#!/usr/bin/env bash

export HADOOP_CONF_DIR=$HOME/hadoop/conf
export HADOOP_HOME=$HOME/hadoop
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$HADOOP_HOME/lib/native
export SPARK_JAVA_OPTS="-Dhdp.version=2.6.3.0-235"
export PYTHONIOENCODING=utf8

$HOME/spark/bin/spark-submit\
 --master yarn\
 --deploy-mode cluster\
 --queue default\
 --num-executors 10\
 --conf "spark.driver.memory=1g"\
 --conf "spark.driver.memoryOverhead=600m"\
 --conf "spark.executor.memory=600m"\
 --conf "spark.executor.memoryOverhead=300m"\
 --name "$1"\
 --conf "spark.sql.autoBroadcastJoinThreshold=-1"\
 --conf "spark.driver.extraJavaOptions=-Dhdp.version=2.6.3.0-235"\
 --conf "spark.yarn.am.extraJavaOptions=-Dhdp.version=2.6.3.0-235"\
 --conf "spark.sql.shuffle.partitions=100" $1