docker swarm部署 graph无法启动

问答 问题
,
1

当前图库版本1.1，使用docker swarm 部署测试环境时，3个graph节点无法启动。
docker stack 文件如下：

version: '3.6'
services:
  metad0:
    image: vesoft/nebula-metad:v1.0.1
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=IP1:45500,IP2:45500,IP3:45500
      - --local_ip=IP1
      - --ws_ip=IP1
      - --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 == CS-1155-YQFXY-1
    healthcheck:
      test: ["CMD", "curl", "-f", "http://IP1:11000/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:v1.0.1
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=IP1:45500,IP2:45500,IP3:45500
      - --local_ip=IP2
      - --ws_ip=IP2
      - --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 == CS-1155-YQFXYJ-1
    healthcheck:
      test: ["CMD", "curl", "-f", "http://IP2:11000/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:v1.0.1
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=IP1:45500,IP2:45500,IP3:45500
      - --local_ip=IP3
      - --ws_ip=IP3
      - --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 == CS-1155-YQFXYJ-2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://IP3:11000/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:v1.0.1
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=IP1:45500,IP2:45500,IP3:45500
      - --local_ip=IP1
      - --ws_ip=IP1
      - --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 == CS-1155-YQFXY-1
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://IP1:12000/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:v1.0.1
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=IP1:45500,IP2:45500,IP3:45500
      - --local_ip=IP2
      - --ws_ip=IP2
      - --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 == CS-1155-YQFXYJ-1
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://IP2:12000/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:v1.0.1
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=IP1:45500,IP2:45500,IP3:45500
      - --local_ip=IP3
      - --ws_ip=IP3
      - --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 == CS-1155-YQFXYJ-2
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://IP3:12000/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
  graphd1:
    image: vesoft/nebula-graphd:v1.0.1
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=IP1:45500,IP2:45500,IP3:45500
      - --port=3699
      - --ws_ip=IP1
      - --log_dir=/logs
      - --v=0
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == CS-1155-YQFXY-1
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://IP1:13000/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

  graphd2:
    image: vesoft/nebula-graphd:v1.0.1
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=IP1:45500,IP2:45500,IP3:45500
      - --port=3699
      - --ws_ip=IP2
      - --log_dir=/logs
      - --v=2
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == CS-1155-YQFXYJ-1
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://IP2:13000/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-graphd2:/logs
    networks:
      - nebula-net
  graphd3:
    image: vesoft/nebula-graphd:v1.0.1
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=IP1:45500,IP2:45500,IP3:45500
      - --port=3699
      - --ws_ip=IP3
      - --log_dir=/logs
      - --v=0
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == CS-1155-YQFXYJ-2
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://IP3:13000/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-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:

启动集群后，发现3个graph均未启动，使用
docker service ps xxx --no-trunc
查看异常信息如下：

Failed 58 seconds ago      "starting container failed: OCI runtime create failed: container_linux.go:348: starting container process caused "exec: \"--meta_server_addrs=ip1:45500,ip2:45500,ip3:45500\": executable file not found in $PATH": unknown"

百度搜索是docker版本与系统版本不一致，但是其他的镜像是可以正常启动的。

2

尝试 删除 volume 重启 之后，依然还是这个错。

docker volume ls
docker volume rm xxx
3

已修复。换了一个graph镜像之后就可以了 :dog:

1 个赞