Files
templates/blueprints/erpnext-v16/docker-compose.yml
Mauricio Siu c7487d8c09 fix: db healthcheck window too short and blocking depends_on aborted deploy
The deploy failed with 'dependency failed to start: container db-1 is
unhealthy'. Root cause: the MariaDB 11.8 healthcheck allowed only ~40s
(start_period 10s + 3x10s retries) before flagging the container
unhealthy, which is not enough for the first-boot datadir
initialization on a modest VPS. Since create-site depended on
db:service_healthy, docker compose up -d aborted the whole deploy.

Fixes, following the pattern of the existing working erpnext template:
- Extend the db healthcheck window (start_period 120s, 30 retries) so
  first-boot initialization does not mark the container unhealthy.
- Drop depends_on from the one-shot create-site and migration jobs and
  gate create-site with wait-for-it (db/redis) inside its command, so
  docker compose up -d returns without blocking on the multi-minute
  site creation and cannot fail on transient health states.

Verified on a fresh deploy: all services up, create-site installed
frappe + erpnext and enabled the scheduler, frontend serves the
ERPNext login page with HTTP 200.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-08 02:44:14 -06:00

301 lines
8.3 KiB
YAML

x-custom-image: &custom_image
image: ${IMAGE_NAME:-docker.io/frappe/erpnext}:${VERSION:-version-16}
pull_policy: ${PULL_POLICY:-always}
deploy:
restart_policy:
condition: always
services:
backend:
<<: *custom_image
volumes:
- sites:/home/frappe/frappe-bench/sites
healthcheck:
test: ["CMD", "wait-for-it", "127.0.0.1:8000"]
interval: 2s
timeout: 10s
retries: 30
frontend:
<<: *custom_image
command:
- nginx-entrypoint.sh
depends_on:
backend:
condition: service_started
websocket:
condition: service_started
environment:
BACKEND: backend:8000
FRAPPE_SITE_NAME_HEADER: ${FRAPPE_SITE_NAME_HEADER:-$$host}
SOCKETIO: websocket:9000
UPSTREAM_REAL_IP_ADDRESS: 127.0.0.1
UPSTREAM_REAL_IP_HEADER: X-Forwarded-For
UPSTREAM_REAL_IP_RECURSIVE: "off"
volumes:
- sites:/home/frappe/frappe-bench/sites
healthcheck:
test: ["CMD", "wait-for-it", "127.0.0.1:8080"]
interval: 2s
timeout: 30s
retries: 30
queue-default:
<<: *custom_image
command:
- bench
- worker
- --queue
- default
volumes:
- sites:/home/frappe/frappe-bench/sites
healthcheck:
test: ["CMD", "wait-for-it", "redis-queue:6379"]
interval: 2s
timeout: 10s
retries: 30
depends_on:
configurator:
condition: service_completed_successfully
queue-long:
<<: *custom_image
command:
- bench
- worker
- --queue
- long
volumes:
- sites:/home/frappe/frappe-bench/sites
healthcheck:
test: ["CMD", "wait-for-it", "redis-queue:6379"]
interval: 2s
timeout: 10s
retries: 30
depends_on:
configurator:
condition: service_completed_successfully
queue-short:
<<: *custom_image
command:
- bench
- worker
- --queue
- short
volumes:
- sites:/home/frappe/frappe-bench/sites
healthcheck:
test: ["CMD", "wait-for-it", "redis-queue:6379"]
interval: 2s
timeout: 10s
retries: 30
depends_on:
configurator:
condition: service_completed_successfully
scheduler:
<<: *custom_image
healthcheck:
test: ["CMD", "wait-for-it", "redis-queue:6379"]
interval: 2s
timeout: 10s
retries: 30
command:
- bench
- schedule
depends_on:
configurator:
condition: service_completed_successfully
volumes:
- sites:/home/frappe/frappe-bench/sites
websocket:
<<: *custom_image
healthcheck:
test: ["CMD", "wait-for-it", "websocket:9000"]
interval: 2s
timeout: 10s
retries: 30
command:
- node
- /home/frappe/frappe-bench/apps/frappe/socketio.js
depends_on:
configurator:
condition: service_completed_successfully
volumes:
- sites:/home/frappe/frappe-bench/sites
configurator:
<<: *custom_image
deploy:
mode: replicated
replicas: ${CONFIGURE:-0}
restart_policy:
condition: none
entrypoint: ["bash", "-c"]
command:
- >
echo "[configurator] starting";
if [[ $${REGENERATE_APPS_TXT} == "1" ]]; then
echo "[configurator] regenerating sites/apps.txt";
ls -1 apps > sites/apps.txt;
fi;
existing_db_host=$$(grep -hs '^' sites/common_site_config.json | jq -r ".db_host // empty" 2>/dev/null || true);
