关于nebula:用-Docker-swarm-快速部署分布式图数据库-Nebula-Graph-集群

44次阅读

共计 10914 个字符，预计需要花费 28 分钟才能阅读完成。

本文作者系：视线金服工程师 | 吴海胜
首发于 Nebula Graph 论坛：https://discuss.nebula-graph.com.cn/t/topic/1388

一、前言

本文介绍如何应用 Docker Swarm 来部署 Nebula Graph 集群，并部署客户端负载平衡和高可用。

二、nebula 集群搭建

2.1 环境筹备

机器筹备

在装置前确保所有机器已装置 Docker

2.2 初始化 swarm 集群

在 192.168.1.166 机器上执行

$ docker swarm init --advertise-addr 192.168.1.166
Swarm initialized: current node (dxn1zf6l61qsb1josjja83ngz) is now a manager.
To add a worker to this swarm, run the following command:
 docker swarm join \
 --token SWMTKN-1-49nj1cmql0jkz5s954yi3oex3nedyz0fb0xx14ie39trti4wxv-8vxv8rssmk743ojnwacrr2e7c \
 192.168.1.166:2377
 
To add a manager to this swarm, run 'docker swarm join-token manager' and follow the instructions.

2.3 退出 worker 节点

依据 init 命令提醒内容，退出 swarm worker 节点，在 192.168.1.167 192.168.1.168 别离执行

docker swarm join \
 --token SWMTKN-1-49nj1cmql0jkz5s954yi3oex3nedyz0fb0xx14ie39trti4wxv-8vxv8rssmk743ojnwacrr2e7c \
 192.168.1.166:2377

2.4 验证集群

docker node ls
 
ID                            HOSTNAME            STATUS              AVAILABILITY        MANAGER STATUS      ENGINE VERSION
h0az2wzqetpwhl9ybu76yxaen *   KF2-DATA-166        Ready               Active              Reachable           18.06.1-ce
q6jripaolxsl7xqv3cmv5pxji     KF2-DATA-167        Ready               Active              Leader              18.06.1-ce
h1iql1uvm7123h3gon9so69dy     KF2-DATA-168        Ready               Active                                  18.06.1-ce

2.5 配置 docker stack

vi docker-stack.yml

配置如下内容

version: '3.6'
services:
  metad0:
    image: vesoft/nebula-metad:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.1.166:45500,192.168.1.167:45500,192.168.1.168:45500
      - --local_ip=192.168.1.166
      - --ws_ip=192.168.1.166
      - --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 == KF2-DATA-166
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.1.166:11000/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=192.168.1.166:45500,192.168.1.167:45500,192.168.1.168:45500
      - --local_ip=192.168.1.167
      - --ws_ip=192.168.1.167
      - --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 == KF2-DATA-167
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.1.167:11000/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=192.168.1.166:45500,192.168.1.167:45500,192.168.1.168:45500
      - --local_ip=192.168.1.168
      - --ws_ip=192.168.1.168
      - --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 == KF2-DATA-168
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.1.168:11000/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=192.168.1.166:45500,192.168.1.167:45500,192.168.1.168:45500
      - --local_ip=192.168.1.166
      - --ws_ip=192.168.1.166
      - --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 == KF2-DATA-166
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.1.166:12000/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=192.168.1.166:45500,192.168.1.167:45500,192.168.1.168:45500
      - --local_ip=192.168.1.167
      - --ws_ip=192.168.1.167
      - --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 == KF2-DATA-167
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.1.167:12000/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=192.168.1.166:45500,192.168.1.167:45500,192.168.1.168:45500
      - --local_ip=192.168.1.168
      - --ws_ip=192.168.1.168
      - --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 == KF2-DATA-168
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.1.168:12000/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:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.1.166:45500,192.168.1.167:45500,192.168.1.168:45500
      - --port=3699
      - --ws_ip=192.168.1.166
      - --log_dir=/logs
      - --v=0
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == KF2-DATA-166
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.1.166:13000/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:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.1.166:45500,192.168.1.167:45500,192.168.1.168:45500
      - --port=3699
      - --ws_ip=192.168.1.167
      - --log_dir=/logs
      - --v=2
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == KF2-DATA-167
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.1.167:13001/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
  graphd3:
    image: vesoft/nebula-graphd:nightly
    env_file:
      - ./nebula.env
    command:
      - --meta_server_addrs=192.168.1.166:45500,192.168.1.167:45500,192.168.1.168:45500
      - --port=3699
      - --ws_ip=192.168.1.168
      - --log_dir=/logs
      - --v=0
      - --minloglevel=2
    deploy:
      replicas: 1
      restart_policy:
        condition: on-failure
      placement:
        constraints:
          - node.hostname == KF2-DATA-168
    depends_on:
      - metad0
      - metad1
      - metad2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://192.168.1.168:13002/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    ports:
      - target: 3699
        published: 3641
        protocol: tcp
        mode: host
      - target: 13000
        published: 13002
        protocol: tcp
#        mode: host
      - target: 13002
        published: 13004
        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:

