dolphinscheduler部署文档（集群版）

2020-03-31 本文已影响0人 Rudolf_liu

集群规划

ds集群（生产配置）

hostname	CPU	Memory	Disk size	Master	Worker	Logger	Alert	API	UI
DS01	8C	16G	50G	√	√	√	√	√	√
DS02	8C	16G	50G	√	√	√
DS03	4C	8G	50G		√	√

若是部署了大数据框架，则机器性能需要进一步提升

zk集群

1C-2G-50G

准备（每台机器都要这样操作）

创建用户

# 创建用户需使用root登录，设置部署用户名，请自行修改，后面以dolphinscheduler为例
useradd dolphinscheduler;

# 设置用户密码，请自行修改，后面以dolphinscheduler123为例
echo "dolphinscheduler" | passwd --stdin dolphinscheduler

# 配置sudo免密
echo 'dolphinscheduler  ALL=(ALL)  NOPASSWD: NOPASSWD: ALL' >> /etc/sudoers

hosts映射

vi /etc/hosts

10.10.xxx.xxx master
10.10.xxx.xxx slave1
10.10.xxx.xxx slave2

配置免密登录

su dolphinscheduler;

ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa
cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
chmod 600 ~/.ssh/authorized_keys

# 分发
su dolphinscheduler;
for ip in slave1 slave2;     #请将此处ds2 ds3替换为自己要部署的机器的hostname
do
    ssh-copy-id  $ip   #该操作执行过程中需要手动输入dolphinscheduler用户的密码
done

在每台机器上使用ssh，需要输入yes，让机器记录下public-key，包括localhost

下载

后端: wget https://downloads.apache.org/incubator/dolphinscheduler/1.2.0/apache-dolphinscheduler-incubating-1.2.0-dolphinscheduler-backend-bin.tar.gz
前端: wget https://downloads.apache.org/incubator/dolphinscheduler/1.2.0/apache-dolphinscheduler-incubating-1.2.0-dolphinscheduler-front-bin.tar.gz

部署后端

安装

mkdir -p /opt/app/dolphinscheduler    # ds的安装目录
mkdir -p /opt/soft/dolphinscheduler    # ds的下载目录
cd /opt/soft/dolphinscheduler
tar -zxvf apache-dolphinscheduler-incubating-1.2.0-dolphinscheduler-backend-bin.tar.gz -C /opt/app/dolphinscheduler
mv apache-dolphinscheduler-incubating-1.2.0-dolphinscheduler-backend-bin  dolphinscheduler-backend

tree -L 1    # 查看目录结构
.
├── bin           # 基础服务启动脚本
├── conf          # 项目配置文件
├── DISCLAIMER-WIP# DISCLAIMER文件
├── install.sh    # 一键部署脚本
├── lib           # 项目依赖jar包，包括各个模块jar和第三方jar
├── LICENSE       # LICENSE文件
├── licenses      # 运行时license
├── NOTICE        # NOTICE文件
├── script        # 集群启动、停止和服务监控启停脚本
└── sql           # 项目依赖sql文件

# 授权解压目录
sudo chown -R dolphinscheduler:dolphinscheduler dolphinscheduler-backend
# 授权安装目录
sudo chown -R dolphinscheduler:dolphinscheduler /opt/app/dolphinscheduler

jdk软连接

echo $JAVA_HOME    # 没有软连接后面在启动脚本的时候会报错：nohup /bin/java不存在
sudo ln -s /usr/java/jdk1.8.0_111/bin/java /usr/bin/java
原先软连接关联的是openjdk的需要删掉

数据库初始化

创建数据库

mysql -uroot -p
-- 创建数据库
CREATE DATABASE dolphinscheduler DEFAULT CHARACTER SET utf8 DEFAULT COLLATE utf8_general_ci;
-- 创建用户及授权（可能需要修改数据库密码等级）
GRANT ALL PRIVILEGES ON dolphinscheduler.* TO 'dolphinscheduler'@'%' IDENTIFIED BY 'dolphinscheduler';
GRANT ALL PRIVILEGES ON dolphinscheduler.* TO 'dolphinscheduler'@'localhost' IDENTIFIED BY 'dolphinscheduler';
flush privileges;

修改配置

vi conf/application-dao.properties
# 需要注释掉postgresql的信息
# postgre
#spring.datasource.driver-class-name=org.postgresql.Driver
#spring.datasource.url=jdbc:postgresql://localhost:5432/dolphinscheduler
# mysql
spring.datasource.driver-class-name=com.mysql.jdbc.Driver
spring.datasource.url=jdbc:mysql://master:3306/dolphinscheduler?useUnicode=true&characterEncoding=UTF-8     #需要修改ip，本机localhost即可
spring.datasource.username=dolphinscheduler
spring.datasource.password=dolphinscheduler

