目录
Yarn配置
增加ApplicationMaster资源比例
(1)在hadoop102的/opt/module/hadoop-3.1.3/etc/hadoop/capacity-scheduler.xml文件中修改如下参数值
[doudou@hadoop102 hadoop]$ vim capacity-scheduler.xml
<property>
<name>yarn.scheduler.capacity.maximum-am-resource-percent</name>
<value>0.8</value>
分发
[doudou@hadoop102 hadoop]$ xsync capacity-scheduler.xml
已成功
数仓开发环境
1.启动HiveServer2
[doudou@hadoop102 hadoop]$ hiveserver2
下载datagrip
2.配置DataGrip连接
1)创建连接
数据准备
1.用户行为日志
[doudou@hadoop102 db_log]$ vim application.properties
2.业务数据
1)修改hadoop102节点上的/opt/module/db_log/application.properties文件,将mock.date、mock.clear,mock.clear.user三个参数
[doudou@hadoop102 db_log]$ vim application.properties
mock.date=2020-06-10
#是否重置 注意:第一次执行必须设置为1,后续不需要重置不用设置为1
mock.clear=1
#是否重置用户 注意:第一次执行必须设置为1,后续不需要重置不用设置为1
mock.clear.user=1
2)执行模拟生成业务数据的命令,生成第一天2020-06-10的历史数据。
[doudou@hadoop102 db_log]$ java -jar gmall2020-mock-db-2021-01-22.jar
3)修改/opt/module/db_log/application.properties文件,将mock.date、mock.clear,mock.clear.user三个参数
[doudou@hadoop102 db_log]$ vim application.properties
#业务日期
mock.date=2020-06-11
#是否重置 注意:第一次执行必须设置为1,后续不需要重置不用设置为1
mock.clear=0
#是否重置用户 注意:第一次执行必须设置为1,后续不需要重置不用设置为1
mock.clear.user=0
4)执行模拟生成业务数据的命令,生成第二天2020-06-11的历史数据。
[doudou@hadoop102 db_log]$ java -jar gmall2020-mock-db-2021-01-22.jar
5)之后只修改/opt/module/db_log/application.properties文件中的mock.date参数,依次改为2020-06-12,2020-06-13,2020-06-14,并分别生成对应日期的数据
6)执行mysql_to_hdfs_init.sh脚本,将模拟生成的业务数据同步到HDFS。
[doudou@hadoop102 bin]$ ./mysql_to_hdfs_init.sh all 2022-09-03
数仓搭建-ODS层
创建日志表ods_log
--ODS层
--ods日志表
drop table if exists ods_log;
CREATE EXTERNAL TABLE ods_log (`line` string)
PARTITIONED BY (`dt` string) -- 按照时间创建分区
STORED AS -- 指定存储方式,读数据采用LzoTextInputFormat;
INPUTFORMAT 'com.hadoop.mapred.DeprecatedLzoTextInputFormat'
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
LOCATION '/warehouse/gmall/ods/ods_log' -- 指定数据在hdfs上的存储位置
;
--数据装载
load data inpath '/origin_data/gmall/log/topic_log/2020-06-14'into table ods_log partition(dt='2020-06-14');
ODS层日志表加载数据脚本
[doudou@hadoop102 bin]$ vim hdfs_to_ods_log.sh
#!/bin/bash
# 定义变量方便修改
APP=gmall
# 如果是输入的日期按照取输入日期;如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
do_date=$1
else
do_date=`date -d "-1 day" +%F`
fi
echo ================== 日志日期为 $do_date ==================
sql="
load data inpath '/origin_data/$APP/log/topic_log/$do_date' into table ${APP}.ods_log partition(dt='$do_date');
"
hive -e "$sql"
hadoop jar /opt/module/hadoop-3.1.3/share/hadoop/common/hadoop-lzo-0.4.20.jar com.hadoop.compression.lzo.DistributedLzoIndexer /warehouse/$APP/ods/ods_log/dt=$do_date
[doudou@hadoop102 bin]$ ./hdfs_to_ods_log.sh 2020-06-14
ODS层(业务数据)
创建业务数据表
ODS层业务表首日数据装载脚本
[doudou@hadoop102 bin]$ vim hdfs_to_ods_db_init.sh
#!/bin/bash
APP=gmall
if [ -n "$2" ] ;then
do_date=$2
else
echo "请传入日期参数"
exit
fi
ods_order_info="
load data inpath '/origin_data/$APP/db/order_info/$do_date' OVERWRITE into table ${APP}.ods_order_info partition(dt='$do_date');"
ods_order_detail="
load data inpath '/origin_data/$APP/db/order_detail/$do_date' OVERWRITE into table ${APP}.ods_order_detail partition(dt='$do_date');"
