Files
composes/alloy/docker-compose.yml
T
tiennm99 b055d4f66b refactor: tighten filters, add missing metrics + journal labels
correctness:
- drop dead ALLOY_HOSTNAME env passthrough (alloy uses constants.hostname)
- tighten netdev regex so iface names like 'lore0' no longer match 'lo'
- widen alloy-container drop to /alloy.* (catches renamed variants)

more info for same cost (~80 extra series, still ~1.6k of 10k):
- add MemFree, disk IOPS (reads/writes_completed), disk saturation
  (io_time_weighted), inode tracking (filesystem_files, _files_free),
  network drops, container working_set memory, container_last_seen,
  machine_scrape_error
- add journal unit + level labels (log querying by service/severity)
- docker discovery refresh 60s -> 5s (fast pickup of new containers)

efficiency:
- loki batch_wait=5s, batch_size=1MiB (~5x fewer push requests)

layout:
- drop redundant expose: [12345] (other containers can reach it anyway)
2026-04-24 09:27:57 +07:00

136 lines
4.9 KiB
YAML

# Required shell env vars (export before `docker compose up`):
# ALLOY_HOSTNAME PROM_URL PROM_USER LOKI_URL LOKI_USER GRAFANA_TOKEN
# UI reachable only from inside the Docker network: http://alloy:12345
services:
alloy:
image: grafana/alloy:v1.10.0
container_name: alloy
restart: unless-stopped
hostname: ${ALLOY_HOSTNAME:?required}
user: "0:0" # root needed for docker.sock + journal files
environment:
PROM_URL: ${PROM_URL:?required}
PROM_USER: ${PROM_USER:?required}
LOKI_URL: ${LOKI_URL:?required}
LOKI_USER: ${LOKI_USER:?required}
GRAFANA_TOKEN: ${GRAFANA_TOKEN:?required}
security_opt: [ "no-new-privileges:true" ]
cap_drop: [ ALL ]
volumes:
- alloy-data:/var/lib/alloy/data
- /var/run/docker.sock:/var/run/docker.sock:ro
- /var/lib/docker:/var/lib/docker:ro
- /proc:/host/proc:ro
- /sys:/host/sys:ro
- /:/rootfs:ro,rslave
- /var/log/journal:/var/log/journal:ro
configs:
- { source: alloy_config, target: /etc/alloy/config.alloy }
command: [ run, --server.http.listen-addr=0.0.0.0:12345, --storage.path=/var/lib/alloy/data, /etc/alloy/config.alloy ]
volumes:
alloy-data:
configs:
alloy_config:
content: |
prometheus.remote_write "gc" {
endpoint {
url = sys.env("PROM_URL")
basic_auth {
username = sys.env("PROM_USER")
password = sys.env("GRAFANA_TOKEN")
}
}
}
loki.write "gc" {
endpoint {
url = sys.env("LOKI_URL")
batch_wait = "5s"
batch_size = "1MiB"
basic_auth {
username = sys.env("LOKI_USER")
password = sys.env("GRAFANA_TOKEN")
}
}
}
prometheus.exporter.unix "host" {
rootfs_path = "/rootfs"
procfs_path = "/host/proc"
sysfs_path = "/host/sys"
filesystem { mount_points_exclude = "^/(dev|proc|sys|run|var/lib/docker)($|/)" }
netdev { device_exclude = "^(veth.*|docker.*|br-.*|lo)$" }
}
prometheus.exporter.cadvisor "containers" {
docker_only = true
}
discovery.relabel "metrics" {
targets = array.concat(
prometheus.exporter.unix.host.targets,
prometheus.exporter.cadvisor.containers.targets,
)
rule { target_label = "instance" replacement = constants.hostname }
}
prometheus.scrape "metrics" {
targets = discovery.relabel.metrics.output
forward_to = [prometheus.relabel.filter.receiver]
scrape_interval = "60s"
}
// Keep only metrics powering standard dashboards.
// Essential for the 10k active-series cap on Grafana Cloud Free.
prometheus.relabel "filter" {
forward_to = [prometheus.remote_write.gc.receiver]
rule {
source_labels = ["__name__"]
action = "keep"
regex = "up|node_(cpu_seconds_total|load(1|5|15)|boot_time_seconds|uname_info|memory_(MemTotal|MemFree|MemAvailable|Cached|Buffers|SwapTotal|SwapFree)_bytes|filesystem_(size|avail)_bytes|filesystem_(files|files_free|readonly)|disk_(reads|writes)_completed_total|disk_(read|written)_bytes_total|disk_io_time(_weighted)?_seconds_total|network_(receive|transmit)_(bytes|errs|drop)_total)|container_(cpu_usage_seconds_total|memory_(usage|working_set)_bytes|fs_(usage|limit)_bytes|network_(receive|transmit)_bytes_total|last_seen)|machine_(memory_bytes|scrape_error)"
}
}
discovery.docker "containers" {
host = "unix:///var/run/docker.sock"
refresh_interval = "5s"
}
discovery.relabel "container_logs" {
targets = discovery.docker.containers.targets
rule { target_label = "instance" replacement = constants.hostname }
rule {
source_labels = ["__meta_docker_container_name"]
regex = "/(.*)"
target_label = "container"
}
rule {
source_labels = ["__meta_docker_container_name"]
regex = "/alloy.*"
action = "drop"
}
}
loki.source.docker "containers" {
host = "unix:///var/run/docker.sock"
targets = discovery.relabel.container_logs.output
forward_to = [loki.write.gc.receiver]
}
loki.relabel "journal" {
forward_to = []
rule { source_labels = ["__journal__systemd_unit"] target_label = "unit" }
rule { source_labels = ["__journal_priority_keyword"] target_label = "level" }
}
loki.source.journal "system" {
max_age = "12h"
path = "/var/log/journal"
forward_to = [loki.write.gc.receiver]
relabel_rules = loki.relabel.journal.rules
labels = { job = "systemd-journal", instance = constants.hostname }
}