if [[ -n "$${existing_db_host}" ]]; then
echo "[configurator] common_site_config.json already configured, skipping";
exit 0;
fi;
echo "[configurator] applying bench global config";
bench set-config -g db_host $$DB_HOST;
bench set-config -gp db_port $$DB_PORT;
bench set-config -g redis_cache "redis://$$REDIS_CACHE";
bench set-config -g redis_queue "redis://$$REDIS_QUEUE";
bench set-config -g redis_socketio "redis://$$REDIS_SOCKETIO";
bench set-config -gp socketio_port $$SOCKETIO_PORT;
echo "[configurator] done";
environment:
DB_HOST: "${DB_HOST:-db}"
DB_PORT: "3306"
REDIS_CACHE: redis-cache:6379
REDIS_QUEUE: redis-queue:6379
REDIS_SOCKETIO: redis-socketio:6379
SOCKETIO_PORT: "9000"
REGENERATE_APPS_TXT: "${REGENERATE_APPS_TXT:-0}"
volumes:
- sites:/home/frappe/frappe-bench/sites
create-site:
<<: *custom_image
deploy:
mode: replicated
replicas: ${CREATE_SITE:-0}
restart_policy:
condition: none
entrypoint: ["bash", "-c"]
command:
- >
wait-for-it -t 300 $${DB_HOST}:$${DB_PORT};
wait-for-it -t 120 redis-cache:6379;
wait-for-it -t 120 redis-queue:6379;
export start=`date +%s`;
until [[ -n `grep -hs ^ sites/common_site_config.json | jq -r ".db_host // empty"` ]] && \
[[ -n `grep -hs ^ sites/common_site_config.json | jq -r ".redis_cache // empty"` ]] && \
[[ -n `grep -hs ^ sites/common_site_config.json | jq -r ".redis_queue // empty"` ]];
do
echo "Waiting for sites/common_site_config.json to be created";
sleep 5;
if (( `date +%s`-start > 120 )); then
echo "could not find sites/common_site_config.json with required keys";
exit 1
fi
done;
echo "sites/common_site_config.json found";
[[ -d "sites/${SITE_NAME}" ]] && echo "${SITE_NAME} already exists" && exit 0;
bench new-site --mariadb-user-host-login-scope='%' --admin-password=$${ADMIN_PASSWORD} --db-root-username=root --db-root-password=$${DB_ROOT_PASSWORD} $${INSTALL_APP_ARGS} $${SITE_NAME};
if [[ $${ENABLE_SCHEDULER} == "1" ]]; then
bench --site $${SITE_NAME} enable-scheduler;
else
echo "Skipping scheduler enable";
fi;
volumes:
- sites:/home/frappe/frappe-bench/sites
environment:
SITE_NAME: ${SITE_NAME}
ADMIN_PASSWORD: ${ADMIN_PASSWORD}
DB_HOST: ${DB_HOST:-db}
DB_PORT: "${DB_PORT:-3306}"
DB_ROOT_PASSWORD: ${DB_ROOT_PASSWORD}
INSTALL_APP_ARGS: ${INSTALL_APP_ARGS}
ENABLE_SCHEDULER: "${ENABLE_SCHEDULER}"
migration:
<<: *custom_image
deploy:
mode: replicated
replicas: ${MIGRATE:-0}
restart_policy:
condition: none
entrypoint: ["bash", "-c"]
command:
- >
curl -f -H "Host: ${SITE_NAME}" http://frontend:8080/api/method/ping || { echo "Site not reachable yet, skipping migration"; exit 0; };
bench --site all set-config -p maintenance_mode 1;
bench --site all set-config -p pause_scheduler 1;
bench --site all migrate;
bench --site all set-config -p maintenance_mode 0;
bench --site all set-config -p pause_scheduler 0;
volumes:
- sites:/home/frappe/frappe-bench/sites
db:
image: mariadb:${DB_VERSION:-11.8.6}
deploy:
mode: replicated
replicas: ${ENABLE_DB:-0}
restart_policy:
condition: always
healthcheck:
test: ["CMD", "healthcheck.sh", "--connect", "--innodb_initialized"]
start_period: 120s
interval: 5s
timeout: 5s
retries: 30
command:
- --character-set-server=utf8mb4
- --collation-server=utf8mb4_unicode_ci
- --skip-character-set-client-handshake
environment:
- MARIADB_ROOT_PASSWORD=${DB_ROOT_PASSWORD}
volumes:
- db-data:/var/lib/mysql
redis-cache:
deploy:
restart_policy:
condition: always
image: redis:6.2-alpine
volumes:
- redis-cache-data:/data
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 5s
timeout: 5s
retries: 3
redis-queue:
deploy:
restart_policy:
condition: always
image: redis:6.2-alpine
volumes:
- redis-queue-data:/data
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 5s
timeout: 5s
retries: 3
redis-socketio:
deploy:
restart_policy:
condition: always
image: redis:6.2-alpine
volumes:
- redis-socketio-data:/data
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 5s
timeout: 5s
retries: 3
volumes:
db-data:
redis-cache-data:
redis-queue-data:
redis-socketio-data:
sites:
driver_opts:
type: "${SITE_VOLUME_TYPE}"
o: "${SITE_VOLUME_OPTS}"
device: "${SITE_VOLUME_DEV}"