Files
flowsint/docker-compose.prod.yml
harmsolo13 d4dbe8d0fe fix: replace celery container's inherited curl-based healthcheck
The celery container builds from flowsint-api/Dockerfile which carries
a HEALTHCHECK directive that does `curl -f http://localhost:5001/health`.
The API container has an HTTP server on 5001 — celery doesn't, it's a
worker. So the inherited healthcheck always fails and `docker ps` shows
celery as (unhealthy) even when the worker is actively processing jobs.

This is cosmetic noise today but bites in two real ways: (1) restart
policies that key off health won't re-up celery on a real failure
because Docker can't tell good unhealthy from bad unhealthy, (2) any
service that adds `depends_on: celery: condition: service_healthy`
will refuse to start.

Fix: add a service-level healthcheck on celery in both compose files
(prod and dev) that uses celery's own `inspect ping` primitive
against the worker's broker. Compose-level healthcheck overrides the
Dockerfile-level one, so no Dockerfile change needed.

Smoke-tested locally: container goes from (unhealthy) to (healthy)
within ~30s of restart with no other changes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-29 18:13:26 +09:30

173 lines
4.4 KiB
YAML

name: flowsint-prod
services:
postgres:
image: postgres:15-alpine
container_name: flowsint-postgres-prod
restart: always
environment:
POSTGRES_USER: ${POSTGRES_USER:-flowsint}
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-flowsint}
POSTGRES_DB: ${POSTGRES_DB:-flowsint}
ports:
- "5433:5432"
volumes:
- pg_data_prod:/var/lib/postgresql/data
networks:
- flowsint_network
healthcheck:
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-flowsint}"]
interval: 10s
timeout: 5s
retries: 5
redis:
image: redis:7-alpine
container_name: flowsint-redis-prod
restart: always
ports:
- "6379:6379"
networks:
- flowsint_network
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 10s
timeout: 5s
retries: 5
neo4j:
image: neo4j:5
container_name: flowsint-neo4j-prod
restart: always
ports:
- "7474:7474"
- "7687:7687"
environment:
- NEO4J_AUTH=${NEO4J_USERNAME}/${NEO4J_PASSWORD}
- NEO4J_PLUGINS=["apoc"]
- NEO4J_apoc_export_file_enabled=true
- NEO4J_apoc_import_file_enabled=true
- NEO4J_apoc_import_file_use__neo4j__config=true
volumes:
- neo4j_data_prod:/data
- neo4j_logs_prod:/logs
- neo4j_import_prod:/var/lib/neo4j/import
- neo4j_plugins_prod:/plugins
networks:
- flowsint_network
healthcheck:
test: cypher-shell -u ${NEO4J_USERNAME} -p ${NEO4J_PASSWORD} "RETURN 1"
interval: 5s
timeout: 5s
retries: 10
api:
build:
context: .
dockerfile: flowsint-api/Dockerfile
target: production
container_name: flowsint-api-prod
restart: always
ports:
- "5001:5001"
volumes:
- /var/run/docker.sock:/var/run/docker.sock:ro
environment:
- DATABASE_URL=postgresql://${POSTGRES_USER:-flowsint}:${POSTGRES_PASSWORD:-flowsint}@postgres:5432/${POSTGRES_DB:-flowsint}
- NEO4J_URI_BOLT=bolt://neo4j:7687
- NEO4J_USERNAME=${NEO4J_USERNAME}
- NEO4J_PASSWORD=${NEO4J_PASSWORD}
- AUTH_SECRET=${AUTH_SECRET}
- MASTER_VAULT_KEY_V1=${MASTER_VAULT_KEY_V1}
- REDIS_URL=redis://redis:6379/0
depends_on:
postgres:
condition: service_healthy
redis:
condition: service_healthy
neo4j:
condition: service_healthy
healthcheck:
test: ["CMD-SHELL", "curl -f http://localhost:5001/health || exit 1"]
interval: 10s
timeout: 5s
retries: 5
networks:
- flowsint_network
celery:
build:
context: .
dockerfile: flowsint-api/Dockerfile
target: production
container_name: flowsint-celery-prod
restart: always
command:
[
"celery",
"-A",
"flowsint_core.core.celery",
"worker",
"--loglevel=info",
"--pool=threads",
"--concurrency=10",
]
volumes:
- /var/run/docker.sock:/var/run/docker.sock:ro
environment:
- DATABASE_URL=postgresql://${POSTGRES_USER:-flowsint}:${POSTGRES_PASSWORD:-flowsint}@postgres:5432/${POSTGRES_DB:-flowsint}
- NEO4J_URI_BOLT=bolt://neo4j:7687
- NEO4J_USERNAME=${NEO4J_USERNAME}
- NEO4J_PASSWORD=${NEO4J_PASSWORD}
- MASTER_VAULT_KEY_V1=${MASTER_VAULT_KEY_V1}
- REDIS_URL=redis://redis:6379/0
- SKIP_MIGRATIONS=true
- AUTH_SECRET=${AUTH_SECRET}
healthcheck:
# Celery has no HTTP server — Dockerfile's curl-based healthcheck always fails.
# Use celery's own ping primitive instead.
test: ["CMD-SHELL", "celery -A flowsint_core.core.celery inspect ping -d celery@$$HOSTNAME || exit 1"]
interval: 30s
timeout: 10s
retries: 3
start_period: 30s
depends_on:
postgres:
condition: service_healthy
redis:
condition: service_healthy
neo4j:
condition: service_healthy
api:
condition: service_healthy
networks:
- flowsint_network
app:
build:
context: ./flowsint-app
dockerfile: Dockerfile
args:
- VITE_API_URL=${VITE_API_URL}
container_name: flowsint-app-prod
restart: always
ports:
- "5173:8080"
networks:
- flowsint_network
depends_on:
api:
condition: service_healthy
networks:
flowsint_network:
name: flowsint_network_prod
driver: bridge
volumes:
pg_data_prod:
neo4j_data_prod:
neo4j_logs_prod:
neo4j_import_prod:
neo4j_plugins_prod: