thermograph/observability/alloy/config.alloy
emi d138f00a20
Some checks failed
Sync infra to hosts / sync-beta (push) Has been skipped
Sync infra to hosts / sync-prod (push) Has been skipped
Sync infra to hosts / sync-dev (push) Failing after 6s
secrets-guard / encrypted (push) Successful in 6s
shell-lint / shellcheck (push) Successful in 13s
Validate observability stack / validate (push) Successful in 17s
PR build (required check) / changes (pull_request) Successful in 6s
secrets-guard / encrypted (pull_request) Successful in 5s
PR build (required check) / build-backend (pull_request) Has been skipped
shell-lint / shellcheck (pull_request) Successful in 6s
PR build (required check) / build-frontend (pull_request) Has been skipped
PR build (required check) / validate-observability (pull_request) Successful in 18s
PR build (required check) / gate (pull_request) Successful in 2s
infra: split the estate into vps1/vps2 — beta joins prod, dev gets a home (#103)
2026-07-26 06:56:38 +00:00

273 lines
11 KiB
Text

// Grafana Alloy — the log collector that runs on EVERY node (vps1, vps2). It
// gathers three sources and ships them to the central Loki on vps1:
//
// 1. Every Docker container's stdout/stderr (app, db, and on vps1 forgejo +
// the monitoring stack itself) via the Docker socket.
// 2. Caddy's host access logs (/var/log/caddy/*.log) — the reverse proxy runs
// on the host, not in a container, so its logs aren't in Docker.
// 3. The app's structured JSON logs (errors/access/audit *.jsonl) from the
// `applogs` Docker volumes, parsed so `level`/`tag`/`phase` become labels.
//
// ---------------------------------------------------------------------------
// `host` IS THE ENVIRONMENT, AND IT IS NO LONGER THE NODE
// ---------------------------------------------------------------------------
// Every query, dashboard and alert in this estate slices on host="prod" |
// "beta" | "dev". That label used to be an EXTERNAL label — one value stamped
// on everything the agent shipped — which was exact while one node ran exactly
// one environment.
//
// vps2 now runs prod AND beta. A single external label there would have marked
// every beta container, every beta access log and every beta JSON line as
// `prod`: not a cosmetic problem, but wrong data feeding the prod alert rules,
// and beta's own alerts (NotifierHeartbeatMissingBeta) firing on prod's
// traffic or never firing at all.
//
// So `host` is now derived PER SOURCE — from the container's stack prefix, from
// the access-log filename, from which log volume a JSON line came out of — and
// ALLOY_ENV supplies the fallback for anything on the node that isn't
// environment-specific (Forgejo, Grafana, Loki, the portfolio site). The node
// itself is still labelled, as `node`, because "which machine" is a real
// question too — it is just a different question from "which environment".
//
// Per-node settings come from the environment (see docker-compose.agent.yml):
// ALLOY_NODE — the MACHINE this agent runs on (vps1 | vps2 | desktop)
// ALLOY_ENV — the default environment label for logs on this node that
// aren't attributable to a specific stack (vps1 -> dev,
// vps2 -> prod)
// LOKI_URL — where to push (http://10.10.0.2:3100/loki/api/v1/push over wg0)
livedebugging { enabled = false }
// --- 1. All Docker container logs ------------------------------------------------
// refresh_interval defaults to 60s; Swarm task churn reshuffles the target set on
// roughly that cadence, which restarts tailers ~every 90s and was costing ~11% of
// Alloy's own CPU in tailer restarts alone. 5m is still fast enough to pick up a
// real deploy without paying that churn cost.
discovery.docker "containers" {
host = "unix:///var/run/docker.sock"
refresh_interval = "5m"
}
// Turn Docker metadata into tidy labels: `container` (short name) and `service`
// (the compose service, e.g. app/db). Drop noise/duplicate containers so Loki never
// ingests them: Alloy itself (loop), the autoscaler, throwaway `thermograph-test_*`
// stacks, the loopback LB bridge (`thermograph-lb`, pure plumbing, nothing to debug
// from its logs), and the app's own worker (`thermograph_worker`'s stdout is 100%
// `/healthz` poll noise — the app's `access/*.jsonl` under source #3 is a strict
// superset of anything useful it logs).
