Dolphinscheduler 下載：
wget --no-check-certificate https://dlcdn.apache.org/dolphinscheduler/2.0.0-alpha/apache-dolphinscheduler-2.0.0-alpha-bin.tar.gz
Dolphinscheduler 集群部署
前置准備工作 && 准備 DolphinScheduler 啟動環境
1. JDK（1.8+） 2. mysql5.7 3. zk 4. yum install psmisc #進程樹分析
配置用戶和權限
# 創建用戶需使用 root 登錄 useradd dolphinscheduler # 添加密碼 echo "dolphinscheduler" | passwd --stdin dolphinscheduler # 配置 sudo 免密 sed -i '$adolphinscheduler ALL=(ALL) NOPASSWD: NOPASSWD: ALL' /etc/sudoers sed -i 's/Defaults requirett/#Defaults requirett/g' /etc/sudoers # 修改目錄權限，使得部署用戶對 dolphinscheduler-bin 目錄有操作權限 chown -R dolphinscheduler:dolphinscheduler dolphinscheduler-bin
密鑰
su dolphinscheduler ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys chmod 600 ~/.ssh/authorized_keys
初始化數據庫
mysql -uroot -p mysql> CREATE DATABASE dolphinscheduler DEFAULT CHARACTER SET utf8 DEFAULT COLLATE utf8_general_ci; mysql> CREATE USER 'dolphinscheduler'@'%' IDENTIFIED BY 'dolphinscheduler'; mysql> GRANT ALL PRIVILEGES ON dolphinscheduler.* TO 'dolphinscheduler'@'%' ;
mysql> source /usr/local/src/apache-dolphinscheduler/sql/dolphinscheduler_mysql.sql; mysql> flush privileges;
拷貝 mysql 驅動程序
mysql-connector-java 到 DolphinScheduler lib目錄下
[dolphinscheduler@hdp0 ~]$ scp mysql-connector-java.jar dolphinscheduler@hdp1:/data/apache-dolphinscheduler/lib/
修改配置
進入到 /data/tools/apache-dolphinscheduler/conf/config 修改install_config.conf # # Licensed to the Apache Software Foundation (ASF) under one or more # contributor license agreements. See the NOTICE file distributed with # this work for additional information regarding copyright ownership. # The ASF licenses this file to You under the Apache License, Version 2.0 # (the "License"); you may not use this file except in compliance with # the License. You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # --------------------------------------------------------- # INSTALL MACHINE # --------------------------------------------------------- # A comma separated list of machine hostname or IP would be installed DolphinScheduler, # including master, worker, api, alert. If you want to deploy in pseudo-distributed # mode, just write a pseudo-distributed hostname # Example for hostnames: ips="ds1,ds2,ds3,ds4,ds5", Example for IP: ips="192.168.8.1,192.168.8.2,192.168.8.3,192.168.8.4,192.168.8.5" ips="hdp0,hdp1,hdp2,hdp3" # Port of SSH protocol, default value is 22. For now we only support same port in all `ips` machine # modify it if you use different ssh port sshPort="22" # A comma separated list of machine hostname or IP would be installed Master server, it # must be a subset of configuration `ips`. # Example for hostnames: ips="ds1,ds2", Example for IP: ips="192.168.8.1,192.168.8.2" masters="hdp0,hdp1" # A comma separated list of machine <hostname>:<workerGroup> or <IP>:<workerGroup>.All hostname or IP must be a # subset of configuration `ips`, And workerGroup have default value as `default`, but we recommend you declare behind the hosts # Example for hostnames: ips="ds1:default,ds2:default,ds3:default", Example for IP: ips="192.168.8.1:default,192.168.8.2:default,192.168.8.3:default" workers="hdp2:default,hdp3:default" # A comma separated list of machine hostname or IP would be installed Alert server, it # must be a subset of configuration `ips`. # Example for hostnames: ips="ds3", Example for IP: ips="192.168.8.3" alertServer="hdp0" # A comma separated list of machine hostname or IP would be installed API server, it # must be a subset of configuration `ips`. # Example for hostnames: ips="ds1", Example for IP: ips="192.168.8.1" apiServers="hdp1,hdp0" # The directory to install DolphinScheduler for all machine we config above. It will automatically created by `install.sh` script if not exists. # **DO NOT** set this configuration same as the current path (pwd) #installPath="/data1_1T/dolphinscheduler" installPath="/data/dolphinscheduler" # The user to deploy DolphinScheduler for all machine we config above. For now user must create by yourself before run `install.sh` # script. The user needs to have sudo privileges and permissions to operate hdfs. If hdfs is enabled than the root directory needs # to be created by this user deployUser="dolphinscheduler" # The directory to store local data for all machine we config above. Make sure user `deployUser` have permissions to read and write this directory. #dataBasedirPath="/tmp/dolphinscheduler" dataBasedirPath="/data/dolphinscheduler/dolphinschedulerdata" # --------------------------------------------------------- # DolphinScheduler ENV # --------------------------------------------------------- # JAVA_HOME, we recommend use same JAVA_HOME in all machine you going to install DolphinScheduler # and this configuration only support one parameter so far. javaHome="/data/jdk" # DolphinScheduler API service port, also this your DolphinScheduler UI component's URL port, default values is 12345 apiServerPort="12345" # --------------------------------------------------------- # Database # NOTICE: If database value has special characters, such as `.*[]^${}\+?