merge_install_gender.sh 2.29 KB
Newer Older
wang-jinfeng committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43
#! /bin/bash

# # # # # # # # # # # # # # # # # # # # # #
# @file    :extract_device.sh
# @author  :liushuai
# @revision:2017-01-18 16:12
# # # # # # # # # # # # # # # # # # # # # #

source ../dmp_env.sh

LOG_TIME=$(date +%Y%m%d -d "-1 day $ScheduleTime")
dt=$(date +'%Y-%m-%d' -d "-1 day $ScheduleTime")
date_path=$(date +'%Y/%m/%d' -d "-1 day $ScheduleTime")

# INSTALL_3S_INPUT="${DMP_INSTALL_LIST}/${date_path}/3s"
# ADN_INSTALL_INPUT="${DMP_INSTALL_LIST}/${date_path}/adn_install"
# ADN_REQUEST_INPUT="${DMP_INSTALL_LIST}/${date_path}/adn_request_sdk"
# DSP_REQUEST_INPUT="${DMP_INSTALL_LIST}/${date_path}/dsp_req"
# GA_INSTALL_DATE=$(get_recently_date "${DMP_INSTALL_LIST}" "${LOG_TIME}" "ga")
# OTHER_DATE=$(get_recently_date "${DMP_INSTALL_LIST}" "${LOG_TIME}" "other")

INSTALL_LIST_INPUT="${DMP_INSTALL_LIST}/${date_path}/14days"

GENDER_OUTPUT="${GENDER_MERGE_INSTALL}/${date_path}"

DSP_GENDER_PATH="${GENDER_GET_DSP_PATH}/${date_path}/"
GA_GENDER_PATH="${GENDER_GET_GA_PATH}/${date_path}/"
FB_GENDER_PATH="${GENDER_GET_FACEBOOK_PATH}/${date_path}/"
TP_GENDER_PATH="${GENDER_GET_THIRDPART_PATH}/${date_path}/"

# check_await ${INSTALL_3S_INPUT}/_SUCCESS
# check_await ${ADN_INSTALL_INPUT}/_SUCCESS
# check_await ${ADN_REQUEST_INPUT}/_SUCCESS
# check_await ${DSP_REQUEST_INPUT}/_SUCCESS

check_await ${INSTALL_LIST_INPUT}/_SUCCESS

check_await ${GA_GENDER_PATH}/_SUCCESS
check_await ${DSP_GENDER_PATH}/_SUCCESS
check_await ${FB_GENDER_PATH}/_SUCCESS
check_await ${TP_GENDER_PATH}/_SUCCESS

spark-submit --class mobvista.dmp.datasource.age_gender.MergeInstallGender \
wang-jinfeng committed
44 45 46 47 48 49 50 51 52 53 54 55 56 57 58
  --name "MergeInstallGender.${LOG_TIME}" \
  --conf spark.sql.shuffle.partitions=5000 \
  --conf spark.default.parallelism=2000 \
  --conf spark.storage.memoryFraction=0.4 \
  --conf spark.shuffle.memoryFraction=0.4 \
  --conf spark.sql.files.maxPartitionBytes=536870912 \
  --conf spark.sql.adaptive.enabled=true \
  --conf spark.sql.adaptive.advisoryPartitionSizeInBytes=536870912 \
  --master yarn --deploy-mode cluster --executor-memory 10g --driver-memory 6g --executor-cores 5 --num-executors 60 \
  ../${JAR} -date ${LOG_TIME} \
  -ga_gender_path ${GA_GENDER_PATH} -dsp_gender_path ${DSP_GENDER_PATH} -fb_gender_path ${FB_GENDER_PATH} -tp_gender_path ${TP_GENDER_PATH} -gender_output ${GENDER_OUTPUT} -parallelism 2000

if [ $? -ne 0 ]; then
  exit 255
fi