ods_sku_info="
load data inpath '/origin_data/$APP/db/sku_info/$do_date' OVERWRITE into table ${APP}.ods_sku_info partition(dt='$do_date');"
ods_user_info="
load data inpath '/origin_data/$APP/db/user_info/$do_date' OVERWRITE into table ${APP}.ods_user_info partition(dt='$do_date');"
ods_payment_info="
load data inpath '/origin_data/$APP/db/payment_info/$do_date' OVERWRITE into table ${APP}.ods_payment_info partition(dt='$do_date');"
ods_base_category1="
load data inpath '/origin_data/$APP/db/base_category1/$do_date' OVERWRITE into table ${APP}.ods_base_category1 partition(dt='$do_date');"
ods_base_category2="
load data inpath '/origin_data/$APP/db/base_category2/$do_date' OVERWRITE into table ${APP}.ods_base_category2 partition(dt='$do_date');"
ods_base_category3="
load data inpath '/origin_data/$APP/db/base_category3/$do_date' OVERWRITE into table ${APP}.ods_base_category3 partition(dt='$do_date'); "
ods_base_trademark="
load data inpath '/origin_data/$APP/db/base_trademark/$do_date' OVERWRITE into table ${APP}.ods_base_trademark partition(dt='$do_date'); "
ods_activity_info="
load data inpath '/origin_data/$APP/db/activity_info/$do_date' OVERWRITE into table ${APP}.ods_activity_info partition(dt='$do_date'); "
ods_cart_info="
load data inpath '/origin_data/$APP/db/cart_info/$do_date' OVERWRITE into table ${APP}.ods_cart_info partition(dt='$do_date'); "
ods_comment_info="
load data inpath '/origin_data/$APP/db/comment_info/$do_date' OVERWRITE into table ${APP}.ods_comment_info partition(dt='$do_date'); "
ods_coupon_info="
load data inpath '/origin_data/$APP/db/coupon_info/$do_date' OVERWRITE into table ${APP}.ods_coupon_info partition(dt='$do_date'); "
ods_coupon_use="
load data inpath '/origin_data/$APP/db/coupon_use/$do_date' OVERWRITE into table ${APP}.ods_coupon_use partition(dt='$do_date'); "
ods_favor_info="
load data inpath '/origin_data/$APP/db/favor_info/$do_date' OVERWRITE into table ${APP}.ods_favor_info partition(dt='$do_date'); "
ods_order_refund_info="
load data inpath '/origin_data/$APP/db/order_refund_info/$do_date' OVERWRITE into table ${APP}.ods_order_refund_info partition(dt='$do_date'); "
ods_order_status_log="
load data inpath '/origin_data/$APP/db/order_status_log/$do_date' OVERWRITE into table ${APP}.ods_order_status_log partition(dt='$do_date'); "
ods_spu_info="
load data inpath '/origin_data/$APP/db/spu_info/$do_date' OVERWRITE into table ${APP}.ods_spu_info partition(dt='$do_date'); "
ods_activity_rule="
load data inpath '/origin_data/$APP/db/activity_rule/$do_date' OVERWRITE into table ${APP}.ods_activity_rule partition(dt='$do_date');"
ods_base_dic="
load data inpath '/origin_data/$APP/db/base_dic/$do_date' OVERWRITE into table ${APP}.ods_base_dic partition(dt='$do_date'); "
ods_order_detail_activity="
load data inpath '/origin_data/$APP/db/order_detail_activity/$do_date' OVERWRITE into table ${APP}.ods_order_detail_activity partition(dt='$do_date'); "
ods_order_detail_coupon="
