Install Hadoop

[tylerpotts]

Hadoop will be installed on the cluster when the following flag is set in group_vars/all.yaml

bodo:
  enabled: true

This is a script provided by bodo to install hadoop

      "conda install --quiet --yes adlfs -c conda-forge",
      "apt-get install -y openjdk-11-jre-headless",
      "cd /opt",
      "wget https://mirrors.sonic.net/apache/hadoop/common/hadoop-3.3.0/hadoop-3.3.0.tar.gz",
      "tar xf hadoop-3.3.0.tar.gz",
      "rm hadoop-3.3.0.tar.gz",
      "echo \"export JAVA_HOME=/usr/lib/jvm/java-11-openjdk-amd64\" >> /etc/bash.bashrc",
      "echo \"export HADOOP_HOME=/opt/hadoop-3.3.0\" >> /etc/bash.bashrc",
      "echo \"export HADOOP_INSTALL=\\$HADOOP_HOME\" >> /etc/bash.bashrc",
      "echo \"export HADOOP_MAPRED_HOME=\\$HADOOP_HOME\" >> /etc/bash.bashrc",
      "echo \"export HADOOP_COMMON_HOME=\\$HADOOP_HOME\" >> /etc/bash.bashrc",
      "echo \"export HADOOP_HDFS_HOME=\\$HADOOP_HOME\" >> /etc/bash.bashrc",
      "echo \"export YARN_HOME=\\$HADOOP_HOME\" >> /etc/bash.bashrc",
      "echo \"export HADOOP_COMMON_LIB_NATIVE_DIR=\\$HADOOP_HOME/lib/native\" >> /etc/bash.bashrc",
      "echo \"export PATH=\\$PATH:\\$HADOOP_HOME/sbin:\\$HADOOP_HOME/bin\" >> /etc/bash.bashrc",
      "echo \"export HADOOP_OPTS='-Djava.library.path=/opt/hadoop-3.3.0/lib/native'\" >> /etc/bash.bashrc",
      "echo \"export HADOOP_OPTIONAL_TOOLS=hadoop-azure\" >> /etc/bash.bashrc",
      "echo \"export ARROW_LIBHDFS_DIR=\\$HADOOP_COMMON_LIB_NATIVE_DIR\" >> /etc/bash.bashrc",
      "echo \"export CLASSPATH=\\`\\$HADOOP_HOME/bin/hdfs classpath --glob\\`\" >> /etc/bash.bashrc"