执行脚本初始化数据表

sh script/create-dolphinscheduler.sh

尖叫提示：执行脚本前需要下载mysql-java驱动程序包（需要选择对应mysql版本的驱动，不是bin），https://downloads.mysql.com/archives/c-j/
尖叫提示：如果执行上述脚本报 ”/bin/java: No such file or directory“ 错误，请在/etc/profile下配置 JAVA_HOME 及 PATH 变量

修改环境变量

vi conf/env/.dolphinscheduler_env.sh    # 这是一个隐藏文件
# JAVA_HOME 和 PATH 是必须要配置的，其他没有用到的可以忽略或者注释掉
#export HADOOP_HOME=/opt/soft/hadoop
#export HADOOP_CONF_DIR=/opt/soft/hadoop/etc/hadoop
#export SPARK_HOME1=/opt/soft/spark1
#export SPARK_HOME2=/opt/soft/spark2
#export PYTHON_HOME=/opt/soft/python
export JAVA_HOME=/usr/java/jdk1.8.0_111
#export HIVE_HOME=/opt/soft/hive
#export FLINK_HOME=/opt/soft/flink
export PATH=$HADOOP_HOME/bin:$SPARK_HOME2/bin:$PYTHON_HOME:$JAVA_HOME/bin:$HIVE_HOME/bin:$PATH:$FLINK_HOME/bin:$PATH

安装python的zookeeper工具kazoo（每台都要安装）

#安装pip
sudo yum -y install python-pip;  #ubuntu请使用 sudo apt-get install python-pip
sudo pip install kazoo;

# 注意：如果yum没找到python-pip，也可以通过下面方式安装
sudo curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py
sudo python get-pip.py  # 如果是python3，使用sudo python3 get-pip.py
#然后
sudo pip install kazoo;

修改一键部署脚本

vi install.sh
# for example postgresql or mysql ...
dbtype="mysql"

# db config
# db address and port
dbhost="master:3306"

# db name
dbname="dolphinscheduler"

# db username
username="dolphinscheduler"

# db passwprd
# Note: if there are special characters, please use the \ transfer character to transfer
passowrd="dolphinscheduler"

# conf/config/install_config.conf config
# Note: the installation path is not the same as the current path (pwd)
# 将应用安装到哪个目录下
installPath="/opt/app/dolphinscheduler"

# deployment user
# Note: the deployment user needs to have sudo privileges and permissions to operate hdfs. If hdfs is enabled, the root directory needs to be created by itself
# 使用哪个用户部署
deployUser="dolphinscheduler"

# zk cluster,集群方式以逗号分隔
zkQuorum="master:2181,slave1:2181,slave2:2181"

# install hosts
# Note: install the scheduled hostname list. If it is pseudo-distributed, just write a pseudo-distributed hostname
# 在哪些机器上部署
ips="master,slave1,slave2"

# conf/config/run_config.conf config
# run master machine
# Note: list of hosts hostname for deploying master
masters="master,slave1"

# run worker machine
# note: list of machine hostnames for deploying workers
workers="master,slave1,slave2"

# run alert machine
# note: list of machine hostnames for deploying alert server
alertServer="master"

# run api machine
# note: list of machine hostnames for deploying api server
apiServers="master"

# 邮件服务
# alert config
# mail protocol
mailProtocol="SMTP"

# mail server host
mailServerHost="****"

# mail server port
mailServerPort="***"

# sender
mailSender="*******"

# user
mailUser="*******"

# sender password
mailPassword="*******"

# TLS mail protocol support
starttlsEnable="false"

sslTrust="*******"

# SSL mail protocol support
# note: The SSL protocol is enabled by default.
# only one of TLS and SSL can be in the true state.
sslEnable="true"

# download excel path
xlsFilePath="/tmp/xls"

# 业务用到的比如sql等资源文件上传到哪里，可以设置：HDFS,S3,NONE，单机如果想使用本地文件系统，请配置为HDFS，因为HDFS支持本地文件系统；如果不需要资源上传功能请选择NONE。强调一点：使用本地文件系统不需要部署hadoop
resUploadStartupType="HDFS"

# 这里以保存到本地文件系统为例
#注：但是如果你想上传到HDFS的话，NameNode启用了HA，则需要将core-site.xml和hdfs-site.xml放到conf目录下，本例即是放到/opt/dolphinscheduler/conf下面，并配置namenode cluster名称；如果NameNode不是HA,则修改为具体的ip或者主机名即可
defaultFS="hdfs://hadoopcluster/dolphinscheduler"    #hdfs://{具体的ip/主机名}:8020

