Add hadoop scripts (#260)

* add entrypoint to all containers

* adding hadoop scripts to docker dir

docker/build-hadoop.sh

@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+
+if [[ "$#" != 1 ]]; then
+  echo "ERROR: Must provide Hadoop version number!"
+  echo "       Example: ${BASH_SOURCE[0]} \"3.3.2\""
+  exit 1
+fi
+HADOOP_VER="$1"
+
+SCRIPT_DIR=$(dirname ${BASH_SOURCE[0]})
+cd ${SCRIPT_DIR}
+
+# Download desired revision.
+git clone --branch rel/release-${HADOOP_VER} --depth 1 https://github.com/apache/hadoop.git hadoop
+cd hadoop
+
+# Temporarily disable name resolution for jboss repository. NVIDIA IT ticket number: "INC0866408"
+if [[ ! "$(curl --connect-timeout 5 https://repository.jboss.org)" ]] 2>/dev/null; then
+    echo 'Unable to connect to repository.jboss.org. Disabling...'
+    echo '127.0.0.1 repository.jboss.org' >> /etc/hosts
+fi
+
+# Build Hadoop.
+mvn clean package \
+  -Pdist,native \
+  -DskipTests \
+  -Dtar -Dmaven.javadoc.skip=true \
+  -Drequire.snappy \
+  -Drequire.zstd \
+  -Drequire.openssl \
+  -Drequire.pmdk
+
+# Move compiled distribution to $SCRIPT_DIR and delete temporary files.
+mv hadoop-dist/target/hadoop-${HADOOP_VER}.tar.gz ..
+cd ..
+rm -rf hadoop /root/.m2
+
+# Self-delete.
+rm -rf ${BASH_SOURCE[0]}

docker/install-hadoop.sh

@@ -0,0 +1,71 @@
+#!/usr/bin/env bash
+
+if [[ "$#" != 1 ]]; then
+  echo "ERROR: Must provide Hadoop version number!"
+  echo "       Example: ${BASH_SOURCE[0]} \"3.3.2\""
+  exit 1
+fi
+HADOOP_VER="$1"
+
+SCRIPT_DIR=$(dirname ${BASH_SOURCE[0]})
+cd ${SCRIPT_DIR}
+
+# Extract files and delete archive.
+mkdir -p ${HADOOP_HOME}/logs
+tar xf hadoop-${HADOOP_VER}.tar.gz --strip-components 1 --directory ${HADOOP_HOME}
+rm -rf hadoop-${HADOOP_VER}.tar.gz
+
+# Cleanup reundant files.
+for f in $(find ${HADOOP_HOME} -name *.cmd); do
+  rm -rf $f
+done
+
+# Pretend that the package has been installed like any other.
+ln -s ${HADOOP_HOME}/include/hdfs.h /usr/local/include/hdfs.h
+ln -s ${HADOOP_HOME}/lib/native/libhdfs.so /usr/local/lib/libhdfs.so
+ln -s ${HADOOP_HOME}/lib/native/libhdfs.so.0.0.0 /usr/local/lib/libhdfs.so.0.0.0
+ln -s ${HADOOP_HOME}/lib/native/libhadoop.so /usr/local/lib/libhadoop.so
+ln -s ${HADOOP_HOME}/lib/native/libhadoop.so.1.0.0 /usr/local/lib/libhadoop.so.1.0.0
+
+# Create minimalist single-node "default" configuration.
+sed -i "s/^# export JAVA_HOME=$/export JAVA_HOME=${JAVA_HOME//\//\\\/}/g" ${HADOOP_HOME}/etc/hadoop/hadoop-env.sh
+
+echo '<?xml version="1.0" encoding="UTF-8"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+<!-- Single-node dummy configuration -->
+<configuration>
+  <property>
+    <name>fs.defaultFS</name>
+    <value>hdfs://localhost:9000</value>
+  </property>
+</configuration>' > ${HADOOP_HOME}/etc/hadoop/core-site.xml
+
+echo '<?xml version="1.0" encoding="UTF-8"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+
+<!-- Single-node dummy configuration -->
+<configuration>
+  <property>
+    <name>dfs.replication</name>
+    <value>1</value>
+  </property>
+</configuration>' > ${HADOOP_HOME}/etc/hadoop/hdfs-site.xml
+
+ssh-keygen -q -t ecdsa -b 521 -N "" <<< ""
+cat $HOME/.ssh/id_ecdsa.pub >> $HOME/.ssh/authorized_keys
+
+ldconfig
+echo "
+Hadoop version: $(hadoop version)
+
+To run a single-node hadoop instance (for development only):
+
+    hadoop namenode -format
+    service ssh start
+    start-dfs.sh
+
+"
+
+# Self-delete.
+rm -rf ${BASH_SOURCE[0]}