discovery.relabel "containers" {
targets = discovery.docker.containers.targets
rule {
source_labels = ["__meta_docker_container_name"]
regex = "/(.*)"
target_label = "container"
}
rule {
source_labels = ["__meta_docker_container_label_com_docker_compose_service"]
target_label = "service"
}
// --- environment attribution -------------------------------------------
// Relabel rules are applied in order and a later write to the same target
// wins, so this is "default, then override with anything more specific".
//
// The regexes are fully anchored (Prometheus relabel semantics), which is
// what keeps `/thermograph_web.1.x` and `/thermograph-beta_beta-web.1.x`
// from matching each other: prod's stack prefix ends in an underscore,
// beta's in `-beta_`.
rule {
source_labels = ["__meta_docker_container_name"]
regex = ".*"
target_label = "host"
replacement = sys.env("ALLOY_ENV")
}
rule {
source_labels = ["__meta_docker_container_name"]
regex = "/thermograph_.*"
target_label = "host"
replacement = "prod"
}
rule {
source_labels = ["__meta_docker_container_name"]
regex = "/thermograph-beta_.*"
target_label = "host"
replacement = "beta"
}
rule {
source_labels = ["__meta_docker_container_name"]
regex = "/thermograph-dev[-_].*"
target_label = "host"
replacement = "dev"
}
// Drop noise/duplicate containers, per environment. Beta's equivalents are
// listed explicitly: its LB is `thermograph-beta-lb` (which does NOT match
// `thermograph-lb.*`) and its worker is `thermograph-beta_beta-worker`, so
// omitting them would have quietly re-admitted exactly the healthz-poll
// noise the prod entries exist to exclude.
rule {
source_labels = ["container"]
regex = "(alloy|autoscaler|thermograph-test_.*|thermograph-lb|thermograph-beta-lb|thermograph_worker|thermograph-beta_beta-worker).*"
action = "drop"
}
}
// Pass RAW targets here (not discovery.relabel.containers.output) alongside
// relabel_rules: loki.source.docker applies relabel_rules itself, once, using the
// __meta_docker_* metadata it still holds at collection time. Passing the
// already-relabelled output *and* relabel_rules ran the same rules twice per log
// entry, and made the drop rules above a no-op on the second pass since the
// __meta_docker_* labels are already gone from the pre-relabelled output.
loki.source.docker "containers" {
host = "unix:///var/run/docker.sock"
targets = discovery.docker.containers.targets
forward_to = [loki.write.central.receiver]
relabel_rules = discovery.relabel.containers.rules
labels = { job = "docker" }
}
// --- 2. Caddy host access logs ---------------------------------------------------
// sync_period (glob rescan) defaults to 10s; 1m is plenty for a log file that only
// appears/rotates on the order of hours.
local.file_match "caddy" {
path_targets = [{ __path__ = "/var/log/caddy/*.log", job = "caddy" }]
sync_period = "1m"
}
loki.source.file "caddy" {
targets = local.file_match.caddy.targets
forward_to = [loki.process.caddy.receiver]
// PollingFileWatcher defaults (250ms/250ms) stat every tailed file 4x/second
// forever. Caddy's access log doesn't need sub-second latency into Loki.
file_watch {
min_poll_frequency = "2s"
max_poll_frequency = "10s"
}
}
// Drop well-known crawler/bot traffic before it hits Loki. Caddy itself can't do
// this cheaply (log_skip needs Caddy >= 2.7; both hosts run older Caddy, and an
// upgrade is out of scope here), so filter it at the shipper instead.
loki.process "caddy" {
forward_to = [loki.write.central.receiver]
stage.drop {
expression = "(?i)(semrushbot|claudebot|ahrefsbot|yandexbot|bytespider|mj12bot|petalbot)"
drop_counter_reason = "crawler"
}
// Attribute each access log to an environment BY FILENAME. On vps2 one
// Caddy fronts both thermograph.org and beta.thermograph.org, so a single
// node-wide label would file every beta request under prod.