# 如果ResourceManager是HA，则配置为ResourceManager节点的主备ip或者hostname,比如"192.168.xx.xx,192.168.xx.xx"，否则如果是单ResourceManager或者根本没用到yarn,请配置yarnHaIps=""即可，我这里没用到yarn，配置为""
yarnHaIps=""

# 如果是单ResourceManager，则配置为ResourceManager节点ip或主机名，否则保持默认值即可。我这里没用到yarn，保持默认
singleYarnIp=""

# 由于hdfs支持本地文件系统，需要确保本地文件夹存在且有读写权限
hdfsPath="/data/dolphinscheduler"

执行一键部署脚本

su dolphinscheduler

sh install.sh

查看进程是否启动

jps

master
MasterServer         ----- master服务
WorkerServer         ----- worker服务
LoggerServer         ----- logger服务
ApiApplicationServer ----- api服务
AlertServer          ----- alert服务

slave1
MasterServer         ----- master服务
WorkerServer         ----- worker服务
LoggerServer         ----- logger服务

slave2
WorkerServer         ----- worker服务
LoggerServer         ----- logger服务

解压

tar -zxvf apache-dolphinscheduler-incubating-1.2.0-dolphinscheduler-front-bin.tar.gz -C /opt/soft/dolphinscheduler;
mv apache-dolphinscheduler-incubating-1.2.0-dolphinscheduler-front-bin dolphinscheduler-ui

部署前端

部署

自动化部署

执行自动化部署脚本

cd dolphinscheduler-ui;
sh ./install-dolphinscheduler-ui.sh;
执行后，会在运行中请键入前端端口，默认端口是8888，如果选择默认，键入回车，或者键入其他端口
然后会让键入跟前端ui交互的api-server的ip
接着是让键入跟前端ui交互的api-server的port
接着是操作系统选择
等待部署完成

修改nginx配置

vi /etc/nginx/nginx.conf
# add param 在http方法体内添加即可
client_max_body_size 1024m;
systemctl restart nginx

手动部署

安装nginx，官网下载: http://nginx.org/en/download.html 或者 yum install nginx -y
修改nginx配置文件

vi /etc/nginx/nginx.conf
server {
  listen       8888;# 访问端口(自行修改)
  server_name  localhost;
  #charset koi8-r;
  #access_log  /var/log/nginx/host.access.log  main;
  location / {
      root   /opt/app/dolphinscheduler-ui/dist;      # 前端解压的dist目录地址(自行修改)
      index  index.html index.html;
  }
  location /dolphinscheduler {
      proxy_pass http://localhost:12345;    # api服务地址(自行修改)
      proxy_set_header Host $host;
      proxy_set_header X-Real-IP $remote_addr;
      proxy_set_header x_real_ipP $remote_addr;
      proxy_set_header remote_addr $remote_addr;
      proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
      proxy_http_version 1.1;
      proxy_connect_timeout 4s;
      proxy_read_timeout 30s;
      proxy_send_timeout 12s;
      proxy_set_header Upgrade $http_upgrade;
      proxy_set_header Connection "upgrade";
  }
  #error_page  404              /404.html;
  # redirect server error pages to the static page /50x.html
  #
  error_page   500 502 503 504  /50x.html;
  location = /50x.html {
      root   /usr/share/nginx/html;
  }
}

初始账号密码

地址：master:8888 用户名密码：admin/dolphinscheduler123

指令

启动：
    启动所有进程：sh bin/start-all.sh
    启动master-server：sh bin/dolphinscheduler-daemon.sh start master-server
    启动worker-server：sh bin/dolphinscheduler-daemon.sh start worker-server
    启动logger-server：sh bin/dolphinscheduler-daemon.sh start logger-server
    启动alert-server：sh bin/dolphinscheduler-daemon.sh start alert-server
    启动api-server：sh bin/dolphinscheduler-daemon.sh start api-server

停止：
    停止所有进程：sh bin/stop-all.sh
    停止master-server：sh bin/dolphinscheduler-daemon.sh stop master-server
    停止worker-server：sh bin/dolphinscheduler-daemon.sh stop worker-server
    停止logger-server：sh bin/dolphinscheduler-daemon.sh stop logger-server
    停止alert-server：sh bin/dolphinscheduler-daemon.sh stop alert-server
    停止api-server：sh bin/dolphinscheduler-daemon.sh stop api-server