Server monitoring with TIG
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
telegraf-influxDB-grafana/telegraf/telegraf.conf

329 lines
12 KiB

# 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.
# 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"
# Configuration for telegraf agent
[agent]
## Default data collection interval for all inputs
interval = "5s"
## Rounds collection interval to 'interval'
## ie, if interval="10s" then always collect on :00, :10, :20, etc.
round_interval = true
## Telegraf will cache metric_buffer_limit metrics for each output, and will
## flush this buffer on a successful write.
metric_buffer_limit = 10000
## Flush the buffer whenever full, regardless of flush_interval.
flush_buffer_when_full = true
## 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 = "1s"
## 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"
## Run telegraf in debug mode
debug = false
## Run telegraf in quiet mode
quiet = false
## Override default hostname, if empty use os.Hostname()
hostname = ""
###############################################################################
# OUTPUTS #
###############################################################################
# Configuration for influxdb server to send metrics to
[[outputs.influxdb]]
# The full HTTP or UDP endpoint URL for your InfluxDB instance.
# Multiple urls can be specified but it is assumed that they are part of the same
# cluster, this means that only ONE of the urls will be written to each interval.
# urls = ["udp://localhost:8089"] # UDP endpoint example
urls = ["http://influxdb:8086"] # required
# The target database for metrics (telegraf will create it if not exists)
database = "influx" # required
# Precision of writes, valid values are "ns", "us" (or "µs"), "ms", "s", "m", "h".
# note: using second precision greatly helps InfluxDB compression
precision = "s"
## Write timeout (for the InfluxDB client), formatted as a string.
## If not provided, will default to 5s. 0s means no timeout (not recommended).
timeout = "5s"
username = ""
password = ""
# Set the user agent for HTTP POSTs (can be useful for log differentiation)
# user_agent = "telegraf"
# Set UDP payload size, defaults to InfluxDB UDP Client default (512 bytes)
# udp_payload = 512
###############################################################################
# INPUTS #
###############################################################################
# Statsd Server
[[inputs.statsd]]
## Protocol, must be "tcp", "udp4", "udp6" or "udp" (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]
## separator to use between elements of a statsd metric
metric_separator = "_"
## Parses tags in the datadog statsd format
## http://docs.datadoghq.com/guides/dogstatsd/
parse_data_dog_tags = false
## Statsd data translation templates, more info can be read here:
## https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md#graphite
# templates = [
# "cpu.* measurement*"
# ]
## Number of UDP messages allowed to queue up, once filled,
## the statsd server will start dropping packets
allowed_pending_messages = 10000
## Number of timing/histogram values to track per-measurement in the
## calculation of percentiles. Raising this limit increases the accuracy
## of percentiles but also increases the memory usage and cpu time.
percentile_limit = 1000
## Maximum socket buffer size in bytes, once the buffer fills up, metrics
## will start dropping. Defaults to the OS default.
# read_buffer_size = 65535
# 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
## Comment this line if you want the raw CPU time metrics
fielddrop = ["time_*"]
[[inputs.temp]]
# no configuration
# Read metrics about disk usage by mount point
[[inputs.disk]]
## By default, telegraf gather stats for all mountpoints.
## Setting mountpoints will restrict the stats to the specified mountpoints.
# mount_points = ["/"]
## Ignore some mountpoints by filesystem type. For example (dev)tmpfs (usually
## present on /run, /var/run, /dev/shm or /dev).
ignore_fs = ["tmpfs", "devtmpfs"]
# 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"]
## Uncomment the following line if you need disk serial numbers.
# skip_serial_number = false
# 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 network interface usage
[[inputs.net]]
# collect data only about specific interfaces
# interfaces = ["eth0"]
[[inputs.netstat]]
# no configuration
[[inputs.interrupts]]
# no configuration
[[inputs.linux_sysctl_fs]]
# 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)
## 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 = ["prometheus", "cadvisor", "grafana", "telegraf", "influxdb", "pushgateway"]
## 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 = []
## 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
## FOR PI TEMP
[[inputs.file]]
files = ["/sys/class/thermal/thermal_zone0/temp"]
name_override = "cpu_temperature"
data_format = "value"
data_type = "integer"
[[inputs.exec]]
commands = [ "vcgencmd measure_temp"]
name_override = "gpu_temperature"
data_format = "grok"
grok_patterns = ["%{NUMBER:value:float}"]
[[inputs.exec]]
commands = ["vcgencmd measure_clock arm"]
name_override = "cpu_clock"
data_format = "grok"
grok_patterns = ["=%{NUMBER:value:float}"]
[[inputs.exec]]
commands = [ "vcgencmd measure_volts core"]
name_override = "volts"
data_format = "grok"
grok_patterns = ["%{NUMBER:value:float}"]
[[inputs.exec]]
commands = [ "vcgencmd measure_volts sdram_c"]
name_override = "volts"
data_format = "grok"
grok_patterns = ["%{NUMBER:sdramc:float}"]
[[inputs.exec]]
commands = [ "vcgencmd measure_volts sdram_i"]
name_override = "volts"
data_format = "grok"
grok_patterns = ["%{NUMBER:sdrami:float}"]
[[inputs.exec]]
commands = [ "vcgencmd measure_volts sdram_p"]
name_override = "volts"
data_format = "grok"
grok_patterns = ["%{NUMBER:sdramp:float}"]
## FOR PI TEMP