Spark Writer导入数据时报错:java.net.SocketTimeouteException:connect timed out...

nebula 版本:v2 nightly
studio 版本:v2.1.5-beta
部署方式 :单机
硬件信息
磁盘: 2T SSD
CPU、内存信息:32Core 64G


请问下大佬,这样的情况,配置文件要怎样修改?几天没数据进入了 :sob:

你贴一下数据导入所用的配置文件吧。
报错信息是metaClient连接超时

  1. 你看下metad是否正常
  2. 服务所在机器是不是开启了防火墙,看下提交Exchange任务的机器是否可访问metad地址
version: '3.4'
services:
  metad0:
    image: vesoft/nebula-metad:v2-nightly
    environment:
      USER: root
      TZ:   "${TZ}"
    command:
      - --meta_server_addrs=metad0:9559,metad1:9559,metad2:9559
      - --local_ip=metad0
      - --ws_ip=metad0
      - --port=9559
      - --ws_http_port=19559
      - --data_path=/data/meta
      - --log_dir=/logs
      - --v=0
      - --minloglevel=0
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://metad0:19559/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - 34006:9559
      - 19559
      - 19560
    volumes:
      - ./data/meta0:/data/meta
      - ./logs/meta0:/logs
    networks:
      - nebula-net
    restart: on-failure
    cap_add:
      - SYS_PTRACE

  metad1:
    image: vesoft/nebula-metad:v2-nightly
    environment:
      USER: root
      TZ:   "${TZ}"
    command:
      - --meta_server_addrs=metad0:9559,metad1:9559,metad2:9559
      - --local_ip=metad1
      - --ws_ip=metad1
      - --port=9559
      - --ws_http_port=19559
      - --data_path=/data/meta
      - --log_dir=/logs
      - --v=0
      - --minloglevel=0
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://metad1:19559/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - 34003:9559
      - 19559
      - 19560
    volumes:
      - ./data/meta1:/data/meta
      - ./logs/meta1:/logs
    networks:
      - nebula-net
    restart: on-failure
    cap_add:
      - SYS_PTRACE

  metad2:
    image: vesoft/nebula-metad:v2-nightly
    environment:
      USER: root
      TZ:   "${TZ}"
    command:
      - --meta_server_addrs=metad0:9559,metad1:9559,metad2:9559
      - --local_ip=metad2
      - --ws_ip=metad2
      - --port=9559
      - --ws_http_port=19559
      - --data_path=/data/meta
      - --log_dir=/logs
      - --v=0
      - --minloglevel=0
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://metad2:19559/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - 34001:9559
      - 19559
      - 19560
    volumes:
      - ./data/meta2:/data/meta
      - ./logs/meta2:/logs
    networks:
      - nebula-net
    restart: on-failure
    cap_add:
      - SYS_PTRACE

  storaged0:
    image: vesoft/nebula-storaged:v2-nightly
    environment:
      USER: root
      TZ:   "${TZ}"
    command:
      - --meta_server_addrs=metad0:9559,metad1:9559,metad2:9559
      - --local_ip=storaged0
      - --ws_ip=storaged0
      - --port=9779
      - --ws_http_port=19779
      - --data_path=/data/storage
      - --log_dir=/logs
      - --v=0
      - --minloglevel=0
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://storaged0:19779/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - 9779
      - 19779
      - 19780
    volumes:
      - ./data/storage0:/data/storage
      - ./logs/storage0:/logs
    networks:
      - nebula-net
    restart: on-failure
    cap_add:
      - SYS_PTRACE

  storaged1:
    image: vesoft/nebula-storaged:v2-nightly
    environment:
      USER: root
      TZ:   "${TZ}"
    command:
      - --meta_server_addrs=metad0:9559,metad1:9559,metad2:9559
      - --local_ip=storaged1
      - --ws_ip=storaged1
      - --port=9779
      - --ws_http_port=19779
      - --data_path=/data/storage
      - --log_dir=/logs
      - --v=0
      - --minloglevel=0
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://storaged1:19779/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - 9779
      - 19779
      - 19780
    volumes:
      - ./data/storage1:/data/storage
      - ./logs/storage1:/logs
    networks:
      - nebula-net
    restart: on-failure
    cap_add:
      - SYS_PTRACE

  storaged2:
    image: vesoft/nebula-storaged:v2-nightly
    environment:
      USER: root
      TZ:   "${TZ}"
    command:
      - --meta_server_addrs=metad0:9559,metad1:9559,metad2:9559
      - --local_ip=storaged2
      - --ws_ip=storaged2
      - --port=9779
      - --ws_http_port=19779
      - --data_path=/data/storage
      - --log_dir=/logs
      - --v=0
      - --minloglevel=0
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://storaged2:19779/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - 9779
      - 19779
      - 19780
    volumes:
      - ./data/storage2:/data/storage
      - ./logs/storage2:/logs
    networks:
      - nebula-net
    restart: on-failure
    cap_add:
      - SYS_PTRACE

  graphd:
    image: vesoft/nebula-graphd:v2-nightly
    environment:
      USER: root
      TZ:   "${TZ}"
    command:
      - --meta_server_addrs=metad0:9559,metad1:9559,metad2:9559
      - --port=9669
      - --ws_ip=graphd
      - --ws_http_port=19669
      - --log_dir=/logs
      - --v=0
      - --minloglevel=0
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://graphd:19669/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - "9669:9669"
      - 19669
      - 19670
    volumes:
      - ./logs/graph:/logs
    networks:
      - nebula-net
    restart: on-failure
    cap_add:
      - SYS_PTRACE

  graphd1:
    image: vesoft/nebula-graphd:v2-nightly
    environment:
      USER: root
      TZ:   "${TZ}"
    command:
      - --meta_server_addrs=metad0:9559,metad1:9559,metad2:9559
      - --port=9669
      - --ws_ip=graphd1
      - --ws_http_port=19669
      - --log_dir=/logs
      - --v=0
      - --minloglevel=0
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://graphd1:19669/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - 9669
      - 19669
      - 19670
    volumes:
      - ./logs/graph1:/logs
    networks:
      - nebula-net
    restart: on-failure
    cap_add:
      - SYS_PTRACE

  graphd2:
    image: vesoft/nebula-graphd:v2-nightly
    environment:
      USER: root
      TZ:   "${TZ}"
    command:
      - --meta_server_addrs=metad0:9559,metad1:9559,metad2:9559
      - --port=9669
      - --ws_ip=graphd2
      - --ws_http_port=19669
      - --log_dir=/logs
      - --v=0
      - --minloglevel=0
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://graphd2:19669/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - 9669
      - 19669
      - 19670
    volumes:
      - ./logs/graph2:/logs
    networks:
      - nebula-net
    restart: on-failure
    cap_add:
      - SYS_PTRACE

networks:
  nebula-net:

docker-compose.yaml (6.9 KB)
请大佬帮忙看下哈

{
#park 相关配置
  spark: {
    app: {
      name: Spark Writer
    }
    driver: {
      cores: 16
      maxResultSize: 32G
    }
    cores {
      max: 128
    }
  }
  # Nebula Graph 相关配置
  nebula: {
    address:{
      # 以下为 Nebula Graph 的 Graph 服务和 Meta 服务所在机器的 IP 地址及端口
      # 如果有多个地址,格式为 "ip1:port","ip2:port","ip3:port"
      # 不同地址之间以英文逗号 (,) 隔开
      graph:["172.16.113.127:9669"]
      meta:["172.16.113.127:33837"]
    }

    # 填写的账号必须拥有 Nebula Graph 相应图空间的写数据权限
    user: user
    pswd: password
    # 填写 Nebula Graph 中需要写入数据的图空间名称
    space: TestGraph
    connection {
      timeout: 3000
      retry: 3
    }
    execution {
      retry: 3
    }
    error: {
      max: 32
      output: /tmp/errors
    }
    rate: {
      limit: 1024
      timeout: 1000
    }
  }
  # 处理标签
  tags: [
     
    ]
}

你在你运行spark writer 的机器上执行下 telnet 172.16.113.127 33837 截图

image

你需要修改docker-compose,将外面的端口固定。

    ports:
      - "9559:9559"
      - 11000
      - 11002

image 配置文件meta端口是:34006,是可以连上的。

配置文件中的meta端口是:34006,发的application.conf中的是之前的端口。端口是没问题的。

之前配置已经固定住了 刚搞错了 发了之前的Application.conf

也是端口没问题的前提下,出现起初的报错

可是你spark的配置用的是33837的端口呀

实际的配置文件就是34006 其余一致

会不会是32Core 64G并发时不够用了啊 然后就是超时错误

你现在是所有线程都报这个错,还是就个别,你可以修改线程数试试

是个别。因为有些实时任务调用查询数据没有问题。就是批量导数据是有问题的。

那你看下运行docker-compose 的机器设置的文件数是多少, ulimit -a 看是不是默认的。
还有你现在 sparkwriter 的连接超时时间是1秒,可能当大并发的的时候,这个有点小。这个现在没有支持传入,假如还是,不行,你搜 new MetaClient,传下 connect time

请问下怎么搜new MetaClient??

浙ICP备20010487号