load data inpath '/origin_data/$APP/db/order_detail_coupon/$do_date' OVERWRITE into table ${APP}.ods_order_detail_coupon partition(dt='$do_date'); "
ods_refund_payment="
load data inpath '/origin_data/$APP/db/refund_payment/$do_date' OVERWRITE into table ${APP}.ods_refund_payment partition(dt='$do_date'); "
ods_sku_attr_value="
load data inpath '/origin_data/$APP/db/sku_attr_value/$do_date' OVERWRITE into table ${APP}.ods_sku_attr_value partition(dt='$do_date'); "
ods_sku_sale_attr_value="
load data inpath '/origin_data/$APP/db/sku_sale_attr_value/$do_date' OVERWRITE into table ${APP}.ods_sku_sale_attr_value partition(dt='$do_date'); "
ods_base_province="
load data inpath '/origin_data/$APP/db/base_province/$do_date' OVERWRITE into table ${APP}.ods_base_province;"
ods_base_region="
load data inpath '/origin_data/$APP/db/base_region/$do_date' OVERWRITE into table ${APP}.ods_base_region;"
case $1 in
"ods_order_info"){
hive -e "$ods_order_info"
};;
"ods_order_detail"){
hive -e "$ods_order_detail"
};;
"ods_sku_info"){
hive -e "$ods_sku_info"
};;
"ods_user_info"){
hive -e "$ods_user_info"
};;
"ods_payment_info"){
hive -e "$ods_payment_info"
};;
"ods_base_category1"){
hive -e "$ods_base_category1"
};;
"ods_base_category2"){
hive -e "$ods_base_category2"
};;
"ods_base_category3"){
hive -e "$ods_base_category3"
};;
"ods_base_trademark"){
hive -e "$ods_base_trademark"
};;
"ods_activity_info"){
hive -e "$ods_activity_info"
};;
"ods_cart_info"){
hive -e "$ods_cart_info"
};;
"ods_comment_info"){
hive -e "$ods_comment_info"
};;
"ods_coupon_info"){
hive -e "$ods_coupon_info"
};;
"ods_coupon_use"){
hive -e "$ods_coupon_use"
};;
"ods_favor_info"){
hive -e "$ods_favor_info"
};;
"ods_order_refund_info"){
hive -e "$ods_order_refund_info"
};;
"ods_order_status_log"){
hive -e "$ods_order_status_log"
};;
"ods_spu_info"){
hive -e "$ods_spu_info"
};;
"ods_activity_rule"){
hive -e "$ods_activity_rule"
};;
"ods_base_dic"){
hive -e "$ods_base_dic"
};;
"ods_order_detail_activity"){
hive -e "$ods_order_detail_activity"
};;
"ods_order_detail_coupon"){
hive -e "$ods_order_detail_coupon"
};;
"ods_refund_payment"){
hive -e "$ods_refund_payment"
};;
"ods_sku_attr_value"){
hive -e "$ods_sku_attr_value"
};;
"ods_sku_sale_attr_value"){
hive -e "$ods_sku_sale_attr_value"
};;
"ods_base_province"){
hive -e "$ods_base_province"
};;
"ods_base_region"){
hive -e "$ods_base_region"
};;
"all"){
hive -e "$ods_order_info$ods_order_detail$ods_sku_info$ods_user_info$ods_payment_info$ods_base_category1$ods_base_category2$ods_base_category3$ods_base_trademark$ods_activity_info$ods_cart_info$ods_comment_info$ods_coupon_info$ods_coupon_use$ods_favor_info$ods_order_refund_info$ods_order_status_log$ods_spu_info$ods_activity_rule$ods_base_dic$ods_order_detail_activity$ods_order_detail_coupon$ods_refund_payment$ods_sku_attr_value$ods_sku_sale_attr_value$ods_base_province$ods_base_region"
};;
esac
[doudou@hadoop102 bin]$ chmod 777 hdfs_to_ods_db_init.sh
ODS层业务表每日数据装载脚本
[doudou@hadoop102 bin]$ vim hdfs_to_ods_db.sh
#!/bin/bash
APP=gmall
# 如果是输入的日期按照取输入日期;如果没输入日期取当前时间的前一天
if [ -n "$2" ] ;then
do_date=$2
else
