#!/bin/bash source ../dmp_env.sh today=${ScheduleTime:-$1} date=$(date +"%Y%m%d" -d "-1 day $today") date_path=$(date +"%Y/%m/%d/" -d "-1 day $today") INPUT="s3://mob-emr-test/dataplatform/DataWareHouse/data/dev/device_region_daily/${date_path}" OUTPUT="s3://mob-emr-test/dataplatform/DataWareHouse/data/dwh/dmp_device_region/${date_path}" spark-submit --class mobvista.dmp.datasource.rtdmp.DeviceRegionMerge \ --name "DeviceRegionMerge.wangjf.${date}" \ --conf spark.sql.shuffle.partitions=1000 \ --conf spark.default.parallelism=1000 \ --conf spark.kryoserializer.buffer.max=256m \ --conf spark.executor.extraJavaOptions="-XX:+UseG1GC" \ --master yarn --deploy-mode cluster --executor-memory 4g --driver-memory 4g --executor-cores 2 --num-executors 50 \ ../${JAR} -date ${date} -output ${OUTPUT} -input ${INPUT} -coalesce 200 if [[ $? -ne 0 ]]; then exit 255 fi mount_partition "dmp_device_region" "dt='${date}'" "$OUTPUT"