Merge pull request 'devops(observability): add Loki + Promtail for centralised container log aggregation' (#586) from feat/issue-574-loki-promtail into main
All checks were successful
CI / Unit & Component Tests (push) Successful in 3m22s
CI / OCR Service Tests (push) Successful in 16s
CI / Backend Unit Tests (push) Successful in 4m36s
CI / fail2ban Regex (push) Successful in 40s
CI / Compose Bucket Idempotency (push) Successful in 57s

devops(observability): add Loki + Promtail for centralised container log aggregation (#586)
This commit was merged in pull request #586.
This commit is contained in:
2026-05-15 02:58:20 +02:00
7 changed files with 146 additions and 5 deletions

View File

@@ -73,9 +73,44 @@ services:
- obs-net
# --- Logs: Loki + Promtail ---
# loki: (see issue #574)
# promtail: (see issue #575)
#
loki:
image: grafana/loki:3.4.2
container_name: obs-loki
restart: unless-stopped
volumes:
- ./infra/observability/loki/loki-config.yml:/etc/loki/loki-config.yml:ro
- loki_data:/loki
command: -config.file=/etc/loki/loki-config.yml
expose:
- "3100"
healthcheck:
test: ["CMD-SHELL", "wget -qO- http://localhost:3100/ready | grep -q ready || exit 1"]
interval: 10s
timeout: 5s
retries: 5
start_period: 30s
networks:
- obs-net
promtail:
image: grafana/promtail:3.4.2
container_name: obs-promtail
restart: unless-stopped
volumes:
- ./infra/observability/promtail/promtail-config.yml:/etc/promtail/promtail-config.yml:ro
- /var/lib/docker/containers:/var/lib/docker/containers:ro
# :ro restricts file-system access but NOT Docker API permissions — a compromised Promtail has full daemon access. Accepted risk on single-operator self-hosted archive.
- /var/run/docker.sock:/var/run/docker.sock:ro
- promtail_positions:/tmp # persists positions.yaml across restarts — avoids duplicate log ingestion
command: -config.file=/etc/promtail/promtail-config.yml
networks:
- archiv-net # label discovery from application containers via Docker socket
- obs-net # log shipping to Loki
depends_on:
loki:
condition: service_healthy
# --- Traces: Tempo ---
# tempo: (see future issue)
#
@@ -102,6 +137,7 @@ networks:
volumes:
prometheus_data:
loki_data:
promtail_positions:
tempo_data:
grafana_data:
glitchtip_data:

View File

@@ -265,7 +265,40 @@ docker compose logs --tail=200 <service>
### Observability stack
An observability stack (Prometheus + Loki + Grafana) is available via `docker-compose.observability.yml` and configuration lives under `infra/observability/`. It joins the `archiv-net` Docker network to scrape the backend's management port. Full wiring and runbook documentation is tracked in issue #581.
An observability stack is available via `docker-compose.observability.yml`. Configuration lives under `infra/observability/`. Start it after the main stack is up (which creates `archiv-net`):
```bash
docker compose up -d # creates archiv-net
docker compose -f docker-compose.observability.yml up -d
```
Current services:
| Service | Image | Purpose |
|---|---|---|
| `obs-prometheus` | `prom/prometheus:v3.4.0` | Scrapes metrics from backend management port 8081 (`/actuator/prometheus`), node-exporter, and cAdvisor |
| `obs-node-exporter` | `prom/node-exporter:v1.9.0` | Host-level CPU / memory / disk / network metrics |
| `obs-cadvisor` | `gcr.io/cadvisor/cadvisor:v0.52.1` | Per-container resource metrics |
| `obs-loki` | `grafana/loki:3.4.2` | Log aggregation — receives log streams from Promtail. Port 3100 is `expose`-only (not host-bound). |
| `obs-promtail` | `grafana/promtail:3.4.2` | Log shipping agent — reads all Docker container logs via the Docker socket and forwards them to Loki with `container_name`, `compose_service`, and `compose_project` labels |
**Loki quick checks** (after ~60 s, run from inside the `obs-loki` container):
```bash
# Loki health
docker exec obs-loki wget -qO- http://localhost:3100/ready
# List labels
docker exec obs-loki wget -qO- 'http://localhost:3100/loki/api/v1/labels'
# Query logs by service (stable across dev and prod environments)
docker exec obs-loki wget -qO- \
'http://localhost:3100/loki/api/v1/query_range?query=%7Bcompose_service%3D%22backend%22%7D&limit=5'
```
**Prefer `compose_service` over `container_name` in LogQL queries**`container_name` differs between dev (`archive-backend`) and prod (`archiv-production-backend-1`), while `compose_service` is stable (`backend`, `db`, `minio`, etc.).
Prometheus port `9090` is bound to `127.0.0.1:${PORT_PROMETHEUS:-9090}` on the host. No other observability ports are host-bound. Full wiring and Grafana dashboards are tracked in issue #581.
---