//
// By filename rather than by parsing `request.host` out of the JSON: the
// site block that writes the file is the same place the hostname is
// declared (see infra/deploy/Caddyfile.vps2), one label costs nothing to
// evaluate, and it keeps working for a non-JSON log format.
stage.static_labels {
values = { host = sys.env("ALLOY_ENV") }
}
stage.match {
selector = "{filename=~\".*/beta[.]log\"}"
stage.static_labels {
values = { host = "beta" }
}
}
stage.match {
selector = "{filename=~\".*/thermograph[.]log\"}"
stage.static_labels {
values = { host = "prod" }
}
}
}
// --- 3. App structured JSON logs (errors / access / audit) -----------------------
// Mounted read-only from the app's `applogs` volumes (see the agent compose).
// Lift `level`/`tag`/`phase` out of the JSON so they're queryable.
//
// TWO MOUNTS, NOT ONE. Each environment has its own applogs volume, and on vps2
// both exist side by side:
//
// /applogs this node's primary environment (vps2 -> prod, vps1 -> dev)
// /applogs-beta beta's, mounted on vps2 only
//
// A single mount was structurally unable to carry both: whichever volume the
// agent bound, the other environment's structured logs would never reach Loki
// at all — silently, since a missing file source is not an error. Every alert
// built on the JSON stream (the notifier heartbeats in particular) reads this.
local.file_match "app_jsonl" {
path_targets = [{ __path__ = "/applogs/**/*.jsonl", job = "app-json" }]
sync_period = "1m"
}
loki.source.file "app_jsonl" {
targets = local.file_match.app_jsonl.targets
forward_to = [loki.process.app_jsonl.receiver]
file_watch {
min_poll_frequency = "2s"
max_poll_frequency = "10s"
}
}
loki.process "app_jsonl" {
forward_to = [loki.write.central.receiver]
stage.json {
expressions = { level = "level", tag = "tag", phase = "phase", status = "status" }
}
// A record with no explicit level: an error-folder line is an error, else info.
stage.static_labels {
values = { source = "app", host = sys.env("ALLOY_ENV") }
}
stage.labels {
values = { level = "", tag = "", phase = "" }
}
}
// Beta's structured logs. Absent on vps1 (the mount simply isn't there), where
// this matches nothing and costs nothing.
local.file_match "app_jsonl_beta" {
path_targets = [{ __path__ = "/applogs-beta/**/*.jsonl", job = "app-json" }]
sync_period = "1m"
}
loki.source.file "app_jsonl_beta" {
targets = local.file_match.app_jsonl_beta.targets
forward_to = [loki.process.app_jsonl_beta.receiver]
file_watch {
min_poll_frequency = "2s"
max_poll_frequency = "10s"
}
}
loki.process "app_jsonl_beta" {
forward_to = [loki.write.central.receiver]
stage.json {
expressions = { level = "level", tag = "tag", phase = "phase", status = "status" }
}
stage.static_labels {
values = { source = "app", host = "beta" }
}
stage.labels {
values = { level = "", tag = "", phase = "" }
}
}
// --- Ship to the central Loki over the WireGuard mesh ----------------------------
loki.write "central" {
endpoint {
url = sys.env("LOKI_URL")
}
// `node` — the MACHINE, stamped on everything this agent ships. `host` is
// deliberately NOT here: it is the ENVIRONMENT, set per source above,
// because vps2 carries two of them and an external label cannot vary per
// stream. Setting host here would override that work on every line.
external_labels = { node = sys.env("ALLOY_NODE") }
}