编辑 nebula.env，退出如下内容

TZ=UTC
USER=root

2.6 启动 nebula 集群

docker stack deploy nebula -c docker-stack.yml

三、集群负载平衡及高可用配置

Nebula Graph 的客户端目前（1.X）没有提供负载平衡的能力，只是随机选一个 graphd 去连贯。所以生产应用的时候要本人做个负载平衡和高可用。

图 3.1

将整个部署架构分为三层，数据服务层，负载平衡层及高可用层。如图 3.1 所示

负载平衡层：对 client 申请做负载平衡，将申请散发至下方数据服务层

高可用层: 这里实现的是 haproxy 的高可用，保障负载平衡层的服务从而保障整个集群的失常服务

3.1 负载平衡配置

haproxy 应用 docker-compose 配置。别离编辑以下三个文件

Dockerfile 退出以下内容

FROM haproxy:1.7
COPY haproxy.cfg /usr/local/etc/haproxy/haproxy.cfg
EXPOSE 3640

docker-compose.yml 退出以下内容

version: "3.2"
services:
  haproxy:
    container_name: haproxy
    build: .
    volumes:
      - ./haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg
    ports:
      - 3640:3640
    restart: always
    networks:
      - app_net
networks:
  app_net:
    external: true

haproxy.cfg 退出以下内容

global
    daemon
    maxconn 30000
    log 127.0.0.1 local0 info
    log 127.0.0.1 local1 warning

defaults
    log-format %hr\ %ST\ %B\ %Ts
    log  global
    mode http
    option http-keep-alive
    timeout connect 5000ms
    timeout client 10000ms
    timeout server 50000ms
    timeout http-request 20000ms

# custom your own frontends && backends && listen conf
# CUSTOM

listen graphd-cluster
    bind *:3640
    mode tcp
    maxconn 300
    balance roundrobin
    server server1 192.168.1.166:3699 maxconn 300 check
    server server2 192.168.1.167:3699 maxconn 300 check
    server server3 192.168.1.168:3699 maxconn 300 check

listen stats
    bind *:1080
    stats refresh 30s
    stats uri /stats

3.2 启动 haproxy

docker-compose up -d

3.3 高可用配置

注：配置 keepalive 需事后筹备好 vip（虚构 ip），在以下配置中 192.168.1.99 便为虚构 ip

在 192.168.1.166、192.168.1.167、192.168.1.168 上 均做以下配置

装置 keepalived

apt-get update && apt-get upgrade && apt-get install keepalived -y

更改 keepalived 配置文件 /etc/keepalived/keepalived.conf（三台机器中 做如下配置，priority 应设置不同值确定优先级）

192.168.1.166 机器配置

global_defs {router_id lb01 # 标识信息，一个名字而已；}
vrrp_script chk_haproxy {script "killall -0 haproxy"    interval 2}
vrrp_instance VI_1 {
    state MASTER
    interface ens160
    virtual_router_id 52
    priority 999
    # 设定 MASTER 与 BACKUP 负载均衡器之间同步查看的工夫距离，单位是秒
    advert_int 1
    # 设置验证类型和明码
    authentication {
    # 设置验证类型，次要有 PASS 和 AH 两种
        auth_type PASS
    # 设置验证明码，在同一个 vrrp_instance 下，MASTER 与 BACKUP 必须应用雷同的明码能力失常通信
        auth_pass amber1
    }
    virtual_ipaddress {
        # 虚构 IP 为 192.168.1.99/24; 绑定接口为 ens160; 别名 ens169:1，主备雷同
        192.168.1.99/24 dev ens160 label ens160:1
    }
    track_script {chk_haproxy}
}

167 机器配置

global_defs {router_id lb01 # 标识信息，一个名字而已；}
vrrp_script chk_haproxy {script "killall -0 haproxy"    interval 2}
vrrp_instance VI_1 {
    state BACKUP
    interface ens160
    virtual_router_id 52
    priority 888
    # 设定 MASTER 与 BACKUP 负载均衡器之间同步查看的工夫距离，单位是秒
    advert_int 1
    # 设置验证类型和明码
    authentication {
    # 设置验证类型，次要有 PASS 和 AH 两种
        auth_type PASS
    # 设置验证明码，在同一个 vrrp_instance 下，MASTER 与 BACKUP 必须应用雷同的明码能力失常通信
        auth_pass amber1
    }
    virtual_ipaddress {
        # 虚构 IP 为 192.168.1.99/24; 绑定接口为 ens160; 别名 ens160:1，主备雷同
        192.168.1.99/24 dev ens160 label ens160:1
    }
    track_script {chk_haproxy}
}

168 机器配置

global_defs {router_id lb01 # 标识信息，一个名字而已；}
vrrp_script chk_haproxy {script "killall -0 haproxy"    interval 2}
vrrp_instance VI_1 {
    state BACKUP
    interface ens160
    virtual_router_id 52
    priority 777
    # 设定 MASTER 与 BACKUP 负载均衡器之间同步查看的工夫距离，单位是秒
    advert_int 1
    # 设置验证类型和明码
    authentication {
    # 设置验证类型，次要有 PASS 和 AH 两种
        auth_type PASS
    # 设置验证明码，在同一个 vrrp_instance 下，MASTER 与 BACKUP 必须应用雷同的明码能力失常通信
        auth_pass amber1
    }
    virtual_ipaddress {
        # 虚构 IP 为 192.168.1.99/24; 绑定接口为 ens160; 别名 ens160:1，主备雷同
        192.168.1.99/24 dev ens160 label ens160:1
    }
    track_script {chk_haproxy}
}

keepalived 相干命令

# 启动 keepalived
systemctl start keepalived
# 使 keepalived 开机自启
systemctl enable keeplived
# 重启 keepalived
systemctl restart keepalived

四、其余

离线怎么部署？把镜像更改为公有镜像库就成了，有问题欢送来勾结啊。

我的小鱼你醒了 还意识晚上吗 昨夜你已经说 愿夜幕永不开启

如果你对本文有任何疑难，欢送来论坛和原作者聊聊~~ 原帖地址：https://discuss.nebula-graph.com.cn/t/topic/1388

正文完
nebula
发表至： nebula
2020-10-14
 0
关于nebula:从全球顶级数据库大会-SIGMOD-看数据库发展趋势
关于nebula:关于-LLM-和图数据库知识图谱的那些事
关于nebula:百亿级图数据在快手安全情报的应用与挑战
关于nebula:图查询语言-nGQL-简明教程-vol01-快速入门