集群部署 graph节点无法正常启动

[SeniaCiel]

• nebula 版本：v2-alpha
• 部署方式（分布式 / 单机 / Docker / DBaaS）：Docker swarm
• 问题的具体描述:
  
  
  
  
  
  
  使用Docker Swarm部署三台机器的集群，meta和storage都正常启动，但graph节点都没有正常启动，报错“container cannot be disconnected from host network or connected to host network”，配置文件使用的是 https://docs.nebula-graph.com.cn/manual-CN/3.build-develop-and-administration/2.install/deploy-nebula-with-swarm/ 示例的docker-stack.yml。

[Amber]

根据报错信息估计是docker容器的网络问题，默认情况下启动docker容器是连接到 brigde 网络的。如果连接到host 网络，就会报以下错误：
Error response from daemon: container cannot be disconnected from host network or connected to host network

[SeniaCiel]

这边是通过docker stack deploy命令部署的，为什么meta和storage都能正常启动，只有graph有问题呢？如果是网络的问题，请问应该怎么修复呢？谢谢！

[Amber]

也有可能是graphd挂了，可以ps看一下进程。如果只是网络问题，建议删除容器再在host网络上运行。

[SeniaCiel]

刚查看了容器，发现只有meta和storage…没有graph的容器。原因可能是什么呢？

[Amber]

可能graph服务就没起起来

[SeniaCiel]

这边的操作就是修改了示例中docker-stack.yml的ip，然后通过docker stack deploy部署，结果就是graph起不来…有遗漏的步骤吗？

[Amber]

nebula.env文件配置过吗

[SeniaCiel]

就是这样配置的

[SeniaCiel]

顶一下

[kevin.qiao]

确认一下graphd连接的网络是host模式还是docker-stack.yaml里的nebula-net，另外检查一下字段mode: host是什么配置，初步怀疑graphd跟其他组件使用的网络模式没有统一

[henson]

贴一下docker-stack文件？

[henson]

2.0版本应该可以不使用host模式，支持service_name:port，文档需要更新下

[Amber]

来贡献个文档呗~~

[henson]

来试下这个
还没小白鼠给反馈（关键是我现在没机器测试）

gumupaier/flute

[SeniaCiel]

这个支持2.0-alpha版本吗？

[SeniaCiel]

version: '3.6'
services:
  metad0:
    image: vesoft/nebula-metad:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.2.3:45500,192.168.2.4:45500,192.168.2.6:45500
      - --local_ip=192.168.2.3
      - --ws_ip=192.168.2.3
      - --port=45500
      - --data_path=/data/meta
      - --log_dir=/logs
      - --v=0
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == ecnu01
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.2.3:11000/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - target: 11000
        published: 11000
        protocol: tcp
        mode: host
      - target: 11002
        published: 11002
        protocol: tcp
        mode: host
      - target: 45500
        published: 45500
        protocol: tcp
        mode: host
    volumes:
      - data-metad0:/data/meta
      - logs-metad0:/logs
    networks:
      - nebula-net

  metad1:
    image: vesoft/nebula-metad:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.2.3:45500,192.168.2.4:45500,192.168.2.6:45500
      - --local_ip=192.168.2.4
      - --ws_ip=192.168.2.4
      - --port=45500
      - --data_path=/data/meta
      - --log_dir=/logs
      - --v=0
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == ecnu02
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.2.4:11000/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - target: 11000
        published: 11000
        protocol: tcp
        mode: host
      - target: 11002
        published: 11002
        protocol: tcp
        mode: host
      - target: 45500
        published: 45500
        protocol: tcp
        mode: host
    volumes:
      - data-metad1:/data/meta
      - logs-metad1:/logs
    networks:
      - nebula-net

  metad2:
    image: vesoft/nebula-metad:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.2.3:45500,192.168.2.4:45500,192.168.2.6:45500
      - --local_ip=192.168.2.6
      - --ws_ip=192.168.2.6
      - --port=45500
      - --data_path=/data/meta
      - --log_dir=/logs
      - --v=0
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == ecnu04
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.2.6:11000/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - target: 11000
        published: 11000
        protocol: tcp
        mode: host
      - target: 11002
        published: 11002
        protocol: tcp
        mode: host
      - target: 45500
        published: 45500
        protocol: tcp
        mode: host
    volumes:
      - data-metad2:/data/meta
      - logs-metad2:/logs
    networks:
      - nebula-net

