fzirker/homeserver
0
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

Influxdb over Proxy. Split telegraf in host and net

Browse source
This commit is contained in:
Florian Zirker 2022-03-06 18:33:13 +01:00
parent f0802c2242
commit c770df59f7
4 changed files with 304 additions and 186 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

34
monitoring/docker-compose.yaml
View file

@ -16,7 +16,6 @@ services:
- "traefik.http.services.monitoring.loadbalancer.server.port=3000"
- "traefik.docker.network=web"
- "docker.group=monitoring"
restart: unless-stopped
environment:
- GF_DEFAULT_INSTANCE_NAME=monitoring.${DOMAIN}
- GF_SERVER_ROOT_URL=http://monitoring.${DOMAIN}
@ -38,7 +37,7 @@ services:
grafanadb:
image: postgres
image: postgres:13
volumes:
- ${VOLUMES_PATH}/grafanadb:/var/lib/postgresql/data
networks:
@ -53,11 +52,8 @@ services:
influxdb:
# image: arm32v7/influxdb
image: influxdb:1.8
restart: unless-stopped
ports:
- 8086:8086
networks:
- web
- monitoring
@ -67,13 +63,18 @@ services:
- ${VOLUMES_PATH}/influxdb/:/var/lib/influxdb
- ${PWD}/influxdb.conf:/etc/influxdb/influxdb.conf:ro
labels:
- "traefik.enable=true"
- "traefik.http.routers.influxdb.rule=Host(`influxdb.${DOMAIN}`)"
- "traefik.http.routers.influxdb.entrypoints=web"
- "traefik.http.services.influxdb.loadbalancer.server.port=8086"
- "traefik.docker.network=web"
- "docker.group=monitoring"
##################################################################
# here starts data collection
telegraf:
telegraf_host:
image: telegraf:1.18
restart: unless-stopped
environment:
@ -84,8 +85,7 @@ services:
- HOST_VAR=/hostfs/var
- HOST_RUN=/hostfs/run
volumes:
- ./telegraf/telegraf.conf:/etc/telegraf/telegraf.conf:ro
- /var/run/docker.sock:/var/run/docker.sock:ro
- ./telegraf/telegraf_host.conf:/etc/telegraf/telegraf.conf:ro
- /var/run/utmp:/var/run/utmp:ro
- /:/hostfs:ro
network_mode: "host"
@ -93,10 +93,26 @@ services:
- "docker.group=monitoring"
depends_on:
- influxdb
telegraf_net:
image: telegraf:1.18
restart: unless-stopped
volumes:
- ./telegraf/telegraf_net.conf:/etc/telegraf/telegraf.conf:ro
networks:
- monitoring
- dockersocket
labels:
- "docker.group=monitoring"
depends_on:
- influxdb
dns:
- 9.9.9.9
- 192.168.16.5
networks:
monitoring:
web:
external: true
dockersocket:
external: true

178
monitoring/telegraf/telegraf.conf → monitoring/telegraf/telegraf_host.conf
View file

@ -80,7 +80,7 @@
# 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
urls = ["http://influxdb.lan"] # required
###############################################################################
@ -170,141 +170,6 @@
# 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)
@ -337,47 +202,6 @@ interfaces = ["enx001e0636be71"]
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

262
monitoring/telegraf/telegraf_net.conf Normal file
View file

@ -0,0 +1,262 @@
# 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://influxdb.lan"] # required
###############################################################################
# INPUT PLUGINS #
###############################################################################
# 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"
endpoint = "tcp://docker-socket-proxy:2375"
## 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
# 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"]

16
proxy/docker-compose.yaml
View file

@ -24,6 +24,20 @@ services:
- host.docker.internal:172.17.0.1
docker-socket-proxy:
image: tecnativa/docker-socket-proxy
restart: unless-stopped
volumes:
- /var/run/docker.sock:/var/run/docker.sock:ro
environment:
# grant privileges as environment variables: https://github.com/Tecnativa/docker-socket-proxy#grant-or-revoke-access-to-certain-api-sections
- CONTAINERS=1
- INFO=1
networks:
- dockersocket
privileged: true
whoami:
image: containous/whoami
networks:
@ -40,4 +54,6 @@ services:
networks:
web:
external: true
dockersocket:
external: true