gitlab ci dind 或其他方法不起作用

Question

我一直在尝试在 aws 上使用 docker runner 设置 gitlab ci。我设法让 runner 最终与 gitlab 合作。我遇到的问题是在构建阶段。我在构建阶段不断出错。 error during connect: Post http://docker:2375/v1.40/auth: dial tcp: lookup docker on 172.31.0.2:53: no such host 我正在尝试构建一个 python django 应用程序。如果我使用共享运行器，则整个过程都可以正常工作，并且我可以在容器注册表中看到新图像。

这是我的 gitlab-ci.yaml

image: python:latest

services:
  - name: docker:dind
    entrypoint: ["env", "-u", "DOCKER_HOST"]
    command: ["dockerd-entrypoint.sh"]

stages:
  - test
  - compile
  - build
  - deploy

variables:
  DOCKER_HOST: tcp://docker:2375
  DOCKER_DRIVER: overlay2
  DOCKER_TLS_CERTDIR: ""
  MOUNT_POINT: /builds/$CI_PROJECT_PATH/mnt

before_script:
  - docker info
  - export IMAGE=$CI_REGISTRY/$CI_PROJECT_NAMESPACE/$CI_PROJECT_NAME
  - export WEB_IMAGE=$IMAGE:web
  - export NGINX_IMAGE=$IMAGE:nginx
  - apk add --no-cache openssh-client bash
  - chmod +x ./setup_env.sh
  - bash ./setup_env.sh
  - docker login -u $CI_REGISTRY_USER -p $CI_JOB_TOKEN $CI_REGISTRY

unittests:
  stage: test
  before_script:
    - python -m pip install --upgrade pip
    - pip install -r app/pipeline-requirements.txt
  script:
    - python app/manage.py jenkins --enable-coverage
  artifacts:
    reports:
      junit: app/reports/junit.xml
    paths:
      - "app/reports/*.xml"
    expire_in: 30 days
    when: on_success
  only:
    refs:
      - merge_requests
    variables:
      - $CI_MERGE_REQUEST_TARGET_BRANCH_NAME == "qa"

migrations:
  stage: compile
  before_script:
    - pip install -r app/pipeline-requirements.txt
  script:
    - python app/manage.py makemigrations
  artifacts:
    paths:
      - "app/*/migrations/*.py"
    expire_in: 1 day
  only:
    refs:
      - merge_requests
    variables:
      - $CI_MERGE_REQUEST_TARGET_BRANCH_NAME == "qa"

build:
  image:
    name: docker/compose:1.25.4
    entrypoint: [ "" ]
  stage: build
  before_script:
    - export IMAGE=$CI_REGISTRY/$CI_PROJECT_NAMESPACE/$CI_PROJECT_NAME
    - export WEB_IMAGE=$IMAGE:web
    - export NGINX_IMAGE=$IMAGE:nginx
  script:
    - apk add --no-cache bash
    - chmod +x ./setup_env.sh
    - bash ./setup_env.sh
    - docker login -u $CI_REGISTRY_USER -p $CI_JOB_TOKEN $CI_REGISTRY
    - docker pull $IMAGE:web || true
    - docker pull $IMAGE:nginx || true
    - docker-compose -f docker-compose.ci.yml build
    - docker push $IMAGE:web
    - docker push $IMAGE:nginx
  dependencies:
    - migrations
  only:
    refs:
      - merge_requests
    variables:
      - $CI_MERGE_REQUEST_TARGET_BRANCH_NAME == "qa"

config.toml

concurrent = 1
check_interval = 10
log_level = "debug"

[session_server]
  session_timeout = 1800

[[runners]]
  name = "aws-qa"
  url = "https://gitlab.com/"
  token = "xxx"
  executor = "docker+machine"
  listen_address="pipelines.domain.digital:8043"
  limit = 10
  pre_build_script = "export DOCKER_HOST=tcp://docker:2375"
  environment = ["DOCKER_DRIVER=overlay2", "DOCKER_TLS_CERTDIR="]
  [runners.custom_build_dir]
  [runners.cache]
    Type = "s3"
    Shared = true
    [runners.cache.s3]
      ServerAddress = "s3.amazonaws.com"
      AccessKey = "xxx"
      SecretKey = "xxx"
      BucketName = "domain-gitlab-runner"
      BucketLocation = "eu-west-2"
    [runners.cache.gcs]
    [runners.cache.azure]
  [runners.docker]
    tls_verify = false
    image = "docker:19.03.12"
    privileged = true
    disable_entrypoint_overwrite = false
    oom_kill_disable = false
    disable_cache = false
    volumes = ["/cache"]
    shm_size = 0
    tls_cert_path = ""
  [runners.machine]
    IdleCount = 0
    MachineDriver = "amazonec2"
    MachineName = "gitlab-docker-machine-%s"
    MaxGrowthRate = 2
    IdleTime = 60
    MachineOptions = [
      "amazonec2-access-key=xxx",
      "amazonec2-secret-key=xxx",
      "amazonec2-region=eu-west-2",
      "amazonec2-vpc-id=vpc-xxx",
      "amazonec2-subnet-id=subnet-xxx",
      "amazonec2-zone=a",
      "amazonec2-use-private-address=true",
      "amazonec2-tags=runner-manager-name,gitlab-aws-autoscaler,gitlab,true,gitlab-runner-autoscale,true,project,pipelines",
      "amazonec2-security-group=gitlab-loadbalancer-sec-group",
      "amazonec2-instance-type=m4.2xlarge",
    ]
    [[runners.machine.autoscaling]]
      Periods = ["* * 9-17 * * mon-fri *"]
      IdleCount = 2
      IdleTime = 60
      Timezone = "UTC"
    [[runners.machine.autoscaling]]
      Periods = ["* * * * * sat,sun *"]
      IdleCount = 0
      IdleTime = 60
      Timezone = "UTC"

Answer 1

这个错误通常是在 [runners.docker] 中添加这个配置来解决的

volumes = ["/var/run/docker.sock:/var/run/docker.sock", "/cache"]