  storaged0:
    image: vesoft/nebula-storaged:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.2.3:45500,192.168.2.4:45500,192.168.2.6:45500
      - --local_ip=192.168.2.3
      - --ws_ip=192.168.2.3
      - --port=44500
      - --data_path=/data/storage
      - --log_dir=/logs
      - --v=0
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == ecnu01
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.2.3:12000/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - target: 12000
        published: 12000
        protocol: tcp
        mode: host
      - target: 12002
        published: 12002
        protocol: tcp
        mode: host
    volumes:
      - data-storaged0:/data/storage
      - logs-storaged0:/logs
    networks:
      - nebula-net
  storaged1:
    image: vesoft/nebula-storaged:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.2.3:45500,192.168.2.4:45500,192.168.2.6:45500
      - --local_ip=192.168.2.4
      - --ws_ip=192.168.2.4
      - --port=44500
      - --data_path=/data/storage
      - --log_dir=/logs
      - --v=0
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == ecnu02
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.2.4:12000/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - target: 12000
        published: 12000
        protocol: tcp
        mode: host
      - target: 12002
        published: 12004
        protocol: tcp
        mode: host
    volumes:
      - data-storaged1:/data/storage
      - logs-storaged1:/logs
    networks:
      - nebula-net

  storaged2:
    image: vesoft/nebula-storaged:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.2.3:45500,192.168.2.4:45500,192.168.2.6:45500
      - --local_ip=192.168.2.6
      - --ws_ip=192.168.2.6
      - --port=44500
      - --data_path=/data/storage
      - --log_dir=/logs
      - --v=0
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == ecnu04
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.2.6:12000/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - target: 12000
        published: 12000
        protocol: tcp
        mode: host
      - target: 12002
        published: 12006
        protocol: tcp
        mode: host
    volumes:
      - data-storaged2:/data/storage
      - logs-storaged2:/logs
    networks:
      - nebula-net
  graphd0:
    image: vesoft/nebula-graphd:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.2.3:45500,192.168.2.4:45500,192.168.2.6:45500
      - --port=3699
      - --ws_ip=192.168.2.3
      - --log_dir=/logs
      - --v=0
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == ecnu01
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.2.3:13000/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - target: 3699
        published: 3699
        protocol: tcp
        mode: host
      - target: 13000
        published: 13000
        protocol: tcp
#        mode: host
      - target: 13002
        published: 13002
        protocol: tcp
        mode: host
    volumes:
      - logs-graphd:/logs
    networks:
      - nebula-net

  graphd1:
    image: vesoft/nebula-graphd:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.2.3:45500,192.168.2.4:45500,192.168.2.6:45500
      - --port=3699
      - --ws_ip=192.168.2.4
      - --log_dir=/logs
      - --v=2
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == ecnu02
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.2.4:13001/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - target: 3699
        published: 3640
        protocol: tcp
        mode: host
      - target: 13000
        published: 13001
        protocol: tcp
        mode: host
      - target: 13002
        published: 13003
        protocol: tcp
#        mode: host
    volumes:
      - logs-graphd2:/logs
    networks:
      - nebula-net
  graphd2:
    image: vesoft/nebula-graphd:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.2.3:45500,192.168.2.4:45500,192.168.2.6:45500
      - --port=3699
      - --ws_ip=192.168.2.6
      - --log_dir=/logs
      - --v=0
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == ecnu04
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.2.6:13002/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - target: 3699
        published: 3641
        protocol: tcp
        mode: host
      - target: 13000
        published: 13004
        protocol: tcp
#        mode: host
      - target: 13002
        published: 13005
        protocol: tcp
        mode: host
    volumes:
      - logs-graphd3:/logs
    networks:
      - nebula-net
networks:
  nebula-net:
    external: true
    attachable: true
    name: host
volumes:
  data-metad0:
  logs-metad0:
  data-metad1:
  logs-metad1:
  data-metad2:
  logs-metad2:
  data-storaged0:
  logs-storaged0:
  data-storaged1:
  logs-storaged1:
  data-storaged2:
  logs-storaged2:
  logs-graphd:
  logs-graphd2:
  logs-graphd3:

[steam]

下次发日志、配置信息可以用 markdown 的代码包裹语法把日志包裹起来方便阅读呀~

```
日志 / 配置信息 / 代码
```

[SeniaCiel]

了解，谢谢

[henson]

暂不支持2.0版本，这个后面会加上