do_date=`date -d "-1 day" +%F`
fi
ods_order_info="
load data inpath '/origin_data/$APP/db/order_info/$do_date' OVERWRITE into table ${APP}.ods_order_info partition(dt='$do_date');"
ods_order_detail="
load data inpath '/origin_data/$APP/db/order_detail/$do_date' OVERWRITE into table ${APP}.ods_order_detail partition(dt='$do_date');"
ods_sku_info="
load data inpath '/origin_data/$APP/db/sku_info/$do_date' OVERWRITE into table ${APP}.ods_sku_info partition(dt='$do_date');"
ods_user_info="
load data inpath '/origin_data/$APP/db/user_info/$do_date' OVERWRITE into table ${APP}.ods_user_info partition(dt='$do_date');"
ods_payment_info="
load data inpath '/origin_data/$APP/db/payment_info/$do_date' OVERWRITE into table ${APP}.ods_payment_info partition(dt='$do_date');"
ods_base_category1="
load data inpath '/origin_data/$APP/db/base_category1/$do_date' OVERWRITE into table ${APP}.ods_base_category1 partition(dt='$do_date');"
ods_base_category2="
load data inpath '/origin_data/$APP/db/base_category2/$do_date' OVERWRITE into table ${APP}.ods_base_category2 partition(dt='$do_date');"
ods_base_category3="
load data inpath '/origin_data/$APP/db/base_category3/$do_date' OVERWRITE into table ${APP}.ods_base_category3 partition(dt='$do_date'); "
ods_base_trademark="
load data inpath '/origin_data/$APP/db/base_trademark/$do_date' OVERWRITE into table ${APP}.ods_base_trademark partition(dt='$do_date'); "
ods_activity_info="
load data inpath '/origin_data/$APP/db/activity_info/$do_date' OVERWRITE into table ${APP}.ods_activity_info partition(dt='$do_date'); "
ods_cart_info="
load data inpath '/origin_data/$APP/db/cart_info/$do_date' OVERWRITE into table ${APP}.ods_cart_info partition(dt='$do_date'); "
ods_comment_info="
load data inpath '/origin_data/$APP/db/comment_info/$do_date' OVERWRITE into table ${APP}.ods_comment_info partition(dt='$do_date'); "
ods_coupon_info="
load data inpath '/origin_data/$APP/db/coupon_info/$do_date' OVERWRITE into table ${APP}.ods_coupon_info partition(dt='$do_date'); "
ods_coupon_use="
load data inpath '/origin_data/$APP/db/coupon_use/$do_date' OVERWRITE into table ${APP}.ods_coupon_use partition(dt='$do_date'); "
ods_favor_info="
load data inpath '/origin_data/$APP/db/favor_info/$do_date' OVERWRITE into table ${APP}.ods_favor_info partition(dt='$do_date'); "
ods_order_refund_info="
load data inpath '/origin_data/$APP/db/order_refund_info/$do_date' OVERWRITE into table ${APP}.ods_order_refund_info partition(dt='$do_date'); "
ods_order_status_log="
load data inpath '/origin_data/$APP/db/order_status_log/$do_date' OVERWRITE into table ${APP}.ods_order_status_log partition(dt='$do_date'); "
ods_spu_info="
load data inpath '/origin_data/$APP/db/spu_info/$do_date' OVERWRITE into table ${APP}.ods_spu_info partition(dt='$do_date'); "
ods_activity_rule="
load data inpath '/origin_data/$APP/db/activity_rule/$do_date' OVERWRITE into table ${APP}.ods_activity_rule partition(dt='$do_date');"
ods_base_dic="
load data inpath '/origin_data/$APP/db/base_dic/$do_date' OVERWRITE into table ${APP}.ods_base_dic partition(dt='$do_date'); "
