#!/bin/bash source ../../dmp_env.sh tb_type=$1 today=${ScheduleTime} date=$(date +"%Y%m%d" -d "-1 day $today") date_path=$(date +"%Y/%m/%d/" -d "-1 day $today") INPUT="s3://mob-ad/adn/tracking-v3" hours="23" res="beijing virginia" for hh in ${hours}; do for re in ${res}; do check_await "${INPUT}/${tb_type}/${date_path}/${re}/${hh}/_SUCCESS" done done OUTPUT="s3://mob-emr-test/dataplatform/DataWareHouse/data/dwh/etl_adn_tracking_${tb_type}/${date_path}" spark-submit --class mobvista.dmp.datasource.rtdmp.lazada.ETLJob \ --name "ETLJob.${tb_type}.${date}" \ --conf spark.sql.shuffle.partitions=100 \ --conf spark.default.parallelism=100 \ --conf spark.kryoserializer.buffer.max=256m \ --conf spark.executor.extraJavaOptions="-XX:+UseG1GC" \ --master yarn --deploy-mode cluster --executor-memory 6g --driver-memory 4g --executor-cores 4 --num-executors 5 \ ../../${JAR} -dt ${date} -output ${OUTPUT} -tb_type ${tb_type} if [[ $? -ne 0 ]]; then exit 255 fi mount_partition "etl_adn_tracking_${tb_type}" "dt='${date}'" "$OUTPUT"