diff --git a/.github/workflows/test-and-build.yml b/.github/workflows/test-and-build.yml index 148607b..722e4f7 100644 --- a/.github/workflows/test-and-build.yml +++ b/.github/workflows/test-and-build.yml @@ -8,6 +8,7 @@ on: - main env: + PYTHON_VERSION: 3.8.16 AIRFLOW_HOME: /home/runner/work/airflow-dags/airflow-dags REGISTRY: registry.cern.ch IMAGE: cern-sis/airflow @@ -45,32 +46,12 @@ jobs: with: python-version: 3.8.16 - - name: Install python dependencies - run: | - pip install --upgrade pip - pip install --no-cache-dir --upgrade setuptools - pip install --no-cache-dir --upgrade wheel - pip install -r requirements.txt -r requirements-test.txt -r requirements-airflow.txt - - name: Run services on docker compose run: docker compose up -d postgres redis sftp ftp s3 create_buckets - - name: Start airflow - run: | - airflow db init - airflow webserver -D - airflow triggerer -D - airflow scheduler -D - airflow celery worker -D - airflow celery flower -D - echo -e "\033[0;32m Airflow Started. \033[0m" - - name: List services for IT Tests run: docker ps - - name: List all dags - run: airflow dags list - - name: Build Image id: build uses: cern-sis/gh-workflows/.github/actions/docker-build@v6 @@ -82,20 +63,24 @@ jobs: username: ${{ secrets.HARBOR_USERNAME }} password: ${{ secrets.HARBOR_PASSWORD }} + - name: Run tests with pytest and generate report - run: > - docker run - --name airflowdags - --network=host - -v "$(pwd)"/tests:/opt/airflow/tests - -v "$(pwd)"/dags:/opt/airflow/dags - -v "$(pwd)"/airflow.cfg:/opt/airflow/airflow.cfg - -v "$(pwd)"/data:/opt/airflow/data - --entrypoint pytest - $REGISTRY/$IMAGE@${{ steps.build.outputs.image-digest }} - tests - --cov=./ - --cov-report=xml + run: | + docker run \ + --name airflowdags \ + --network=host \ + -v "$(pwd)"/tests:/opt/airflow/tests \ + -v "$(pwd)"/dags:/opt/airflow/dags \ + -v "$(pwd)"/airflow.cfg:/opt/airflow/airflow.cfg \ + -v "$(pwd)"/data:/opt/airflow/data \ + $REGISTRY/$IMAGE@${{ steps.build.outputs.image-digest }} \ + bash -c "airflow db init && \ + airflow webserver -D && \ + airflow scheduler -D && \ + airflow triggerer -D && \ + airflow celery worker -D && \ + airflow celery flower -D && \ + pytest /opt/airflow/tests --cov=/opt/airflow --cov-report=xml" - name: Copy test coverage file to host machine run: docker cp airflowdags:/opt/airflow/coverage.xml . diff --git a/Dockerfile b/Dockerfile index c24e29a..28b51e3 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,4 +1,8 @@ -FROM apache/airflow:2.8.3 -COPY requirements.txt / -COPY requirements-airflow.txt / -RUN pip install --no-cache-dir "apache-airflow==${AIRFLOW_VERSION}" -r /requirements.txt -r /requirements-airflow.txt +FROM apache/airflow:2.8.3-python3.8 +ENV AIRFLOW_HOME=/opt/airflow +WORKDIR /opt/airflow +RUN curl -o constraints.txt 'https://raw.githubusercontent.com/apache/airflow/constraints-${AIRFLOW_VERSION}/constraints-${PYTHON_VERSION}.txt' +COPY requirements.txt ./requirements.txt +COPY requirements-airflow.txt ./requirements-airflow.txt +COPY requirements-test.txt ./requirements-test.txt +RUN pip install --no-cache-dir --user -r requirements.txt -r requirements-test.txt -r requirements-airflow.txt diff --git a/Dockerfile.test b/Dockerfile.test deleted file mode 100644 index 24274df..0000000 --- a/Dockerfile.test +++ /dev/null @@ -1,23 +0,0 @@ -FROM apache/airflow:2.8.3-python3.8 - -ENV AIRFLOW_HOME=/opt/airflow -WORKDIR /opt/airflow - -ENV PYTHONBUFFERED=0 -ENV AIRFLOW__LOGGING__LOGGING_LEVEL=INFO - -COPY requirements.txt ./requirements.txt -COPY requirements-test.txt ./requirements-test.txt -COPY requirements-airflow.txt ./requirements-airflow.txt - -COPY dags ./dags -COPY tests ./tests -COPY data ./data - -COPY airflow.cfg ./airflow.cfg - -RUN pip install --upgrade pip &&\ - pip install --no-cache-dir --upgrade setuptools==59.1.1 &&\ - pip install --no-cache-dir --upgrade wheel &&\ - pip install --no-cache-dir --user -r requirements.txt -r requirements-test.txt -r requirements-airflow.txt - diff --git a/docker-compose.yaml b/docker-compose.yaml index ef039cb..4982ba3 100644 --- a/docker-compose.yaml +++ b/docker-compose.yaml @@ -1,8 +1,6 @@ version: "3.8" x-airflow-common: &airflow-common - build: - context: . - dockerfile: Dockerfile.test + build: . environment: &airflow-common-env AIRFLOW__CORE__EXECUTOR: CeleryExecutor AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow @@ -24,6 +22,7 @@ x-airflow-common: &airflow-common _PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:-} volumes: - ./dags:/opt/airflow/dags + - ./tests:/opt/airflow/tests - ./logs:/opt/airflow/logs - ./airflow.cfg:/opt/airflow/airflow.cfg user: "${AIRFLOW_UID:-50000}:0" @@ -108,5 +107,194 @@ services: - s3 entrypoint: > /bin/sh -c " sleep 10; /usr/bin/mc alias set airflow http://s3:9000 airflow Airflow01; /usr/bin/mc mb airflow/springer; /usr/bin/mc mb airflow/aps; /usr/bin/mc mb airflow/hindawi; /usr/bin/mc mb airflow/iop; /usr/bin/mc mb airflow/elsevier; /usr/bin/mc mb airflow/oup; exit 0; " + 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 + restart: always + depends_on: + <<: *airflow-common-depends-on + airflow-init: + condition: service_completed_successfully + + airflow-scheduler: + <<: *airflow-common + command: scheduler + healthcheck: + test: + [ + "CMD-SHELL", + 'airflow jobs check --job-type SchedulerJob --hostname "$${HOSTNAME}"', + ] + interval: 30s + timeout: 10s + retries: 5 + start_period: 30s + restart: always + depends_on: + <<: *airflow-common-depends-on + airflow-init: + condition: service_completed_successfully + + airflow-worker: + <<: *airflow-common + command: celery worker + healthcheck: + test: + - "CMD-SHELL" + - 'celery --app airflow.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}"' + interval: 30s + timeout: 10s + retries: 5 + start_period: 30s + environment: + <<: *airflow-common-env + # Required to handle warm shutdown of the celery workers properly + # See https://airflow.apache.org/docs/docker-stack/entrypoint.html#signal-propagation + DUMB_INIT_SETSID: "0" + restart: always + depends_on: + <<: *airflow-common-depends-on + airflow-init: + condition: service_completed_successfully + + airflow-triggerer: + <<: *airflow-common + command: triggerer + healthcheck: + test: + [ + "CMD-SHELL", + 'airflow jobs check --job-type TriggererJob --hostname "$${HOSTNAME}"', + ] + interval: 30s + timeout: 10s + retries: 5 + start_period: 30s + restart: always + depends_on: + <<: *airflow-common-depends-on + airflow-init: + condition: service_completed_successfully + + airflow-init: + <<: *airflow-common + entrypoint: /bin/bash + # yamllint disable rule:line-length + command: + - -c + - | + function ver() { + printf "%04d%04d%04d%04d" $${1//./ } + } + airflow_version=$$(AIRFLOW__LOGGING__LOGGING_LEVEL=INFO && gosu airflow airflow version) + airflow_version_comparable=$$(ver $${airflow_version}) + min_airflow_version=2.2.0 + min_airflow_version_comparable=$$(ver $${min_airflow_version}) + if (( airflow_version_comparable < min_airflow_version_comparable )); then + echo + echo -e "\033[1;31mERROR!!!: Too old Airflow version $${airflow_version}!\e[0m" + echo "The minimum Airflow version supported: $${min_airflow_version}. Only use this or higher!" + echo + exit 1 + fi + if [[ -z "${AIRFLOW_UID}" ]]; then + echo + echo -e "\033[1;33mWARNING!!!: AIRFLOW_UID not set!\e[0m" + echo "If you are on Linux, you SHOULD follow the instructions below to set " + echo "AIRFLOW_UID environment variable, otherwise files will be owned by root." + echo "For other operating systems you can get rid of the warning with manually created .env file:" + echo " See: https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#setting-the-right-airflow-user" + echo + fi + one_meg=1048576 + mem_available=$$(($$(getconf _PHYS_PAGES) * $$(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 + # yamllint enable rule:line-length + environment: + <<: *airflow-common-env + _AIRFLOW_DB_UPGRADE: "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 + + airflow-cli: + <<: *airflow-common + profiles: + - debug + environment: + <<: *airflow-common-env + CONNECTION_CHECK_MAX_COUNT: "0" + # Workaround for entrypoint issue. See: https://github.com/apache/airflow/issues/16252 + command: + - bash + - -c + - airflow + + # You can enable flower by adding "--profile flower" option e.g. docker-compose --profile flower up + # or by explicitly targeted on the command line e.g. docker-compose up flower. + # See: https://docs.docker.com/compose/profiles/ + flower: + <<: *airflow-common + command: celery flower + profiles: + - flower + ports: + - "5555:5555" + healthcheck: + test: ["CMD", "curl", "--fail", "http://localhost:5555/"] + interval: 30s + timeout: 10s + retries: 5 + start_period: 30s + restart: always + depends_on: + <<: *airflow-common-depends-on + airflow-init: + condition: service_completed_successfully volumes: postgres-db-volume: diff --git a/requirements-airflow.txt b/requirements-airflow.txt index b1ce3ee..01b1986 100644 --- a/requirements-airflow.txt +++ b/requirements-airflow.txt @@ -1,5 +1,4 @@ --c https://raw.githubusercontent.com/apache/airflow/constraints-2.8.3/constraints-3.8.txt -apache-airflow[celery, postgres, redis, cncf.kubernetes]==2.8.3 -alembic==1.13.1 -airflow-provider-alembic==1.0.0 -elementpath==4.4.0 +apache-airflow[celery, postgres, redis, cncf.kubernetes] +alembic +airflow-provider-alembic +elementpath