#!/bin/bash source ../dmp_env.sh LOG_TIME=$(date +%Y%m%d -d "-1 day $ScheduleTime") year=${LOG_TIME:0:4} month=${LOG_TIME:4:2} day=${LOG_TIME:6:2} YESTERDAY=$(date -d "$ScheduleTime 2 days ago" "+%Y%m%d") old_year=${YESTERDAY:0:4} old_month=${YESTERDAY:4:2} old_day=${YESTERDAY:6:2} business="3s" DAILY_INPUT="${INSTALL_DAILY_3S}/${year}/${month}/${day}/" check_await "${DAILY_INPUT}/_SUCCESS" sleep 60 INPUT_PATH="${DMP_INSTALL_LIST}/${old_year}/${old_month}/${old_day}/$business" check_await "${INPUT_PATH}/_SUCCESS" OUTPUT="${DMP_INSTALL_LIST}/${year}/${month}/${day}/${business}" mount_partition "dmp_install_list" "dt='$LOG_TIME', business='$business'" "$OUTPUT" expire_date=$(date +%Y%m%d -d "-7 day $LOG_TIME") expire_date_path=$(date +"%Y/%m/%d" -d "-7 day ${LOG_TIME}") EXPIRE_OUTPUT_PATH="${DMP_INSTALL_LIST}/${expire_date_path}/${business}" # --conf spark.shuffle.memoryFraction=0.4 \ # --conf spark.storage.memoryFraction=0.4 \ # --conf spark.driver.extraJavaOptions="-XX:+UseG1GC" \ spark-submit --class mobvista.dmp.common.InstallListLogic \ --name "DmpInstallList.${business}.${LOG_TIME}" \ --conf spark.sql.shuffle.partitions=20 \ --conf spark.default.parallelism=20 \ --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 5 \ ../${JAR} -date ${LOG_TIME} -business ${business} -output ${OUTPUT} -coalesce 10 if [[ $? -ne 0 ]];then exit 255 fi # 删除过期的分区及删除对应路径 unmount_partition "dmp_install_list" "dt='${expire_date}', business='${business}'" "${EXPIRE_OUTPUT_PATH}"