From 17169aaaedce7b4dad6ec7a2cd70e83e1dbaaea9 Mon Sep 17 00:00:00 2001 From: kev Date: Wed, 19 Jun 2024 18:09:02 +0800 Subject: [PATCH] update airflow --- airflow/.env | 4 + airflow/docker-compose.yml | 193 +++++++++++++++++++++++++++++++++++++ 2 files changed, 197 insertions(+) create mode 100644 airflow/.env create mode 100644 airflow/docker-compose.yml diff --git a/airflow/.env b/airflow/.env new file mode 100644 index 0000000..6b53c78 --- /dev/null +++ b/airflow/.env @@ -0,0 +1,4 @@ +AIRFLOW_UID=1000 +AIRFLOW_PROJ_DIR=./data/airflow +# python3 -c 'from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())' +AIRFLOW__CORE__FERNET_KEY=qV3dXnw7hSd34a43soalJ_JJzSOnec6OEDGe6AXd320= diff --git a/airflow/docker-compose.yml b/airflow/docker-compose.yml new file mode 100644 index 0000000..716a177 --- /dev/null +++ b/airflow/docker-compose.yml @@ -0,0 +1,193 @@ +# +# References: +# - https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html +# - https://airflow.apache.org/docs/apache-airflow/2.9.2/docker-compose.yaml +# - https://github.com/apache/airflow/blob/main/Dockerfile +# + +x-airflow-common: + &airflow-common + image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:2.9.2} + environment: + &airflow-common-env + AIRFLOW__CORE__EXECUTOR: CeleryExecutor + AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow + AIRFLOW__CELERY__RESULT_BACKEND: db+postgresql://airflow:airflow@postgres/airflow + AIRFLOW__CELERY__BROKER_URL: redis://:@redis:6379/0 + AIRFLOW__CORE__FERNET_KEY: '${AIRFLOW__CORE__FERNET_KEY:-}' + AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true' + AIRFLOW__CORE__LOAD_EXAMPLES: 'false' + AIRFLOW__API__AUTH_BACKENDS: 'airflow.api.auth.backend.basic_auth,airflow.api.auth.backend.session' + AIRFLOW__SCHEDULER__ENABLE_HEALTH_CHECK: 'true' + _PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:-} + volumes: + - ${AIRFLOW_PROJ_DIR:-.}/dags:/opt/airflow/dags + - ${AIRFLOW_PROJ_DIR:-.}/logs:/opt/airflow/logs + - ${AIRFLOW_PROJ_DIR:-.}/config:/opt/airflow/config + - ${AIRFLOW_PROJ_DIR:-.}/plugins:/opt/airflow/plugins + user: "${AIRFLOW_UID:-50000}:0" + depends_on: + &airflow-common-depends-on + redis: + condition: service_healthy + postgres: + condition: service_healthy + +services: + + postgres: + image: postgres:16-alpine + environment: + POSTGRES_USER: airflow + POSTGRES_PASSWORD: airflow + POSTGRES_DB: airflow + volumes: + - ./data/postgres:/var/lib/postgresql/data + healthcheck: + test: ["CMD", "pg_isready", "-U", "airflow"] + interval: 10s + retries: 5 + start_period: 5s + restart: unless-stopped + + redis: + image: redis:7-alpine + command: --save 900 1 + volumes: + - ./data/redis:/data + healthcheck: + test: ["CMD", "redis-cli", "ping"] + interval: 10s + timeout: 30s + retries: 50 + start_period: 30s + restart: unless-stopped + + airflow-webserver: + <<: *airflow-common + command: webserver + ports: + - "8080:8080" + healthcheck: + test: ["CMD", "curl", "--fail", "http://localhost:8080/health"] + interval: 30s + timeout: 10s + retries: 5 + start_period: 30s + depends_on: + <<: *airflow-common-depends-on + airflow-init: + condition: service_completed_successfully + restart: unless-stopped + + airflow-scheduler: + <<: *airflow-common + command: scheduler + healthcheck: + test: ["CMD", "curl", "--fail", "http://localhost:8974/health"] + interval: 30s + timeout: 10s + retries: 5 + start_period: 30s + depends_on: + <<: *airflow-common-depends-on + airflow-init: + condition: service_completed_successfully + restart: unless-stopped + + airflow-worker: + <<: *airflow-common + command: celery worker + environment: + <<: *airflow-common-env + DUMB_INIT_SETSID: "0" + healthcheck: + test: + - "CMD-SHELL" + - 'celery --app airflow.providers.celery.