ods_order_detail_activity="
load data inpath '/origin_data/$APP/db/order_detail_activity/$do_date' OVERWRITE into table ${APP}.ods_order_detail_activity partition(dt='$do_date'); "
ods_order_detail_coupon="
load data inpath '/origin_data/$APP/db/order_detail_coupon/$do_date' OVERWRITE into table ${APP}.ods_order_detail_coupon partition(dt='$do_date'); "
ods_refund_payment="
load data inpath '/origin_data/$APP/db/refund_payment/$do_date' OVERWRITE into table ${APP}.ods_refund_payment partition(dt='$do_date'); "
ods_sku_attr_value="
load data inpath '/origin_data/$APP/db/sku_attr_value/$do_date' OVERWRITE into table ${APP}.ods_sku_attr_value partition(dt='$do_date'); "
ods_sku_sale_attr_value="
load data inpath '/origin_data/$APP/db/sku_sale_attr_value/$do_date' OVERWRITE into table ${APP}.ods_sku_sale_attr_value partition(dt='$do_date'); "
ods_base_province="
load data inpath '/origin_data/$APP/db/base_province/$do_date' OVERWRITE into table ${APP}.ods_base_province;"
ods_base_region="
load data inpath '/origin_data/$APP/db/base_region/$do_date' OVERWRITE into table ${APP}.ods_base_region;"
case $1 in
"ods_order_info"){
hive -e "$ods_order_info"
};;
"ods_order_detail"){
hive -e "$ods_order_detail"
};;
"ods_sku_info"){
hive -e "$ods_sku_info"
};;
"ods_user_info"){
hive -e "$ods_user_info"
};;
"ods_payment_info"){
hive -e "$ods_payment_info"
};;
"ods_base_category1"){
hive -e "$ods_base_category1"
};;
"ods_base_category2"){
hive -e "$ods_base_category2"
};;
"ods_base_category3"){
hive -e "$ods_base_category3"
};;
"ods_base_trademark"){
hive -e "$ods_base_trademark"
};;
"ods_activity_info"){
hive -e "$ods_activity_info"
};;
"ods_cart_info"){
hive -e "$ods_cart_info"
};;
"ods_comment_info"){
hive -e "$ods_comment_info"
};;
"ods_coupon_info"){
hive -e "$ods_coupon_info"
};;
"ods_coupon_use"){
hive -e "$ods_coupon_use"
};;
"ods_favor_info"){
hive -e "$ods_favor_info"
};;
"ods_order_refund_info"){
hive -e "$ods_order_refund_info"
};;
"ods_order_status_log"){
hive -e "$ods_order_status_log"
};;
"ods_spu_info"){
hive -e "$ods_spu_info"
};;
"ods_activity_rule"){
hive -e "$ods_activity_rule"
};;
"ods_base_dic"){
hive -e "$ods_base_dic"
};;
"ods_order_detail_activity"){
hive -e "$ods_order_detail_activity"
};;
"ods_order_detail_coupon"){
hive -e "$ods_order_detail_coupon"
};;
"ods_refund_payment"){
hive -e "$ods_refund_payment"
};;
"ods_sku_attr_value"){
hive -e "$ods_sku_attr_value"
};;
"ods_sku_sale_attr_value"){
hive -e "$ods_sku_sale_attr_value"
};;
"all"){
hive -e "$ods_order_info$ods_order_detail$ods_sku_info$ods_user_info$ods_payment_info$ods_base_category1$ods_base_category2$ods_base_category3$ods_base_trademark$ods_activity_info$ods_cart_info$ods_comment_info$ods_coupon_info$ods_coupon_use$ods_favor_info$ods_order_refund_info$ods_order_status_log$ods_spu_info$ods_activity_rule$ods_base_dic$ods_order_detail_activity$ods_order_detail_coupon$ods_refund_payment$ods_sku_attr_value$ods_sku_sale_attr_value"
};;
esac
[doudou@hadoop102 bin]$ chmod 777 hdfs_to_ods_db.sh
本文含有隐藏内容,请 开通VIP 后查看