怎么把impala表导入kudu
Posted
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了怎么把impala表导入kudu相关的知识,希望对你有一定的参考价值。
可以通过映射表方式实现。下面说得略细,需要耐心看并做参考:首先要知道目前(2017.05.04)kudu没有timestamp与decimal类型,需要用其它类型代替,比如timestamp可以用长bigint代替,decimal可以用double型代替。
如果想在kudu中创建一个新表,并将数据导入到这个新表中,那么比较简单的方式是通过impala建立kudo的内部映射表,因为建立内部映射表过程会同时建立一个kudu新表并在impala中建立一个内部映射表,建立方法如下:
首先保证kudu正确安装并且master与tserver服务都正常运行,然后在impala shell中输入
create table table_name (
column1 type primary key ...,
column2 type,
...
)
partition by hash(column1) partitions n stored as kudu;
这样就在kudu中建立好表了,下一步就可以通过impala的映射表向这个kudu表中导入数据了(table_name要用自己取的表名代替,columnN也要用自己取的列名代替。)(如果建立列集主键,方式为primary key(column1, column2, column3),具体如何建立这里就不细说了)(顺便说一下:这样建立的kudu中的表名为:impala::database_name.table_name)。
如果kudu中已经存在一个现有表,您想将impala表中数据导入到这个现有kudu表中,那么需要在impala中建立外部映射表,方法是:
create external table table_name
stored as kudu
tblproperties('kudu.table_name' = 'kudu中的table_name');
这样就建立完成了。
在impala shell 中执行:
insert into table_name select * from 你的impala表;
就可以将你的表数据导入到新表了。
最后提及:kudu表必须有主键或者列集主键,可能你的表没有主键或列集主键,而你的表第一列或对应列集的前几列又有重复数据,这种情况下你的表导入后会有数据丢失,比较简单的解决方法是:
在建立kudu表时增加一个专门的主键,放在第一列。然后:
insert into table_name select row_number() over(order by 你的impala表中任意一列名), * from 你的impala表; 参考技术A HDFS和HBase两个系统把持着,一直没有太大突破。在追求高吞吐的批处理场景下,我们选用HDFS,在追求低延迟,有随机读写需求的场景下,我们选用HBase,那么是否存在一种系统,能结合两个系统优点,同时支持高吞吐率和低延迟呢?有人尝试修改HBas
客快物流大数据项目(七十九):Impala映射kudu表
文章目录
Impala映射kudu表
一、登录Hue页面
1、选择Impala
2、登录Hue页面
二、选择Impala执行引擎
1、选择Impala执行引擎
2、进入编写执行sql语句窗口
三、执行sql语句映射Kudu表
若数据库已经存在,则使用级联的方式删除:
DROP DATABASE logistics cascade;
编写kudu与impala表的映射关系,Sql语句如下:
CREATE DATABASE IF NOT EXISTS logistics;
CREATE EXTERNAL TABLE logistics.tbl_warehouse_transport_tool_detail
STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_warehouse_transport_tool_detail',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_dot_transport_tool_detail STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_dot_transport_tool_detail',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_express_bill_detail STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_express_bill_detail',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_waybill STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_waybill',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_collect_package STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_collect_package',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_store_grid STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_store_grid',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_pkg STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_pkg',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_out_warehouse_detail STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_out_warehouse_detail',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_goods_rack STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_goods_rack',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_warehouse_receipt_detail STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_warehouse_receipt_detail',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_fixed_area STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_fixed_area',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_department STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_department',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_express_bill STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_express_bill',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_delivery_record STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_delivery_record',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_waybill_detail STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_waybill_detail',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_warehouse_emp STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_warehouse_emp',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_emp_info_map STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_emp_info_map',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_service_evaluation STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_service_evaluation',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_dot_transport_tool STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_dot_transport_tool',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_postal_standard STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_postal_standard',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_emp STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_emp',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_push_warehouse_detail STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_push_warehouse_detail',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_customer STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_customer',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_warehouse_transport_tool STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_warehouse_transport_tool',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_deliver_region STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_deliver_region',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_waybill_state_record STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_waybill_state_record',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_company_dot_map STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_company_dot_map',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_areas STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_areas',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_company_warehouse_map STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_company_warehouse_map',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_warehouse_send_vehicle STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_warehouse_send_vehicle',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_warehouse_vehicle_map STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_warehouse_vehicle_map',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_customer_detail STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_customer_detail',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_company STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_company',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_courier STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_courier',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_vehicle_monitor STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_vehicle_monitor',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_deliver_package STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_deliver_package',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_charge_standard STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_charge_standard',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_warehouse_rack_map STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_warehouse_rack_map',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_codes STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_codes',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_warehouse STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_warehouse',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_job STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_job',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_waybill_line STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_waybill_line',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_work_time STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_work_time',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_consumer_sender_info STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_consumer_sender_info',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_driver STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_driver',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_consumer_address_map STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_consumer_address_map',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_warehouse_receipt STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_warehouse_receipt',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_dot STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_dot',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_transport_tool STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_transport_tool',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_out_warehouse STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_out_warehouse',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_address STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_address',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_route STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_route',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_push_warehouse STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_push_warehouse',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_company_transport_route_ma STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_company_transport_route_ma',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE logistics.tbl_express_package STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_express_package',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
CREATE EXTERNAL TABLE `tbl_warehouse_detail` STORED AS KUDU TBLPROPERTIES(
'kudu.table_name' = 'tbl_warehouse_detail',
'kudu.master_addresses' = 'node2.lanson.cn:7051');
- 📢博客主页:https://lansonli.blog.csdn.net
- 📢欢迎点赞 👍 收藏 ⭐留言 📝 如有错误敬请指正!
- 📢本文由 Lansonli 原创,首发于 CSDN博客🙉
- 📢停下休息的时候不要忘了别人还在奔跑,希望大家抓紧时间学习,全力奔赴更美好的生活✨
以上是关于怎么把impala表导入kudu的主要内容,如果未能解决你的问题,请参考以下文章