DolphinScheduler-1.3.0-dev 功能体验

git clone https://github.com/apache/incubator-dolphinscheduler.git

git checkout dev-1.3.0
git checkout -b dev-1.3.0-cdh5.16.2

# 修改hadoop版本，也可以不修改
<hadoop.version>2.6.0</hadoop.version>
# 修改hive版本，必须进行调整
<hive.jdbc.version>1.1.0</hive.jdbc.version>
# 修改打包的version(所有模块均需要进行修改)
<version>1.3.0-cdh5.16.2</version>

mvn -U clean package -Prelease -Dmaven.test.skip=true

# 添加部署用户
useradd dscheduler;
# 设置密码
echo "dscheduler" | passwd --stdin dscheduler
# 配置免密
echo 'dscheduler  ALL=(ALL)  NOPASSWD: NOPASSWD: ALL' >> /etc/sudoers
# 切换到部署用户并生成ssh key
su dscheduler;
ssh-keygen -t rsa;
ssh-copy-id -i ~/.ssh/id_rsa.pub dscheduler@[hostname];

CREATE DATABASE dolphinscheduler DEFAULT CHARACTER SET utf8 DEFAULT COLLATE
utf8_general_ci;
CREATE USER 'dscheduler'@'%' IDENTIFIED BY 'dscheduler';
GRANT ALL PRIVILEGES ON dolphinscheduler.* TO 'dscheduler'@'%' IDENTIFIED BY 'dscheduler';
flush privileges;

# /u01 为存放ds安装包的目录，跟根据实际情况进行调整
tar -zxvf apache-dolphinscheduler-incubating-1.3.0-cdh5.16.2-dolphinscheduler-bin.tar.gz -C /u01
# 改一波目录名称
mv apache-dolphinscheduler-incubating-1.3.0-cdh5.16.2-dolphinscheduler-bin.tar.gz ds-130-backend
# 修改所属用户和权限
chmod -R 755 ds-130-backend;
chown -R dscheduler:dscheduler ds-130-backend;

bin - 服务启动脚本
conf - 配置文件目录
DISCLAIMER
install.sh - 一键部署脚本
lib - 依赖的jar包
LICENSE
licenses
NOTICE
script - 集群启动停止，更新数据库等脚本
sql - sql文件
ui - 前端UI

vi /u01/ds-130-backend/conf/datasource.properties;

# 修改pg为mysql 填写刚才配置的数据库用户密码
spring.datasource.driver-class-name=com.mysql.jdbc.Driver
spring.datasource.url=jdbc:mysql://xxxxxx:3306/dolphinscheduler?useUnicode=true&characterEncoding=UTF-8
spring.datasource.username=xxxxxx
spring.datasource.password=xxxxxx

./script/create-dolphinscheduler.sh

vi /u01/ds-130--backend/conf/env/dolphinscheduler_env.sh

# 测试集群上没有datax和flink请忽略相关配置
export HADOOP_HOME=/opt/cloudera/parcels/CDH/lib/hadoop
export HADOOP_CONF_DIR=/opt/cloudera/parcels/CDH/lib/hadoop/etc/hadoop
export SPARK_HOME1=/opt/cloudera/parcels/CDH/lib/spark
export SPARK_HOME2=/opt/cloudera/parcels/SPARK2/lib/spark2
export PYTHON_HOME=/usr/local/anaconda3/bin/python
export JAVA_HOME=/usr/java/jdk1.8.0_131
export HIVE_HOME=/opt/cloudera/parcels/CDH/lib/hive
export FLINK_HOME=/opt/soft/flink
export DATAX_HOME=/opt/soft/datax/bin/datax.py
export PATH=$HADOOP_HOME/bin:$SPARK_HOME1/bin:$SPARK_HOME2/bin:$PYTHON_HOME:$JAVA_HOME/bin:$HIVE_HOME/bin:$PATH:$FLINK_HOME/bin:$DATAX_HOME:$PATH

