john/docker-observation
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

cleanup and convert to periphery

Browse Source
This commit is contained in:
John Lancaster
2025-12-29 23:12:30 -06:00
parent f214a5b31e
commit 79a5345ec3
5 changed files with 79 additions and 271 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
certs/.gitkeep
View File

17
grafana-alloy/config.alloy → config.alloy
View File

@@ -9,9 +9,24 @@ prometheus.exporter.cadvisor "docker_metrics" {
prometheus.scrape "scraper" {
targets = prometheus.exporter.cadvisor.docker_metrics.targets
forward_to = [prometheus.relabel.docker_relabel.receiver]
scrape_interval = "10s"
}
prometheus.relabel "docker_relabel" {
forward_to = [prometheus.remote_write.default.receiver]
scrape_interval = "10s"
rule {
source_labels = ["container_label_com_docker_compose_project"]
target_label = "project"
action = "replace"
}
rule {
source_labels = ["container_label_com_docker_compose_service"]
target_label = "service"
action = "replace"
}
}
prometheus.remote_write "default" {

96
docker-compose.yml
View File

@@ -1,38 +1,4 @@
include:
- komodo/periphery.compose.yaml
services:
portainer-agent:
image: portainer/agent
container_name: portainer_agent
restart: always
ports:
- 9001:9001
volumes:
- /var/run/docker.sock:/var/run/docker.sock
- /var/lib/docker/volumes:/var/lib/docker/volumes
alloy:
image: grafana/alloy
container_name: grafana-alloy
restart: unless-stopped
privileged: true
volumes:
- /:/rootfs:ro
- /var/run:/var/run:rw
- /sys:/sys:ro
- /var/lib/docker:/var/lib/docker:ro
- /var/run/docker.sock:/var/run/docker.sock:ro
- /dev/disk/:/dev/disk:ro
- ./grafana-alloy/config.alloy:/etc/alloy/config.alloy
- /var/lib/ssl:/etc/alloy/certs:ro
ports:
- '12345:12345'
command:
- run
- --server.http.listen-addr=0.0.0.0:12345
- --storage.path=/var/lib/alloy/data
- /etc/alloy/config.alloy
watchtower:
image: nickfedor/watchtower
container_name: watchtower
@@ -56,3 +22,65 @@ services:
- CONTAINERS=1
- INFO=1
- PING=1
alloy:
image: grafana/alloy
container_name: grafana-alloy
restart: unless-stopped
privileged: true
hostname: ${HOSTNAME}
volumes:
- /:/rootfs:ro
- /var/run:/var/run:rw
- /sys:/sys:ro
- /var/lib/docker:/var/lib/docker:ro
- /var/run/docker.sock:/var/run/docker.sock:ro
- /dev/disk/:/dev/disk:ro
- ./config.alloy:/etc/alloy/config.alloy
- /var/lib/ssl:/etc/alloy/certs:ro
ports:
- '12345:12345'
command:
- run
- --server.http.listen-addr=0.0.0.0:12345
- --storage.path=/var/lib/alloy/data
- /etc/alloy/config.alloy
periphery:
image: ghcr.io/moghtech/komodo-periphery:${COMPOSE_KOMODO_IMAGE_TAG:-latest}
labels:
komodo.skip: # Prevent Komodo from stopping with StopAllContainers
restart: unless-stopped
## https://komo.do/docs/connect-servers#configuration
environment:
PERIPHERY_ROOT_DIRECTORY: ${PERIPHERY_ROOT_DIRECTORY:-/etc/komodo}
## Pass the same passkey as used by the Komodo Core connecting to this Periphery agent.
PERIPHERY_PASSKEYS: ${KOMODO_PASSKEY}
## Make server run over https
PERIPHERY_SSL_ENABLED: true
## Specify whether to disable the terminals feature
## and disallow remote shell access (inside the Periphery container).
PERIPHERY_DISABLE_TERMINALS: false
## If the disk size is overreporting, can use one of these to
## whitelist / blacklist the disks to filter them, whichever is easier.
## Accepts comma separated list of paths.
## Usually whitelisting just /etc/hostname gives correct size for single root disk.
PERIPHERY_INCLUDE_DISK_MOUNTS: /etc/hostname
# PERIPHERY_EXCLUDE_DISK_MOUNTS: /snap,/etc/repos
ports:
- "8120:8120"
volumes:
## Mount external docker socket
- /var/run/docker.sock:/var/run/docker.sock
## Allow Periphery to see processes outside of container
- /proc:/proc
## Specify the Periphery agent root directory.
## Must be the same inside and outside the container,
## or docker will get confused. See https://github.com/moghtech/komodo/discussions/180.
## Default: /etc/komodo.
- ${PERIPHERY_ROOT_DIRECTORY:-/etc/komodo}:${PERIPHERY_ROOT_DIRECTORY:-/etc/komodo}
## If periphery is being run remote from the core server, ports need to be exposed
# ports:
# - 8120:8120
## If you want to use a custom periphery config file, use command to pass it to periphery.
# command: periphery --config-path ${PERIPHERY_ROOT_DIRECTORY:-/etc/komodo}/periphery.config.toml

