Ubuntu16安装docker，并安装hue4.8、flink-sql

安装docker

curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -
sudo add-apt-repository    "deb [arch=amd64] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
sudo apt-get update
sudo apt-get install docker-ce
apt install docker-compose

安装测试代码stream-sql-demo（可不安装）

mkdir stream-sql-demo
cd stream-sql-demo
wget https://raw.githubusercontent.com/romainr/query-demo/master/stream-sql-demo/docker-compose.yml


docker-compose up -d

安装hue

docker run -it -p 8888:8888 gethue/hue:latest

#或者导入镜像
docker load -i hue_docker.tar

修改配置文件hue.ini

1、配置数据库连接

[desktop]
[[database]]
engine=mysql
host=127.0.0.1
port=3306
user=root
password=secret
name=hue

2、配置读取mysql

[notebook]
[[interpreters]]
[[[mysql]]]
name = MySQL
interface=sqlalchemy
options='{"url": "mysql://root:secret@database-host:3306/hue"}'

2、配置hdfs

[hadoop]

  # Configuration for HDFS NameNode
  # ------------------------------------------------------------------------
  [[hdfs_clusters]]
    # HA support by using HttpFs

    [[[default]]]
      # Enter the filesystem uri
      fs_defaultfs=hdfs://192.168.36.137:8020

       webhdfs_url=http://192.168.36.138:14000/webhdfs/v1

       hadoop_conf_dir=/etc/hadoop/conf

3、配置yarn

  [[yarn_clusters]]

    [[[default]]]
      # Enter the host on which you are running the ResourceManager
       resourcemanager_host=192.168.36.138

      # The port where the ResourceManager IPC listens on
       resourcemanager_port=8032

      # Whether to submit jobs to this cluster
      submit_to=True

      # Resource Manager logical name (required for HA)
      ## logical_name=

      # Change this if your YARN cluster is Kerberos-secured
      ## security_enabled=false

      # URL of the ResourceManager API
       resourcemanager_api_url=http://192.168.36.138:8088

      # URL of the ProxyServer API
       proxy_api_url=http://192.168.36.138:8088

      # URL of the HistoryServer API
       history_server_api_url=http://192.168.36.138:19888

4、配置hive

[desktop]
    thrift_version=7

[beeswax]

  # Host where HiveServer2 is running.
  # If Kerberos security is enabled, use fully-qualified domain name (FQDN).
   hive_server_host=192.168.36.139

  # Binary thrift port for HiveServer2.
   hive_server_port=10000
   hive_conf_dir=/etc/hive/conf


[notebook]
[[interpreters]]
[[[hive]]]
       name=Hive
       interface=hiveserver2

5、配置flink

注意：配置之前，请先安装flink-sql-gataway，并保证与flink-sql-gataway同在一台机子上有flink集群

https://blog.csdn.net/wqy1200/article/details/109746704

[notebook]
enable_notebook_2=true

[[interpreters]]

[[[flink]]]
name=Flink
interface=flink
options='{"url": "http://172.18.0.7:8083"}'

6、配置spark

6.1、安装livy

下载https://livy.incubator.apache.org/

unzip apache-livy-0.7.0-incubating-bin.zip

修改配置

#修改配置文件 conf/livy-env.sh

export HADOOP_CONF_DIR=/etc/hadoop/conf
export SPARK_HOME=/opt/cloudera/parcels/CDH/lib/spark
export JAVA_HOME=/usr/local/java

#修改配置文件conf/livy.conf 



livy.server.port = 8998
livy.spark.master = yarn
livy.server.session.timeout = 1h
livy.impersonation.enabled = true
livy.repl.enable-hive-context = true

启动程序，注意：使用hdfs账号启动

 sudo -u hdfs ./livy-server 1>&2 &

6.2、修改hue.ini

[notebook]
[[interpreters]]
     [[[sql]]]
       name=SparkSql
       interface=livy

     [[[spark]]]
       name=Scala
       interface=livy

     [[[pyspark]]]
       name=PySpark
       interface=livy



[spark]
  # The Livy Server URL.
  livy_server_url=http://192.168.36.138:8998

7、配置oozie