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 surround
|
|
# 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 = "{{ datacenter_name }}"
|
|
ip = "{{ ansible_host }}"
|
|
|
|
# Configuration for telegraf agent
|
|
[agent]
|
|
|
|
interval = "10s" ## Default data collection interval for all inputs
|
|
round_interval = true ## ie, if interval="10s" then always collect on :00, :10, :20, etc.
|
|
metric_batch_size = 1000 ## Controls the size of writes that Telegraf sends to output plugins
|
|
metric_buffer_limit = 10000 ## Maximum number of unwritten metrics per output.
|
|
collection_jitter = "5s" ## Jitter the collection by a random amount.
|
|
flush_interval = "10s" ## Default flushing interval for all outputs.
|
|
flush_jitter = "5s" ## Jitter the flush interval by a random amount
|
|
precision = ""
|
|
debug = false ## Log at debug level.
|
|
# quiet = false ## Log only error level messages.
|
|
{% if 'pis' in group_names %}
|
|
logtarget = "file" ## destination logs can be one of "file" or "stderr"
|
|
logfile = "/var/log/telegraf/telegraf.log"
|
|
logfile_rotation_interval = "1d"
|
|
# logfile_rotation_max_size = "0MB"
|
|
logfile_rotation_max_archives = 2
|
|
{% elif 'macs' in group_names %}
|
|
logtarget = "stderr" ## destination logs can be one of "file" or "stderr"
|
|
{% endif %}
|
|
|
|
hostname = "{{ inventory_hostname }}" ## Override default hostname, if empty use os.Hostname()
|
|
omit_hostname = false ## If set to true, do no set the "host" tag in the telegraf agent.
|
|
|
|
###############################################################################
|
|
# OUTPUT PLUGINS #
|
|
###############################################################################
|
|
|
|
[[outputs.influxdb]]
|
|
urls = ["http://influxdb.service.consul:{{ influxdb_port }}"]
|
|
database = "homelab"
|
|
retention_policy = "2day"
|
|
timeout = "5s"
|
|
|
|
###############################################################################
|
|
# INPUT PLUGINS #
|
|
###############################################################################
|
|
|
|
[[inputs.cpu]] # Read metrics about cpu usage
|
|
percpu = true ## Whether to report per-cpu stats or not
|
|
totalcpu = true ## Whether to report total system cpu stats or not
|
|
collect_cpu_time = false ## If true, collect raw CPU time metrics.
|
|
report_active = false ## If true, compute and report the sum of all non-idle CPU states.
|
|
[[inputs.disk]] # Read metrics about disk usage by mount point
|
|
#mount_points = ["/mnt/usbDrive","/boot"] # Restrict the stats to only the specified mount points.
|
|
ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs", "nfsd", "nfs4", "smbfs"]
|
|
[[inputs.diskio]] # Read metrics about disk IO by device
|
|
[[inputs.internal]] # Collect telegraf memory stats.
|
|
collect_memstats = true
|
|
[[inputs.mem]] # Read metrics about memory usage
|
|
[[inputs.processes]] # Get the number of processes and group them by status
|
|
[[inputs.swap]] # Read metrics about swap memory usage
|
|
[[inputs.system]] # Read metrics about system load & uptime
|
|
[[inputs.net]] # Gather metrics about network interfaces
|
|
|
|
###############################################################################
|
|
# PROCESSOR PLUGINS #
|
|
###############################################################################
|
|
|
|
[[processors.regex]]
|
|
namepass = ["docker_container_mem"]
|
|
|
|
# Tag and field conversions defined in a separate sub-tables
|
|
[[processors.regex.tags]]
|
|
## Tag to change
|
|
key = "container_name"
|
|
## Regular expression to match on a tag value
|
|
pattern = "^([a-zA-Z0-9_]+)-\\w{8}-\\w{4}-\\w{4}-\\w{4}-\\w{12}$"
|
|
## Matches of the pattern will be replaced with this string. Use ${1}
|
|
## notation to use the text of the first submatch.
|
|
replacement = "${1}"
|
|
|
|
[[processors.regex]]
|
|
namepass = ["docker_container_net"]
|
|
|
|
# Tag and field conversions defined in a separate sub-tables
|
|
[[processors.regex.tags]]
|
|
## Tag to change
|
|
key = "container_name"
|
|
## Regular expression to match on a tag value
|
|
pattern = "^([a-zA-Z0-9_]+)-\\w{8}-\\w{4}-\\w{4}-\\w{4}-\\w{12}$"
|
|
## Matches of the pattern will be replaced with this string. Use ${1}
|
|
## notation to use the text of the first submatch.
|
|
replacement = "${1}"
|
|
|
|
[[processors.regex]]
|
|
namepass = ["docker_container_cpu"]
|
|
|
|
# Tag and field conversions defined in a separate sub-tables
|
|
[[processors.regex.tags]]
|
|
## Tag to change
|
|
key = "container_name"
|
|
## Regular expression to match on a tag value
|
|
pattern = "^([a-zA-Z0-9_]+)-\\w{8}-\\w{4}-\\w{4}-\\w{4}-\\w{12}$"