46
komodo/periphery.compose.yaml
View File

@@ -1,46 +0,0 @@
####################################
# 🦎 KOMODO COMPOSE - PERIPHERY 🦎 #
####################################
## This compose file will deploy:
## 1. Komodo Periphery
services:
periphery:
image: ghcr.io/moghtech/komodo-periphery:${COMPOSE_KOMODO_IMAGE_TAG:-latest}
labels:
komodo.skip: # Prevent Komodo from stopping with StopAllContainers
restart: unless-stopped
## https://komo.do/docs/connect-servers#configuration
environment:
PERIPHERY_ROOT_DIRECTORY: ${PERIPHERY_ROOT_DIRECTORY:-/etc/komodo}
## Pass the same passkey as used by the Komodo Core connecting to this Periphery agent.
PERIPHERY_PASSKEYS: ${KOMODO_PASSKEY}
## Make server run over https
PERIPHERY_SSL_ENABLED: true
## Specify whether to disable the terminals feature
## and disallow remote shell access (inside the Periphery container).
PERIPHERY_DISABLE_TERMINALS: false
## If the disk size is overreporting, can use one of these to
## whitelist / blacklist the disks to filter them, whichever is easier.
## Accepts comma separated list of paths.
## Usually whitelisting just /etc/hostname gives correct size for single root disk.
PERIPHERY_INCLUDE_DISK_MOUNTS: /etc/hostname
# PERIPHERY_EXCLUDE_DISK_MOUNTS: /snap,/etc/repos
ports:
- "8120:8120"
volumes:
## Mount external docker socket
- /var/run/docker.sock:/var/run/docker.sock
## Allow Periphery to see processes outside of container
- /proc:/proc
## Specify the Periphery agent root directory.
## Must be the same inside and outside the container,
## or docker will get confused. See https://github.com/moghtech/komodo/discussions/180.
## Default: /etc/komodo.
- ${PERIPHERY_ROOT_DIRECTORY:-/etc/komodo}:${PERIPHERY_ROOT_DIRECTORY:-/etc/komodo}
## If periphery is being run remote from the core server, ports need to be exposed
# ports:
# - 8120:8120
## If you want to use a custom periphery config file, use command to pass it to periphery.
# command: periphery --config-path ${PERIPHERY_ROOT_DIRECTORY:-/etc/komodo}/periphery.config.toml

189
telegraf/telegraf.conf
View File

@@ -1,189 +0,0 @@
# 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 = ""
## Log at debug level.
# debug = false
## Log only error level messages.
# quiet = false
## Log target controls the destination for logs and can be one of "file",
## "stderr" or, on Windows, "eventlog". When set to "file", the output file
## is determined by the "logfile" setting.
# logtarget = "file"
## Name of the file to be logged to when using the "file" logtarget. If set to
## the empty string then logs are written to stderr.
# logfile = ""
## The logfile will be rotated after the time interval specified. When set
## to 0 no time based rotation is performed. Logs are rotated only when
## written to, if there is no log activity rotation may be delayed.
# logfile_rotation_interval = "0d"
## The logfile will be rotated when it becomes larger than the specified
## size. When set to 0 no size based rotation is performed.
# logfile_rotation_max_size = "0MB"
## Maximum number of rotated archives to keep, any older logs are deleted.
## If set to -1, no archives are removed.
# logfile_rotation_max_archives = 5
## Pick a timezone to use when logging or type 'local' for local time.
## Example: America/Chicago
# log_with_timezone = ""
## 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
[[outputs.influxdb_v2]]
## The URLs of the InfluxDB cluster nodes.
##
## Multiple URLs can be specified for a single cluster, only ONE of the
## urls will be written to each interval.
## ex: urls = ["https://us-west-2-1.aws.cloud2.influxdata.com"]
urls = ["https://influxdb.john-stream.com"]
tls_enable = true
tls_server_name = "influxdb.john-stream.com"
## Token for authentication.
token = "$INFLUX_WRITE_TOKEN"
## Organization is the name of the organization you wish to write to; must exist.
organization = "$DOCKER_INFLUXDB_INIT_ORG"
## Destination bucket to write into.
bucket = "docker"
## The value of this tag will be used to determine the bucket. If this
## tag is not set the 'bucket' option is used as the default.
# bucket_tag = ""
## If true, the bucket tag will not be added to the metric.
# exclude_bucket_tag = false
## Timeout for HTTP messages.
# timeout = "5s"
## Additional HTTP headers
# http_headers = {"X-Special-Header" = "Special-Value"}
## 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"
## HTTP User-Agent
# user_agent = "telegraf"
## Content-Encoding for write request body, can be set to "gzip" to
## compress body or "identity" to apply no encoding.
# content_encoding = "gzip"
## Enable or disable uint support for writing uints influxdb 2.0.
# influx_uint_support = false
## Optional TLS Config for use on HTTP connections.
# 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
# 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
## 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 = []
## Objects to include for disk usage query
## Allowed values are "container", "image", "volume"
## When empty disk usage is excluded
storage_objects = ["container"]
## Timeout for docker list, info, and stats commands
timeout = "5s"
## 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", "blkio", "network"]
## 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 = []
## 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
# Needed to silence a warning, but it's irrelevant for me
# skip_processors_after_aggregators = true