ansible-nas/templates/telegraf/telegraf.conf
David Stephens 3da19e5708 Major updates:
* Rejig of playbook to load roles from ansible-galaxy
* Remove ansible-nas role and move tasks to tasks directory
* Add InfluxDB/Telegraf/Grafana for monitoring & dashboards
* Automatically configure InfluxDB as a datasource in Grafana
* Switch to ZFS Docker driver
* Add note about switching to overlay2 Docker driver if required
2018-04-08 23:29:25 +01:00

422 lines
15 KiB
Text

# 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 = "{{ stat_collection_interval }}"
## 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 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 = true
## Specify the log file name. The empty string means to log to stderr.
logfile = ""
## Override default hostname, if empty use os.Hostname()
hostname = "{{ ansible_nas_hostname }}"
## If set to true, do no set the "host" tag in the telegraf agent.
omit_hostname = false
###############################################################################
# OUTPUT PLUGINS #
###############################################################################
# Configuration for sending metrics to InfluxDB
[[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 = ["http://{{ hostvars[inventory_hostname]['ansible_default_ipv4']['address'] }}:8086"]
## The target database for metrics; will be created as needed.
database = "telegraf"
## 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 = false
## Name of existing retention policy to write to. Empty string writes to
## the default retention policy.
# retention_policy = ""
## Write consistency (clusters only), can be: "any", "one", "quorum", "all"
# write_consistency = "any"
## Timeout for HTTP messages.
# timeout = "5s"
## HTTP Basic Auth
# username = "telegraf"
# password = "metricsmetricsmetricsmetrics"
## HTTP User-Agent
# user_agent = "telegraf"
## UDP payload size is the maximum packet size to send.
# 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
## 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
###############################################################################
# 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
## 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"]
# 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
# Read metrics about system load & uptime
[[inputs.system]]
# no configuration
# Read metrics about docker containers
[[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)
gather_services = false
## Only collect metrics for these containers, collect all if empty
container_names = []
## Containers to include and exclude. Globs accepted.
## Note that an empty array for both will include all containers
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.
# 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...) and
## network (eth0, eth1, ...) stats or not
perdevice = true
## Whether to report for each container total blkio and network stats or not
total = false
## Which environment variables should we use as a tag
##tag_env = ["JAVA_HOME", "HEAP_SIZE"]
## 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 = []
## 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
# # Monitor disks' temperatures using hddtemp
# [[inputs.hddtemp]]
# ## By default, telegraf gathers temps data from all disks detected by the
# ## hddtemp.
# ##
# ## Only collect temps from the selected disks.
# ##
# ## A * as the device name will return the temperature values of all disks.
# ##
# # address = "127.0.0.1:7634"
# # devices = ["sda", "*"]
# 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"]
##
## On linux systems telegraf also collects protocol stats.
## Setting ignore_protocol_stats to true will skip reporting of protocol metrics.
##
# ignore_protocol_stats = false
##
# Read TCP metrics such as established, time wait and sockets counts.
[[inputs.netstat]]
# no configuration
# Monitor sensors, requires lm-sensors package
[[inputs.sensors]]
## Remove numbers from field names.
## If true, a field name like 'temp1_input' will be changed to 'temp_input'.
# remove_numbers = true
# # Read metrics from storage devices supporting S.M.A.R.T.
# [[inputs.smart]]
# ## Optionally specify the path to the smartctl executable
# # path = "/usr/bin/smartctl"
# #
# ## On most platforms smartctl requires root access.
# ## Setting 'use_sudo' to true will make use of sudo to run smartctl.
# ## Sudo must be configured to to allow the telegraf user to run smartctl
# ## with out password.
# # use_sudo = false
# #
# ## Skip checking disks in this power mode. Defaults to
# ## "standby" to not wake up disks that have stoped rotating.
# ## See --nocheck in the man pages for smartctl.
# ## smartctl version 5.41 and 5.42 have faulty detection of
# ## power mode and might require changing this value to
# ## "never" depending on your disks.
# # nocheck = "standby"
# #
# ## Gather detailed metrics for each SMART Attribute.
# ## Defaults to "false"
# ##
# # attributes = false
# #
# ## Optionally specify devices to exclude from reporting.
# # excludes = [ "/dev/pass6" ]
# #
# ## Optionally specify devices and device type, if unset
# ## a scan (smartctl --scan) for S.M.A.R.T. devices will
# ## done and all found will be included except for the
# ## excluded in excludes.
# # devices = [ "/dev/ada0 -d atacam" ]
# # Sysstat metrics collector
# [[inputs.sysstat]]
# ## Path to the sadc command.
# #
# ## Common Defaults:
# ## Debian/Ubuntu: /usr/lib/sysstat/sadc
# ## Arch: /usr/lib/sa/sadc
# ## RHEL/CentOS: /usr/lib64/sa/sadc
# sadc_path = "/usr/lib/sa/sadc" # required
# #
# #
# ## Path to the sadf command, if it is not in PATH
# # sadf_path = "/usr/bin/sadf"
# #
# #
# ## Activities is a list of activities, that are passed as argument to the
# ## sadc collector utility (e.g: DISK, SNMP etc...)
# ## The more activities that are added, the more data is collected.
# # activities = ["DISK"]
# #
# #
# ## Group metrics to measurements.
# ##
# ## If group is false each metric will be prefixed with a description
# ## and represents itself a measurement.
# ##
# ## If Group is true, corresponding metrics are grouped to a single measurement.
# # group = true
# #
# #
# ## Options for the sadf command. The values on the left represent the sadf
# ## options and the values on the right their description (which are used for
# ## grouping and prefixing metrics).
# ##
# ## Run 'sar -h' or 'man sar' to find out the supported options for your
# ## sysstat version.
# [inputs.sysstat.options]
# -C = "cpu"
# -B = "paging"
# -b = "io"
# -d = "disk" # requires DISK activity
# "-n ALL" = "network"
# "-P ALL" = "per_cpu"
# -q = "queue"
# -R = "mem"
# -r = "mem_util"
# -S = "swap_util"
# -u = "cpu_util"
# -v = "inode"
# -W = "swap"
# -w = "task"
# # -H = "hugepages" # only available for newer linux distributions
# # "-I ALL" = "interrupts" # requires INT activity
# #
# #
# ## Device tags can be used to add additional tags for devices.
# ## For example the configuration below adds a tag vg with value rootvg for
# ## all metrics with sda devices.
# # [[inputs.sysstat.device_tags.sda]]
# # vg = "rootvg"
# Read metrics of ZFS from arcstats, zfetchstats, vdev_cache_stats, and pools
[[inputs.zfs]]
## ZFS kstat path. Ignored on FreeBSD
## If not specified, then default is:
# kstatPath = "/proc/spl/kstat/zfs"
## By default, telegraf gather all zfs stats
## If not specified, then default is:
# kstatMetrics = ["arcstats", "zfetchstats", "vdev_cache_stats"]
## For Linux, the default is:
# kstatMetrics = ["abdstats", "arcstats", "dnodestats", "dbufcachestats",
# "dmu_tx", "fm", "vdev_mirror_stats", "zfetchstats", "zil"]
## By default, don't gather zpool stats
# poolMetrics = false