Docker Compose部署Airflow容器卡在启动状态且资源占用过高求助

环境与问题现象 #

• 部署环境：AWS EC2 t3a.xlarge实例（16GiB内存，AMD EPYC 7571处理器），系统为Ubuntu 24.04 LTS
• 问题：包含Apache Airflow在内的多个容器持续卡在「启动」状态，同时CPU和内存占用过高，容器出现循环重启情况

已尝试操作 #

• 查看容器日志，未获取到明确的启动失败错误信息
• 在docker-compose.yml中配置容器CPU和内存资源限制，问题未解决
• 重启容器及EC2实例，无效

疑问 #

1. 是否存在遗漏的Docker Compose配置项导致该问题？
2. 针对卡在启动循环的Docker容器，有哪些特定诊断方法及资源优化手段？
3. 是否需要调整EC2实例规格，或有其他可优先尝试的优化方案？

附docker-compose.yml配置 #

version: "3"
x-airflow-common: &airflow-common
  image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:2.8.1}
  environment: &airflow-common-env
    AIRFLOW__CORE__EXECUTOR: CeleryExecutor
    AIRFLOW__CORE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
    AIRFLOW__CELERY__RESULT_BACKEND: db+postgresql://airflow:airflow@postgres/airflow
    AIRFLOW__CELERY__BROKER_URL: redis://:@redis:6379/0
    AIRFLOW__CORE__FERNET_KEY: ""
    AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: "true"
    AIRFLOW__CORE__LOAD_EXAMPLES: "false"
    AIRFLOW__API__AUTH_BACKEND: "airflow.api.auth.backend.basic_auth"
    AIRFLOW__SMTP__SMTP_HOST: "smtp.gmail.com"
    AIRFLOW__SMTP__SMTP_PORT: 587
    AIRFLOW__SMTP__SMTP_USER: "javiertest592@gmail.com"
    AIRFLOW__SMTP__SMTP_PASSWORD: "${SMTP_PASSWORD}"
    AIRFLOW__SMTP__SMTP_MAIL_FROM: "javiertest592@gmail.com"
    _PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:- pymongo}
  volumes:
  - ../ETL:/opt/airflow/ETL
  - ./dags:/opt/airflow/dags
  - ./logs:/opt/airflow/logs
  - ./plugins:/opt/airflow/plugins
  user: "${AIRFLOW_UID:-50000}:0"
  depends_on:
    redis:
      condition: service_healthy
    postgres:
      condition: service_healthy
  networks:
    - airflow-net  # Référence au réseau airflow-net

services:
  postgres:
    image: postgres:13
    environment:
      POSTGRES_USER: airflow
      POSTGRES_PASSWORD: airflow
      POSTGRES_DB: airflow
    volumes:
      - postgres-db-volume:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD", "pg_isready", "-U", "airflow"]
      interval: 5s
      retries: 5
    restart: always
    networks:
      - airflow-net  # Référence au réseau airflow-net

  redis:
    image: redis:latest
    ports:
      - 6379:6379
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 30s
      retries: 50
    restart: always
    networks:
      - airflow-net  # Référence au réseau airflow-net

  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
    networks:
      - airflow-net  # Référence au réseau airflow-net

  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
    networks:
      - airflow-net  # Référence au réseau airflow-net

  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
    restart: always
    networks:
      - airflow-net  # Référence au réseau airflow-net

  airflow-init:
    <<: *airflow-common
    command: 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}
    networks:
      - airflow-net  # Référence au réseau airflow-net

  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
    networks:
      - airflow-net  # Référence au réseau airflow-net

networks:
  airflow-net:
    external: true  # Définir le réseau comme externe

volumes:
  postgres-db-volume:

内容的提问来源于stack exchange，提问作者Cryptropico973