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}" || celery --app airflow.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}"' + interval: 30s + timeout: 10s + retries: 5 + start_period: 30s + depends_on: + <<: *airflow-common-depends-on + airflow-init: + condition: service_completed_successfully + restart: unless-stopped + + airflow-triggerer: + <<: *airflow-common + command: triggerer + healthcheck: + test: ["CMD-SHELL", 'airflow jobs check --job-type TriggererJob --hostname "$${HOSTNAME}"'] + interval: 30s + timeout: 10s + retries: 5 + start_period: 30s + depends_on: + <<: *airflow-common-depends-on + airflow-init: + condition: service_completed_successfully + restart: unless-stopped + + airflow-init: + <<: *airflow-common + entrypoint: /bin/bash + command: + - -c + - | + if [[ -z "${AIRFLOW_UID}" ]]; then + echo + echo -e "\033[1;33mWARNING!!!: AIRFLOW_UID not set!\e[0m" + echo "If you are on Linux, you SHOULD follow the instructions below to set " + echo "AIRFLOW_UID environment variable, otherwise files will be owned by root." + echo "For other operating systems you can get rid of the warning with manually created .env file:" + echo " See: https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#setting-the-right-airflow-user" + echo + fi + one_meg=1048576 + mem_available=$$(($$(getconf _PHYS_PAGES) * $$(getconf PAGE_SIZE) / one_meg)) + cpus_available=$$(grep -cE 'cpu[0-9]+' /proc/stat) + disk_available=$$(df / | tail -1 | awk '{print $$4}') + warning_resources="false" + if (( mem_available < 4000 )) ; then + echo + echo -e "\033[1;33mWARNING!!!: Not enough memory available for Docker.\e[0m" + echo "At least 4GB of memory required. You have $$(numfmt --to iec $$((mem_available * one_meg)))" + echo + warning_resources="true" + fi + if (( cpus_available < 2 )); then + echo + echo -e "\033[1;33mWARNING!!!: Not enough CPUS available for Docker.\e[0m" + echo "At least 2 CPUs recommended. You have $${cpus_available}" + echo + warning_resources="true" + fi + if (( disk_available < one_meg * 10 )); then + echo + echo -e "\033[1;33mWARNING!!!: Not enough Disk space available for Docker.\e[0m" + echo "At least 10 GBs recommended. You have $$(numfmt --to iec $$((disk_available * 1024 )))" + echo + warning_resources="true" + fi + if [[ $${warning_resources} == "true" ]]; then + echo + echo -e "\033[1;33mWARNING!!!: You have not enough resources to run Airflow (see above)!\e[0m" + echo "Please follow the instructions to increase amount of resources available:" + echo " https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#before-you-begin" + echo + fi + mkdir -p /sources/logs /sources/dags /sources/plugins + chown -R "${AIRFLOW_UID}:0" /sources/{logs,dags,plugins} + exec /entrypoint airflow version + environment: + <<: *airflow-common-env + _AIRFLOW_DB_MIGRATE: 'true' + _AIRFLOW_WWW_USER_CREATE: 'true' + _AIRFLOW_WWW_USER_USERNAME: ${_AIRFLOW_WWW_USER_USERNAME:-airflow} + _AIRFLOW_WWW_USER_PASSWORD: ${_AIRFLOW_WWW_USER_PASSWORD:-airflow} + _PIP_ADDITIONAL_REQUIREMENTS: '' + user: "0:0" + volumes: + - ${AIRFLOW_PROJ_DIR:-.}:/sources