Docker 编写缺少的 python 包

Question

作为序言，我是 Docker、Airflow 和 Whosebug 的新手。

我在 Ubuntu (20.04.3) VM 上的 Docker 中获得了 Airflow 运行ning 实例。

我正在尝试在构建时安装 Openpyxl，以便将其用作 pd.read_excel 的引擎。

这是带有安装命令的Docker文件：

FROM apache/airflow:2.2.4

ENV AIRFLOW_HOME=/opt/airflow

USER root
RUN apt-get update -qq && apt-get install vim -qqq

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Ref: https://airflow.apache.org/docs/docker-stack/recipes.html

SHELL ["/bin/bash", "-o", "pipefail", "-e", "-u", "-x", "-c"]

ARG CLOUD_SDK_VERSION=322.0.0
ENV GCLOUD_HOME=/home/google-cloud-sdk

ENV PATH="${GCLOUD_HOME}/bin/:${PATH}"

RUN DOWNLOAD_URL="https://dl.google.com/dl/cloudsdk/channels/rapid/downloads/google-cloud-sdk-${CLOUD_SDK_VERSION}-linux-x86_64.tar.gz" \
    && TMP_DIR="$(mktemp -d)" \
    && curl -fL "${DOWNLOAD_URL}" --output "${TMP_DIR}/google-cloud-sdk.tar.gz" \
    && mkdir -p "${GCLOUD_HOME}" \
    && tar xzf "${TMP_DIR}/google-cloud-sdk.tar.gz" -C "${GCLOUD_HOME}" --strip-components=1 \
    && "${GCLOUD_HOME}/install.sh" \
    --bash-completion=false \
    --path-update=false \
    --usage-reporting=false \
    --quiet \
    && rm -rf "${TMP_DIR}" \
    && gcloud --version

WORKDIR $AIRFLOW_HOME

USER $AIRFLOW_UID

requirements.txt 文件如下所示：

openpyxl
apache-airflow-providers-google
pyarrow==6.0.1
pandas==1.3.5
requests==2.27.1

docker-compose.yaml 文件如下所示：

version: '3'
x-airflow-common:
  &airflow-common
  build:
    context: .
    dockerfile: ./Dockerfile
  environment:
    &airflow-common-env
    AIRFLOW__CORE__EXECUTOR: CeleryExecutor
    AIRFLOW__CORE__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__DAGS_ARE_PAUSED_AT_CREATION: 'true'
    AIRFLOW__CORE__LOAD_EXAMPLES: 'false'
    AIRFLOW__API__AUTH_BACKEND: 'airflow.api.auth.backend.basic_auth'
    _PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:-}
    GOOGLE_APPLICATION_CREDENTIALS: /.google/credentials/google_credentials.json
    AIRFLOW_CONN_GOOGLE_CLOUD_DEFAULT: 'google-cloud-platform://?extra__google_cloud_platform__key_path=/.google/credentials/google_credentials.json'
    GCP_PROJECT_ID: <MYPROJECTID>
    GCP_GCS_BUCKET: <MYBUCKET>
  volumes:
    - ./dags:/opt/airflow/dags
    - ./logs:/opt/airflow/logs
    - ./plugins:/opt/airflow/plugins
    - ~/.google/credentials/:/.google/credentials:ro
  user: "${AIRFLOW_UID:-50000}:0"
  depends_on:
    &airflow-common-depends-on
    redis:
      condition: service_healthy
    postgres:
      condition: service_healthy

services:
  postgres:
    image: postgres:13
    environment:
      POSTGRES_USER: <USER>
      POSTGRES_PASSWORD: <PASSWORD>
      POSTGRES_DB: <DBNAME>
    volumes:
      - postgres-db-volume:/var/lib/postgresql/data
    healthcheck:
      test: [ "CMD", "pg_isready", "-U", "airflow" ]
      interval: 5s
      retries: 5
    restart: always

