fzirker/homeserver
0
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity
homeserver/monitoring/telegraf/telegraf.conf
Florian Zirker a50057f711 Update monitoring
2021-09-27 20:05:47 +02:00

546 lines
18 KiB
Plaintext
Raw Blame History

# 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})
# Config Sample under https://github.com/influxdata/telegraf/blob/master/etc/telegraf.conf
# Global tags can be specified here in key="value" format.
[global_tags]
# datacenter
dc="fzirker.lan"
# 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
## 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 = ""
## 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
###############################################################################
# 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://127.0.0.1:8086"]
urls = ["http://192.168.16.5:8086"] # required
###############################################################################
# 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 = ["/hostfs", "/hostfs/mnt/sdcard"]
## Ignore mount points by filesystem type.
ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
[[inputs.disk]]
# Festplatte lange schlafen lassen :)
interval = "12h"
mount_points = ["/hostfs/mnt/wdhdd"]
# 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'
## 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"]
# 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]]
## Uncomment to remove deprecated metrics.
# fielddrop = ["uptime_format"]
# 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 = []
## Set the source tag for the metrics to the container ID hostname, eg first 12 chars
source_tag = false
## 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.
## 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...) 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 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
# # 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", "*"]
# HTTP/HTTPS request given an address a method and a timeout
[[inputs.http_response]]
## Deprecated in 1.12, use 'urls'
## Server address (default http://localhost)
# address = "http://localhost"
## List of urls to query.
urls = [
"https://florianzirker.de",
"https://cloud.florianzirker.de/login",
"https://wallabag.florianzirker.de/login",
"https://gitea.florianzirker.de/api/v1/version/",
"https://meet.florianzirker.de/",
#"https://www.feuerwehr-kapsweyer.de",
"https://ping.feuerwehr-kapsweyer.de",
"http://ping.feuerwehr-kapsweyer.de",
"http://portainer.lan",
"http://gpxviewer.lan",
"http://traefik.lan/dashboard/",
"http://heimdall.lan",
"http://monitoring.lan/login",
#"http://solarmaxpi.zirker.lan"
]
interval = "60s"
## Set http_proxy (telegraf uses the system wide proxy settings if it's is not set)
# http_proxy = "http://localhost:8888"
## Set response_timeout (default 5 seconds)
response_timeout = "10s"
## HTTP Request Method
method = "GET"
## Whether to follow redirects from the server (defaults to false)
follow_redirects = false
## Optional HTTP Request Body
# body = '''
# {'fake':'data'}
# '''
## Optional substring or regex match in body of the response
# response_string_match = "\"service_status\": \"up\""
# response_string_match = "ok"
# response_string_match = "\".*_status\".?:.?\"up\""
## 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
## HTTP Request Headers (all values must be strings)
# [inputs.http_response.headers]
# Host = "github.com"
## Interface to use when dialing an address
# interface = "eth0"
# # Collect statistics about itself
# [[inputs.internal]]
# ## If true, collect telegraf memory stats.
# # collect_memstats = true
# # 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 = ["enx001e0636be71"]
##
## 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
# Collect kernel snmp counters and network interface statistics
[[inputs.nstat]]
## file paths for proc files. If empty default paths will be used:
## /proc/net/netstat, /proc/net/snmp, /proc/net/snmp6
## These can also be overridden with env variables, see README.
proc_net_netstat = "/proc/net/netstat"
proc_net_snmp = "/proc/net/snmp"
proc_net_snmp6 = "/proc/net/snmp6"
## dump metrics with 0 values too
dump_zeros = true
# Ping given url(s) and return statistics
[[inputs.ping]]
## List of urls to ping
urls = [
"fritz-box.lan",
"wlan-ap.lan",
"drax.lan",
"florianzirker.de",
"t-online.de",
"8.8.8.8",
"4.2.2.2",
"9.9.9.9",
"example.com"
]
## Number of pings to send per collection (ping -c <COUNT>)
# count = 1
## Interval, in s, at which to ping. 0 == default (ping -i <PING_INTERVAL>)
## Not available in Windows.
ping_interval = 60.0
## Per-ping timeout, in s. 0 == no timeout (ping -W <TIMEOUT>)
# timeout = 1.0
## Total-ping deadline, in s. 0 == no deadline (ping -w <DEADLINE>)
# deadline = 10
## Interface or source address to send ping from (ping -I <INTERFACE/SRC_ADDR>)
## on Darwin and Freebsd only source address possible: (ping -S <SRC_ADDR>)
# interface = ""
## Specify the ping executable binary, default is "ping"
# binary = "ping"
## Arguments for ping command
## when arguments is not empty, other options (ping_interval, timeout, etc) will be ignored
# arguments = ["-c", "3"]
# # Monitor process cpu and memory usage
# [[inputs.procstat]]
# ## PID file to monitor process
# pid_file = "/var/run/nginx.pid"
# ## executable name (ie, pgrep <exe>)
# # exe = "nginx"
# ## pattern as argument for pgrep (ie, pgrep -f <pattern>)
# # pattern = "nginx"
# ## user as argument for pgrep (ie, pgrep -u <user>)
# # user = "nginx"
# ## Systemd unit name
# # systemd_unit = "nginx.service"
# ## CGroup name or path
# # cgroup = "systemd/system.slice/nginx.service"
#
# ## Windows service name
# # win_service = ""
#
# ## override for process_name
# ## This is optional; default is sourced from /proc/<pid>/status
# # process_name = "bar"
#
# ## Field name prefix
# # prefix = ""
#
# ## When true add the full cmdline as a tag.
# # cmdline_tag = false
#
# ## Add PID as a tag instead of a field; useful to differentiate between
# ## processes whose tags are otherwise the same. Can create a large number
# ## of series, use judiciously.
# # pid_tag = false
#
# ## Method to use when finding process IDs. Can be one of 'pgrep', or
# ## 'native'. The pgrep finder calls the pgrep executable in the PATH while
# ## the native finder performs the search directly in a manor dependent on the
# ## platform. Default is 'pgrep'
# # pid_finder = "pgrep"
# # 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
# ## without a 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 all returned S.M.A.R.T. attribute metrics and the detailed
# ## information from each drive into the 'smart_attribute' measurement.
# # 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" ]
#
# ## Timeout for the smartctl command to complete.
# # timeout = "30s"
# # 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"
# Gather systemd units state
# [[inputs.systemd_units]]
# ## Set timeout for systemctl execution
# # timeout = "1s"
# #
# ## Filter for a specific unit type, default is "service", other possible
# ## values are "socket", "target", "device", "mount", "automount", "swap",
# ## "timer", "path", "slice" and "scope ":
# unittype = "service"
# # Read metrics about temperature
[[inputs.temp]]
# no configuration
# # Reads metrics from a SSL certificate
#[[inputs.x509_cert]]
## List certificate sources
#sources = ["/etc/ssl/certs/ssl-cert-snakeoil.pem", "tcp://example.org:443"]
#sources = ["https://florianzirker.de:443", "https://cloud.florianzirker.de:443", "https://wallabag.florianzirker.de:443", "https://gitea.florianzirker.de:443", "https://meet.florianzirker.de:443", "https://www.feuerwehr-kapsweyer.de:443"]
## Timeout for SSL connection
# timeout = "5s"
## Pass a different name into the TLS request (Server Name Indication)
## example: server_name = "myhost.example.org"
# server_name = ""
## Optional TLS Config
# tls_ca = "/etc/telegraf/ca.pem"
# tls_cert = "/etc/telegraf/cert.pem"
# tls_key = "/etc/telegraf/key.pem"
Reference in a new issue View git blame Copy permalink