View File

@@ -19,7 +19,8 @@ System_Boundary(archiv, "Familienarchiv (Docker Compose)") {
System_Boundary(observability, "Observability Stack (docker-compose.observability.yml / archiv-net)") {
Container(prometheus, "Prometheus", "prom/prometheus", "Scrapes metrics from backend management port 8081 (/actuator/prometheus). Retention and alert rules TBD — see issue #581.")
Container(loki, "Loki", "grafana/loki", "Log aggregation. Receives structured logs from the stack. Wiring TBD — see issue #581.")
Container(loki, "Loki", "grafana/loki:3.4.2", "Stores log streams from all containers.")
Container(promtail, "Promtail", "grafana/promtail:3.4.2", "Ships Docker container logs to Loki via Docker SD")
Container(grafana, "Grafana", "grafana/grafana", "Dashboards and alerting UI. Data sources: Prometheus + Loki. Wiring TBD — see issue #581.")
}
@@ -34,5 +35,6 @@ Rel(backend, ocr, "OCR job requests with presigned MinIO URL", "HTTP / REST / JS
Rel(backend, mail, "Sends notification and password-reset emails (optional)", "SMTP")
Rel(ocr, storage, "Fetches PDF via presigned URL", "HTTP / S3 presigned")
Rel(mc, storage, "Bootstraps bucket + service account on startup", "MinIO Client CLI")
Rel(promtail, loki, "Pushes log streams", "HTTP/Loki push API")
@enduml

View File

@@ -0,0 +1,40 @@
auth_enabled: false # safe — loki is not exposed beyond obs-net. Add auth before binding port 3100 to host.
server:
http_listen_port: 3100
common:
instance_addr: 127.0.0.1
path_prefix: /loki
storage:
filesystem:
chunks_directory: /loki/chunks
rules_directory: /loki/rules
replication_factor: 1
ring:
kvstore:
store: inmemory # correct for single-node — no etcd/consul needed here
schema_config:
configs:
- from: 2024-01-01
store: tsdb
object_store: filesystem
schema: v13
index:
prefix: index_
period: 24h
limits_config:
retention_period: 720h # 30 days — low-volume family archive; revisit if log volume grows
compactor:
working_directory: /loki/compactor
compaction_interval: 10m
retention_enabled: true
retention_delete_delay: 2h
retention_delete_worker_count: 150
delete_request_store: filesystem
analytics:
reporting_enabled: false # no telemetry sent to Grafana Labs

View File

@@ -0,0 +1,30 @@
server:
http_listen_port: 9080
grpc_listen_port: 0 # gRPC disabled — used for Promtail clustering only; single-node deployment
positions:
filename: /tmp/positions.yaml # /tmp is a named volume (promtail_positions) — persists across restarts
clients:
- url: http://loki:3100/loki/api/v1/push
# Loki HTTP API is unauthenticated internally. Any container on obs-net can push logs.
# Acceptable: only trusted application containers join this network.
scrape_configs:
- job_name: docker-containers
docker_sd_configs:
- host: unix:///var/run/docker.sock
refresh_interval: 5s
relabel_configs:
- source_labels: ['__meta_docker_container_name']
regex: '/(.*)'
target_label: 'container_name'
# Note: container_name differs between dev (archive-backend) and prod
# (archiv-production-backend-1). Prefer compose_service for stable LogQL
# queries across environments — it is stable: backend, db, minio, etc.
- source_labels: ['__meta_docker_container_label_com_docker_compose_service']
target_label: 'compose_service'
- source_labels: ['__meta_docker_container_label_com_docker_compose_project']
target_label: 'compose_project'
- source_labels: ['__meta_docker_container_log_stream']
target_label: 'logstream'