  redis:
    image: redis:latest
    expose:
      - 6379
    healthcheck:
      test: [ "CMD", "redis-cli", "ping" ]
      interval: 5s
      timeout: 30s
      retries: 50
    restart: always

  airflow-webserver:
    <<: *airflow-common
    command: webserver
    ports:
      - 8080:8080
    healthcheck:
      test:
        [
          "CMD",
          "curl",
          "--fail",
          "http://localhost:8080/health"
        ]
      interval: 10s
      timeout: 10s
      retries: 5
    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: 10s
      timeout: 10s
      retries: 5
    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: 10s
      timeout: 10s
      retries: 5
    environment:
      <<: *airflow-common-env
      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: 10s
      timeout: 10s
      retries: 5
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-init:
    <<: *airflow-common
    entrypoint: /bin/bash
    command:
      - -c
      - |
        function ver() {
          printf "%04d%04d%04d%04d" $${1//./ }
        }
        airflow_version=$$(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 "3[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 "3[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/start/docker.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=$$(df / | tail -1 | awk '{print $}')
        warning_resources="false"
        if (( mem_available < 4000 )) ; then
          echo
          echo -e "3[1;33mWARNING!!!: Not enough memory available for Docker.\e[0m"
          echo "At least 4GB of memory required. You have $$(numfmt --to iec $$((mem_available * one_meg)))"
          echo
          warning_resources="true"
        fi
        if (( cpus_available < 2 )); then
          echo
          echo -e "3[1;33mWARNING!!!: Not enough CPUS available for Docker.\e[0m"
          echo "At least 2 CPUs recommended. You have $${cpus_available}"
          echo
          warning_resources="true"
        fi
        if (( disk_available < one_meg * 10 )); then
          echo
          echo -e "3[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 "3[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/start/docker.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_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}
    user: "0:0"
    volumes:
      - .:/sources

  airflow-cli:
    <<: *airflow-common
    profiles:
      - debug
    environment:
      <<: *airflow-common-env
      CONNECTION_CHECK_MAX_COUNT: "0"
    command:
      - bash
      - -c
      - airflow

  flower:
    <<: *airflow-common
    command: celery flower
    ports:
      - 5555:5555
    healthcheck:
      test: [ "CMD", "curl", "--fail", "http://localhost:5555/" ]
      interval: 10s
      timeout: 10s
      retries: 5
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

volumes:
  postgres-db-volume:

在我运行 docker build 和 docker up 和 shell 进入运行ning worker 容器后，运行ning pip list 表明需求文件中的所有包都已成功安装 除了 Openpyxl。在构建时复制到容器的 requirements.txt 文件甚至包括 Openpyxl。此时我可以通过在 shell.

中执行 pip install openpyxl 来手动 pip install openpyxl

我已经尝试在 RUN pip install --no-cache-dir -r requirements.txt 命令之前和之后将手动安装添加到 Docker 文件 (RUN pip install openpyxl)。
我试过运行宁docker-compose build --no-cache。
我已经尝试运行ning docker system prune -a 并从头开始重建容器。

看起来这应该是一件相当简单的事情，因为我可以毫无问题地正确安装 requirements.txt 文件中的其他包 - 认为这可能与 Openpyxl 包本身有关？

如有任何建议，我们将不胜感激。

Answer 1

我们在 Docker 中遇到了 Airflow 的一些问题，所以我们目前正在努力摆脱它。

一些建议：

将openpyxl的版本设置为requirements.txt
两次添加openpyxl到requirements.txt
使用您的主要组件创建一个 requirements.in 文件，然后使用 pip-compile 创建一个 requirements.txt。这也会添加子组件
也尝试指定 python 版本

希望这些步骤之一能有所帮助。

Answer 2

如果我对你的问题理解正确，docker-compose.yml 中的以下行也可以提供帮助：

_PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:- openpyxl==3.0.9}

顺便说一句，这里的文档解释了添加额外要求的方法：Building the image

Docker 编写缺少的 python 包

Docker compose missing python package

python

openpyxl

docker

docker-compose

airflow