|
|
## Matches of the pattern will be replaced with this string. Use ${1}
|
|
## notation to use the text of the first submatch.
|
|
replacement = "${1}"
|
|
|
|
[[processors.regex]]
|
|
namepass = ["docker_container_blkio"]
|
|
|
|
# Tag and field conversions defined in a separate sub-tables
|
|
[[processors.regex.tags]]
|
|
## Tag to change
|
|
key = "container_name"
|
|
## Regular expression to match on a tag value
|
|
pattern = "^([a-zA-Z0-9_]+)-\\w{8}-\\w{4}-\\w{4}-\\w{4}-\\w{12}$"
|
|
## Matches of the pattern will be replaced with this string. Use ${1}
|
|
## notation to use the text of the first submatch.
|
|
replacement = "${1}"
|
|
|
|
[[processors.regex]]
|
|
namepass = ["docker_container_health"]
|
|
|
|
# Tag and field conversions defined in a separate sub-tables
|
|
[[processors.regex.tags]]
|
|
## Tag to change
|
|
key = "container_name"
|
|
## Regular expression to match on a tag value
|
|
pattern = "^([a-zA-Z0-9_]+)-\\w{8}-\\w{4}-\\w{4}-\\w{4}-\\w{12}$"
|
|
## Matches of the pattern will be replaced with this string. Use ${1}
|
|
## notation to use the text of the first submatch.
|
|
replacement = "${1}"
|
|
[[processors.regex]]
|
|
namepass = ["docker_container_status"]
|
|
|
|
# Tag and field conversions defined in a separate sub-tables
|
|
[[processors.regex.tags]]
|
|
## Tag to change
|
|
key = "container_name"
|
|
## Regular expression to match on a tag value
|
|
pattern = "^([a-zA-Z0-9_]+)-\\w{8}-\\w{4}-\\w{4}-\\w{4}-\\w{12}$"
|
|
## Matches of the pattern will be replaced with this string. Use ${1}
|
|
## notation to use the text of the first submatch.
|
|
replacement = "${1}"
|
|
|
|
###############################################################################
|
|
# INPUT PLUGINS #
|
|
###############################################################################
|
|
|
|
[[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)
|
|
## Note: configure this in one of the manager nodes in a Swarm cluster.
|
|
## configuring in multiple Swarm managers results in duplication of metrics.
|
|
gather_services = false
|
|
|
|
## Only collect metrics for these containers. Values will be appended to
|
|
## container_name_include.
|
|
## Deprecated (1.4.0), use container_name_include
|
|
container_names = []
|
|
|
|
## Set the source tag for the metrics to the container ID hostname, eg first 12 chars
|
|
source_tag = false
|
|
|
|
## Containers to include and exclude. Collect all if empty. Globs accepted.
|
|
container_name_include = []
|
|
container_name_exclude = []
|
|
|
|
## Container states to include and exclude. Globs accepted.
|
|
## When empty only containers in the "running" state will be captured.
|
|
## example: container_state_include = ["created", "restarting", "running", "removing", "paused", "exited", "dead"]
|
|
## example: container_state_exclude = ["created", "restarting", "running", "removing", "paused", "exited", "dead"]
|
|
# container_state_include = []
|
|
# container_state_exclude = []
|
|
|
|
## Timeout for docker list, info, and stats commands
|
|
timeout = "5s"
|
|
|
|
## Whether to report for each container per-device blkio (8:0, 8:1...),
|
|
## network (eth0, eth1, ...) and cpu (cpu0, cpu1, ...) stats or not.
|
|
## Usage of this setting is discouraged since it will be deprecated in favor of 'perdevice_include'.
|
|
## Default value is 'true' for backwards compatibility, please set it to 'false' so that 'perdevice_include' setting
|
|
## is honored.
|
|
perdevice = true
|
|
|
|
## Specifies for which classes a per-device metric should be issued
|
|
## Possible values are 'cpu' (cpu0, cpu1, ...), 'blkio' (8:0, 8:1, ...) and 'network' (eth0, eth1, ...)
|
|
## Please note that this setting has no effect if 'perdevice' is set to 'true'
|
|
# perdevice_include = ["cpu"]
|
|
|
|
## Whether to report for each container total blkio and network stats or not.
|
|
## Usage of this setting is discouraged since it will be deprecated in favor of 'total_include'.
|
|
## Default value is 'false' for backwards compatibility, please set it to 'true' so that 'total_include' setting
|
|
## is honored.
|
|
total = false
|
|
|
|
## Specifies for which classes a total metric should be issued. Total is an aggregated of the 'perdevice' values.
|
|
## Possible values are 'cpu', 'blkio' and 'network'
|
|
## Total 'cpu' is reported directly by Docker daemon, and 'network' and 'blkio' totals are aggregated by this plugin.
|
|
## Please note that this setting has no effect if 'total' is set to 'false'
|
|
# total_include = ["cpu", "blkio", "network"]
|
|
|
|
## 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 = ["traefik.*"] # Do not report on Traefik tags
|
|
|
|
## Which environment variables should we use as a tag
|
|
tag_env = ["JAVA_HOME", "HEAP_SIZE"]
|
|
|
|
## Optional TLS Config
|
|
# 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
|