# NOTICE :  If the following config has special characters in the variable `.*[]^${}\+?|()@#&`, Please escape, for example, `[` escape to `\[`
# postgresql or mysql
dbtype="mysql"
# db config
# db address and port
dbhost="xxxx:3306"
# db username
username="xxxx"
# database name
dbname="dolphinscheduler"
# db passwprd
# NOTICE: if there are special characters, please use the \ to escape, for example, `[` escape to `\[`
password="xxxx"
# zk cluster
zkQuorum="xxx:2181,xxx:2181,xxx:2181"
# Note: the target installation path for dolphinscheduler, please not config as the same as the current path (pwd)
installPath="/opt/ds-1.3.0-dev-agent"
# 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
deployUser="dscheduler"
# alert config
# mail server host
mailServerHost="xxx"
# mail server port
# note: Different protocols and encryption methods correspond to different ports, when SSL/TLS is enabled, make sure the port is correct.
mailServerPort="25"
# sender
mailSender="xxx"
# user
mailUser="xxx"
# sender password
# note: The mail.passwd is email service authorization code, not the email login password.
mailPassword="xxx"
# TLS mail protocol support
starttlsEnable="false"
# SSL mail protocol support
# only one of TLS and SSL can be in the true state.
sslEnable="false"
#note: sslTrust is the same as mailServerHost
sslTrust="xxx"
# resource storage type：HDFS,S3,NONE
resourceStorageType="HDFS"
# if resourceStorageType is HDFS，defaultFS write namenode address，HA you need to put core-site.xml and hdfs-site.xml in the conf directory.
# if S3，write S3 address，HA，for example ：s3a://dolphinscheduler，
# Note，s3 be sure to create the root directory /dolphinscheduler
defaultFS="hdfs://master.eights.com:8020"
# if resourceStorageType is S3, the following three configuration is required, otherwise please ignore
s3Endpoint="http://192.168.xx.xx:9010"
s3AccessKey="xxxxxxxxxx"
s3SecretKey="xxxxxxxxxx"
# if not use hadoop resourcemanager, please keep default value; if resourcemanager HA enable, please type the HA ips ; if resourcemanager is single, make this value empty
yarnHaIps="192.168.xx.xx,192.168.xx.xx"
# if resourcemanager HA enable or not use resourcemanager, please skip this value setting; If resourcemanager is single, you only need to replace yarnIp1 to actual resourcemanager hostname.
singleYarnIp="master.eights.com"
# resource store on HDFS/S3 path, resource file will store to this hadoop hdfs path, self configuration, please make sure the directory exists on hdfs and have read write permissions。/dolphinscheduler is recommended
resourceUploadPath="/dscheduler"
# who have permissions to create directory under HDFS/S3 root path
# Note: if kerberos is enabled, please config hdfsRootUser=
hdfsRootUser="hdfs"
# kerberos config
# whether kerberos starts, if kerberos starts, following four items need to config, otherwise please ignore
kerberosStartUp="false"
# kdc krb5 config file path
krb5ConfPath="$installPath/conf/krb5.conf"
# keytab username
keytabUserName="hdfs-mycluster@ESZ.COM"
# username keytab path
keytabPath="$installPath/conf/hdfs.headless.keytab"
# api server port
apiServerPort="12345"
# install hosts
# Note: install the scheduled hostname list. If it is pseudo-distributed, just write a pseudo-distributed hostname
ips="master.eights.com"
# ssh port, default 22
# Note: if ssh port is not default, modify here
sshPort="22"
# run master machine
# Note: list of hosts hostname for deploying master
masters="master.eights.com"
# run worker machine
# note: need to write the worker group name of each worker, the default value is "default"
workers="master.eights.com:default"
# run alert machine
# note: list of machine hostnames for deploying alert server
alertServer="master.eights.com"
# run api machine
# note: list of machine hostnames for deploying api server
apiServers="master.eights.com"
# whether to start monitoring self-starting scripts
monitorServerState="false"

export DOLPHINSCHEDULER_OPTS="-server -Xmx16g -Xms1g -Xss512k 
-XX:+DisableExplicitGC -XX:+UseConcMarkSweepGC -XX:+CMSParallelRemarkEnabled 
-XX:LargePageSizeInBytes=128m -XX:+UseFastAccessorMethods 
-XX:+UseCMSInitiatingOccupancyOnly -XX:CMSInitiatingOccupancyFraction=70"

sh install.sh

su dscheduler;
jps;

# 一键停止
sh ./bin/stop-all.sh
# 一键开启
sh ./bin/start-all.sh
# 启停master
sh ./bin/dolphinscheduler-daemon.sh start master-server
sh ./bin/dolphinscheduler-daemon.sh stop master-server
# 启停worker
sh ./bin/dolphinscheduler-daemon.sh start worker-server
sh ./bin/dolphinscheduler-daemon.sh stop worker-server
# 启停api-server
sh ./bin/dolphinscheduler-daemon.sh start api-server
sh ./bin/dolphinscheduler-daemon.sh stop api-server
# 启停logger
sh ./bin/dolphinscheduler-daemon.sh start logger-server
sh ./bin/dolphinscheduler-daemon.sh stop logger-server
# 启停alert
sh ./bin/dolphinscheduler-daemon.sh start alert-server
sh ./bin/dolphinscheduler-daemon.sh stop alert-server