#!/usr/bin/env bash source ../../dmp_env.sh LOG_TIME=$(date -d "$ScheduleTime" +"%Y%m%d") date_path=$(date -d "$ScheduleTime" +"%Y/%m/%d") dt_three_days_ago=$(date -d "$ScheduleTime 3 days ago" +"%Y-%m-%d") IMEIMD5_OUTPUT_PATH="${YOUKU_LAXIN_DAILY_TMP_PATH}/$date_path/imeimd5" OAIDMD5_OUTPUT_PATH="${YOUKU_LAXIN_DAILY_TMP_PATH}/$date_path/oaidmd5" hadoop fs -rm -r "${IMEIMD5_OUTPUT_PATH}" hadoop fs -rm -r "${OAIDMD5_OUTPUT_PATH}" spark-submit --class mobvista.dmp.datasource.taobao.YOUKULaxinDF \ --name "YOUKULaxinDF.${LOG_TIME}" \ --conf spark.sql.shuffle.partitions=1000 \ --conf spark.default.parallelism=1000 \ --conf spark.kryoserializer.buffer.max=256m \ --conf spark.driver.extraJavaOptions="-XX:+UseG1GC" \ --conf spark.executor.extraJavaOptions="-XX:+UseG1GC" \ --files ${HIVE_SITE_PATH} \ --jars s3://mob-emr-test/wangjf/jar/spark-clickhouse-connector_2.11-2.4.0_0.22.jar \ --master yarn --deploy-mode cluster --executor-memory 4g --driver-memory 4g --executor-cores 3 --num-executors 10 \ ../../${JAR} -date ${LOG_TIME} -dt_three_days_ago ${dt_three_days_ago} -partNum 10 -imeiOutput ${IMEIMD5_OUTPUT_PATH} -oaidOutput ${OAIDMD5_OUTPUT_PATH} -cluster 'cluster_1st' if [[ $? -ne 0 ]];then exit 255 fi
