Efremenko Arhip
dc92121acc
Align the coordinator with the master PLAN.md (CTX-00, CTX-04) and harden process startup. - CTX-00: freeze docs/api-contract.md as the v1 source of truth for the Go coordinator and Python worker. - CTX-04: worker registry — workers table (migration 0002), domain.Worker, RegisterWorker use case, WorkerRepository, and POST /workers/register. - Contract alignment: claim uses `capabilities` (was `workloads`), COORDINATOR_TOKEN env (WORKER_AUTH_TOKEN kept as fallback), and GET /health now reports database readiness (503 when the DB is down). - Logging: logs are teed to stdout and an optional rotated file (LOG_FILE) via lumberjack, so they survive a container rebuild. - Startup resilience: the initial DB connection is retried with backoff, so the coordinator waits for Postgres to boot instead of crash-looping.
74 lines
2.4 KiB
YAML
74 lines
2.4 KiB
YAML
name: scimesh
|
|
|
|
services:
|
|
postgres:
|
|
image: postgres:16-alpine
|
|
environment:
|
|
POSTGRES_USER: ${POSTGRES_USER:-scimesh}
|
|
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-scimesh}
|
|
POSTGRES_DB: ${POSTGRES_DB:-scimesh}
|
|
ports:
|
|
- "${POSTGRES_PORT:-5432}:5432"
|
|
volumes:
|
|
- pgdata:/var/lib/postgresql/data
|
|
healthcheck:
|
|
# Everything else waits on this, so the check must prove the server
|
|
# accepts queries — not merely that the port is open.
|
|
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-scimesh} -d ${POSTGRES_DB:-scimesh}"]
|
|
interval: 5s
|
|
timeout: 3s
|
|
retries: 10
|
|
start_period: 5s
|
|
|
|
# One-shot: applies migrations, then exits. Schema changes stay an explicit
|
|
# deployment step — the coordinator binary never migrates on startup.
|
|
migrate:
|
|
image: migrate/migrate:v4.17.1
|
|
depends_on:
|
|
postgres:
|
|
condition: service_healthy
|
|
volumes:
|
|
- ./migrations:/migrations:ro
|
|
command:
|
|
- -path=/migrations
|
|
- -database=postgres://${POSTGRES_USER:-scimesh}:${POSTGRES_PASSWORD:-scimesh}@postgres:5432/${POSTGRES_DB:-scimesh}?sslmode=disable
|
|
- up
|
|
restart: on-failure
|
|
|
|
coordinator:
|
|
build:
|
|
context: .
|
|
depends_on:
|
|
postgres:
|
|
condition: service_healthy
|
|
# Start only once the schema exists, otherwise the first query fails.
|
|
migrate:
|
|
condition: service_completed_successfully
|
|
environment:
|
|
COORDINATOR_ADDR: ":8080"
|
|
# Host is the service name: compose resolves it on the project network.
|
|
DATABASE_URL: postgres://${POSTGRES_USER:-scimesh}:${POSTGRES_PASSWORD:-scimesh}@postgres:5432/${POSTGRES_DB:-scimesh}?sslmode=disable
|
|
WORKER_AUTH_TOKEN: ${WORKER_AUTH_TOKEN:-dev-token}
|
|
DB_MAX_CONNS: "10"
|
|
REQUEST_TIMEOUT: "15s"
|
|
LEASE_DURATION: "2m"
|
|
REAPER_INTERVAL: "30s"
|
|
LOG_LEVEL: ${LOG_LEVEL:-info}
|
|
# Logs are teed to stdout (docker logs) and this rotated file, which lives
|
|
# on the mounted ./logs directory so it survives a rebuild.
|
|
LOG_FILE: /var/log/scimesh/coordinator.log
|
|
ports:
|
|
- "${COORDINATOR_PORT:-8080}:8080"
|
|
volumes:
|
|
- ./logs:/var/log/scimesh
|
|
healthcheck:
|
|
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:8080/health"]
|
|
interval: 10s
|
|
timeout: 3s
|
|
retries: 3
|
|
start_period: 5s
|
|
restart: unless-stopped
|
|
|
|
volumes:
|
|
pgdata:
|