Fedora 33上docker-compose搭配Podman部署Mastodon出现主机名解析失败

基础运行环境 #

• 部署目标：官方Mastodon开源社交平台
• 服务器系统：Fedora 33 Server
• 容器栈版本验证输出：

$ docker-compose --version
docker-compose version 1.27.4, build unknown

$ docker --version
podman version 3.0.1

$ cat /etc/fedora-release
Fedora release 33 (Thirty Three)

适配Podman环境的配置修改 #

针对官方docker-compose.yml的调整项：

• 为所有服务的健康检查补充timeout、interval、retries参数，避免Podman环境下健康检查判定异常
• 为PostgreSQL服务新增POSTGRES_HOST_AUTH_METHOD=trust环境变量，配置数据库免密本地访问
• 注释所有服务的本地镜像构建逻辑，直接使用官方发布的预构建镜像（原本地构建流程在当前环境下持续失败）

完整调整后的docker-compose.yml配置：

version: '3'
services:

  db:
    restart: always
    image: postgres:9.6-alpine
    shm_size: 256mb
    networks:
      - internal_network
    healthcheck:
      test: ["CMD", "pg_isready", "-U", "postgres"]
      timeout: 45s
      interval: 10s
      retries: 10
    volumes:
      - ./postgres:/var/lib/postgresql/data
    environment:
      - POSTGRES_HOST_AUTH_METHOD=trust

  redis:
    restart: always
    image: redis:6.0-alpine
    networks:
      - internal_network
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      timeout: 45s
      interval: 10s
      retries: 10
    volumes:
      - ./redis:/data

#  es:
#    restart: always
#    image: docker.elastic.co/elasticsearch/elasticsearch-oss:6.8.10
#    environment:
#      - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
#      - "cluster.name=es-mastodon"
#      - "discovery.type=single-node"
#      - "bootstrap.memory_lock=true"
#    networks:
#      - internal_network
#    healthcheck:
#      test: ["CMD-SHELL", "curl --silent --fail localhost:9200/_cluster/health || exit 1"]
#    volumes:
#      - ./elasticsearch:/usr/share/elasticsearch/data
#    ulimits:
#      memlock:
#        soft: -1
#        hard: -1

  web:
    #    build: .
    image: tootsuite/mastodon
    restart: always
    env_file: .env.production
    command: bash -c "rm -f /mastodon/tmp/pids/server.pid; bundle exec rails s -p 3000"
    networks:
      - external_network
      - internal_network
    healthcheck:
      test: ["CMD-SHELL", "wget -q --spider --proxy=off localhost:3000/health || exit 1"]
      timeout: 45s
      interval: 10s
      retries: 10
    ports:
      - "127.0.0.1:3000:3000"
    depends_on:
      - db
      - redis
#      - es
    volumes:
      - ./public/system:/mastodon/public/system

  streaming:
    build: .
    image: tootsuite/mastodon
    restart: always
    env_file: .env.production
    command: node ./streaming
    networks:
      - external_network
      - internal_network
    healthcheck:
      test: ["CMD-SHELL", "wget -q --spider --proxy=off localhost:4000/api/v1/streaming/health || exit 1"]
      timeout: 45s
      interval: 10s
      retries: 10
    ports:
      - "127.0.0.1:4000:4000"
    depends_on:
      - db
      - redis

  sidekiq:
    build: .
    image: tootsuite/mastodon
    restart: always
    env_file: .env.production
    command: bundle exec sidekiq
    depends_on:
      - db
      - redis
    networks:
      - external_network
      - internal_network
    volumes:
      - ./public/system:/mastodon/public/system
## 取消注释即可启用与Tor实例的联邦访问，同时需添加以下环境变量
## http_proxy=http://privoxy:8118
## ALLOW_ACCESS_TO_HIDDEN_SERVICE=true
#  tor:
#    image: sirboops/tor
#    networks:
#      - external_network
#      - internal_network
#
#  privoxy:
#    image: sirboops/privoxy
#    volumes:
#      - ./priv-config:/opt/config
#    networks:
#      - external_network
#      - internal_network

networks:
  external_network:
  internal_network:
    internal: true

与官方默认配置的diff对比结果：

$ git diff docker-compose.yml
diff --git a/docker-compose.yml b/docker-compose.yml
index 52eea7a74..a8e047ec7 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -9,8 +9,13 @@ services:
       - internal_network
     healthcheck:
       test: ["CMD", "pg_isready", "-U", "postgres"]
+      timeout: 45s
+      interval: 10s
+      retries: 10
     volumes:
       - ./postgres:/var/lib/postgresql/data
+    environment:
+      - POSTGRES_HOST_AUTH_METHOD=trust

  redis:
    restart: always
@@ -19,6 +24,9 @@ services:
      - internal_network
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
+      timeout: 45s
+      interval: 10s
+      retries: 10
    volumes:
      - ./redis:/data

@@ -42,7 +50,7 @@ services:
 #        hard: -1

  web:
-    build: .
+    #    build: .
    image: tootsuite/mastodon
    restart: always
    env_file: .env.production
@@ -52,6 +60,9 @@ services:
      - internal_network
    healthcheck:
      test: ["CMD-SHELL", "wget -q --spider --proxy=off localhost:3000/health || exit 1"]
+      timeout: 45s
+      interval: 10s
+      retries: 10
    ports:
      - "127.0.0.1:3000:3000"
    depends_on:
@@ -72,6 +83,9 @@ services:
      - internal_network
    healthcheck:
      test: ["CMD-SHELL", "wget -q --spider --proxy=off localhost:4000/api/v1/streaming/health || exit 1"]
+      timeout: 45s
+      interval: 10s
+      retries: 10
    ports:
      - "127.0.0.1:4000:4000"
    depends_on:

故障详情 #

密钥生成流程可正常完成，执行数据库迁移命令时流程中断：

$ sudo docker-compose run --rm web bundle exec rails db:migrate
Creating network "mastodon_internal_network" with the default driver
Creating network "mastodon_external_network" with the default driver
Creating mastodon_db_1    ... done
Creating mastodon_redis_1 ... done
Creating mastodon_web_run ... done
rails aborted!
PG::ConnectionBad: could not translate host name "db" to address: Name or service not known

补充排查结果：PostgreSQL容器运行状态正常，日志确认服务已进入可接受连接状态：

$ sudo docker logs -f mastodon_db_1

PostgreSQL Database directory appears to contain a database; Skipping initialization

LOG:  database system was shut down at 2021-04-01 07:02:04 UTC
LOG:  MultiXact member wraparound protections are now enabled
LOG:  database system is ready to accept connections
LOG:  autovacuum launcher started

待验证的排查方向 #

• 此前在其他项目中使用相同的Docker-Compose+Podman 3.0组合，未遇到过容器内部主机名解析异常问题，当前场景不确定是否需要为自定义网络手动指定网络驱动
• 需要可落地的验证方法，确认web类容器内部能否通过db主机名正常访问数据库服务，排除应用代码逻辑层面的故障可能

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