|()@#&`, Please add prefix `\` for escaping. # --------------------------------------------------------- # The type for the metadata database # Supported values: ``postgresql``, ``mysql``. dbtype="mysql" # The <HOST>:<PORT> connection pair DolphinScheduler connect to the metadata database dbhost="172.31.115.17:3306" # The username DolphinScheduler connect to the metadata database username="dolphinscheduler" # The password DolphinScheduler connect to the metadata database password="dolphinscheduler" # The database DolphinScheduler connect to the metadata database dbname="dolphinscheduler" # --------------------------------------------------------- # Registry Server # --------------------------------------------------------- # Registry Server plugin dir. DolphinScheduler will find and load the registry plugin jar package from this dir. # For now default registry server is zookeeper, so the default value is `lib/plugin/registry/zookeeper`. # If you want to implement your own registry server, please see https://dolphinscheduler.apache.org/en-us/docs/dev/user_doc/registry_spi.html registryPluginDir="lib/plugin/registry/zookeeper" # Registry Server plugin name, should be a substring of `registryPluginDir`, DolphinScheduler use this for verifying configuration consistency registryPluginName="zookeeper" # Registry Server address. registryServers="172.31.115.17:2181,172.31.115.18:2181,172.31.115.19:2181" # The root of zookeeper, for now DolphinScheduler default registry server is zookeeper. zkRoot="/dolphinscheduler" # --------------------------------------------------------- # Alert Server # --------------------------------------------------------- # Alert Server plugin dir. DolphinScheduler will find and load the alert plugin jar package from this dir. alertPluginDir="lib/plugin/alert" # --------------------------------------------------------- # Worker Task Server # --------------------------------------------------------- # Worker Task Server plugin dir. DolphinScheduler will find and load the worker task plugin jar package from this dir. taskPluginDir="lib/plugin/task" # resource storage type: HDFS, S3, NONE resourceStorageType="HDFS" # 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="/dolphinscheduler" # 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://hdp0.fengjian.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" # resourcemanager port, the default value is 8088 if not specified resourceManagerHttpAddressPort="8088" # if resourcemanager HA is enabled, please set the HA IPs; if resourcemanager is single, keep this value empty yarnHaIps="hdp0.fengjian.com,hdp1.fengjian.com" # if resourcemanager HA is enabled or not use resourcemanager, please keep the default value; If resourcemanager is single, you only need to replace ds1 to actual resourcemanager hostname singleYarnIp="" # 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,watch out the @ sign should followd by \\ keytabUserName="hdfs-mycluster\\@ESZ.COM" # username keytab path keytabPath="$installPath/conf/hdfs.headless.keytab" # kerberos expire time, the unit is hour kerberosExpireTime="2" # use sudo or not sudoEnable="true" # worker tenant auto create workerTenantAutoCreate="false"
如果是hdfs集群
# if resourceStorageType is HDFS，defaultFS write namenode address，HA you need to put core-site.xml and hdfs-site.xml in the conf directory. # if S3，write S3 address，HA，for example ：s3a://dolphinscheduler， # Note，s3 be sure to create the root directory /dolphinscheduler defaultFS="hdfs://Abcd:8020"
並且拷貝
cp /data/hadoop/etc/core-site.xml /usr/local/src/dolphscheduler/config/ cp /data/hadoop/etc/hdfs -site.xml /usr/local/src/dolphscheduler/config/
修改環境變量
進入到 /data/tools/apache-dolphinscheduler/conf/env 修改dolphinscheduler_env.sh export HADOOP_HOME=/usr/hdp/3.0.0.0-1634/hadoop export HADOOP_CONF_DIR=/usr/hdp/3.0.0.0-1634/hadoop/etc/hadoop export SPARK_HOME1=/usr/hdp/3.0.0.0-1634/spark2 export SPARK_HOME2=/usr/hdp/3.0.0.0-1634/spark2 #export PYTHON_HOME=/opt/soft/python export JAVA_HOME=/data/jdk export HIVE_HOME=/usr/hdp/3.0.0.0-1634/hive #export FLINK_HOME=/opt/soft/flink #export DATAX_HOME=/opt/soft/datax export PATH=$HADOOP_HOME/bin:$SPARK_HOME1/bin:$SPARK_HOME2/bin:$JAVA_HOME/bin:$HIVE_HOME/bin:$PATH #export PATH=$HADOOP_HOME/bin:$SPARK_HOME1/bin:$SPARK_HOME2/bin:$PYTHON_HOME/bin:$JAVA_HOME/bin:$HIVE_HOME/bin:$FLINK_HOME/bin:$DATAX_HOME/bin:$PATH
修改jvm 堆棧參數
/data/tools/apache-dolphinscheduler/bin/dolphinscheduler-daemon.sh
根據內存修改
啟動 Dolphinscheduler
#會復制到其他服務器，並且啟動
sh install.sh
登陸Dolphinscheduler
瀏覽器訪問地址 http://hdp0.fengjjian.com:12345/dolphinscheduler 即可登錄系統UI。默認的用戶名和密碼是 admin/dolphinscheduler123
一些其他的啟停服務命令
# 一鍵停止集群所有服務 sh ./bin/stop-all.sh # 一鍵開啟集群所有服務 sh ./bin/start-all.sh # 啟停 Master sh ./bin/dolphinscheduler-daemon.sh stop master-server sh ./bin/dolphinscheduler-daemon.sh start master-server # 啟停 Worker sh ./bin/dolphinscheduler-daemon.sh start worker-server sh ./bin/dolphinscheduler-daemon.sh stop worker-server # 啟停 Api sh ./bin/dolphinscheduler-daemon.sh start api-server sh ./bin/dolphinscheduler-daemon.sh stop api-server # 啟停 Logger sh ./bin/dolphinscheduler-daemon.sh start logger-server sh ./bin/dolphinscheduler-daemon.sh stop logger-server # 啟停 Alert sh ./bin/dolphinscheduler-daemon.sh start alert-server sh ./bin/dolphinscheduler-daemon.sh stop alert-server