DROP TABLE IF EXISTS tab1;
-- The EXTERNAL clause means the data is located outside the central location
-- for Impala data files and is preserved when the associated Impala table is dropped.
-- We expect the data to already exist in the directory specified by the LOCATION clause.
CREATE EXTERNAL TABLE tab1
(
   id INT,
   col_1 BOOLEAN,
   col_2 DOUBLE,
   col_3 TIMESTAMP
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY ','
LOCATION '/user/cloudera/sample_data/tab1';

DROP TABLE IF EXISTS tab2;
-- TAB2 is an external table, similar to TAB1.
CREATE EXTERNAL TABLE tab2
(
   id INT,
   col_1 BOOLEAN,
   col_2 DOUBLE
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY ','
LOCATION '/user/cloudera/sample_data/tab2';

DROP TABLE IF EXISTS student;
CREATE TABLE student
(
   id INT,
   name STRING
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY ',';

• 前两个表是基于之前上传的文件的外部表
• 第三个表建立了一个空表，存储位置就是 hive 的 hive.metastore.warehouse.dir，依旧是用LOAD DATA方法加载数据
• 因为Impala是对hive的优化，所以impala的数据是直接存在hive上的，确保impala有对 hive.metastore.warehouse.dir 的写权限，如果没有就把impala加到hive这个组里面

[xmseapp03:21000] > select * from tab1;
Query: select * from tab1
+----+-------+------------+-------------------------------+
| id | col_1 | col_2      | col_3                         |
+----+-------+------------+-------------------------------+
| 1  | true  | 123.123    | 2012-10-24 08:55:00           |
| 2  | false | 1243.5     | 2012-10-25 13:40:00           |
| 3  | false | 24453.325  | 2008-08-22 09:33:21.123000000 |
| 4  | false | 243423.325 | 2007-05-12 22:32:21.334540000 |
| 5  | true  | 243.325    | 1953-04-22 09:11:33           |
+----+-------+------------+-------------------------------+
Fetched 5 row(s) in 6.91s

1|AAAAAAAABAAAAAAA|980124|7135|32946|2452238|2452208|Mr.|Javier|Lewis|Y|9|12|1936|CHILE||Javie
r.Lewis@VFAxlnZEvOx.org|2452508|
2|AAAAAAAACAAAAAAA|819667|1461|31655|2452318|2452288|Dr.|Amy|Moses|Y|9|4|1966|TOGO||Amy.Moses@
Ovk9KjHH.com|2452318|
3|AAAAAAAADAAAAAAA|1473522|6247|48572|2449130|2449100|Miss|Latisha|Hamilton|N|18|9|1979|NIUE||
Latisha.Hamilton@V.com|2452313|
4|AAAAAAAAEAAAAAAA|1703214|3986|39558|2450030|2450000|Dr.|Michael|White|N|7|6|1983|MEXICO||Mic
hael.White@i.org|2452361|
5|AAAAAAAAFAAAAAAA|953372|4470|36368|2449438|2449408|Sir|Robert|Moran|N|8|5|1956|FIJI||Robert.
Moran@Hh.edu|2452469|

hdfs dfs -put costomer.dat /user/hive/tpcds/customer/

--
-- store_sales fact table and surrounding dimension tables only
--
create database tpcds;
use tpcds;

drop table if exists customer;
create external table customer
(
    c_customer_sk             int,
    c_customer_id             string,
    c_current_cdemo_sk        int,
    c_current_hdemo_sk        int,
    c_current_addr_sk         int,
    c_first_shipto_date_sk    int,
    c_first_sales_date_sk     int,
    c_salutation              string,
    c_first_name              string,
    c_last_name               string,
    c_preferred_cust_flag     string,
    c_birth_day               int,
    c_birth_month             int,
    c_birth_year              int,
    c_birth_country           string,
    c_login                   string,
    c_email_address           string,
    c_last_review_date        string
)
row format delimited fields terminated by '|' 
location '/user/hive/tpcds/customer.dat';

Step2

impala-shell -i localhost -f customer_setup.sql

单条插入外部分区表的数据

Step1

$ hdfs dfs -mkdir -p /user/impala/data/logs/year=2015/month=01/day=01/host=host1
$ hdfs dfs -mkdir -p /user/impala/data/logs/year=2015/month=02/day=22/host=host2

1,jack
2,michael

3,sara
4,john

hdfs dfs -put /root/a.txt /user/impala/data/logs/year=2015/month=01/day=01/host=host1
hdfs dfs -put /root/b.txt /user/impala/data/logs/year=2015/month=02/day=22/host=host2

create external table logs (id int, name string)
  partitioned by (year string, month string, day string, host string)
  row format delimited fields terminated by ','
  location '/user/impala/data/logs';

alter table logs add partition (year="2015",month="01",day="01",host="host1");
alter table logs add partition (year="2015",month="02",day="22",host="host2");

select * from logs

insert into logs partition (year="2015", month="01", day="01", host="host1") values (6,"ted");

select * from logs;

• 对于Impala 2.0 以及以后的版本， 你需要在 Hive0.13 JDBC驱动 和 Cloudera JDBC 驱动之间选择。
• 如果你在项目中已经用了早期版本的Impala的JDBC， 你需要升级你的JDBC到上面提到的两个驱动中的一个， 因为之前你只能用Hive 0.12 驱动，但是这个驱动是不兼容 Imala2.0 及以上版本的。
• 你可以用linux的包管理器（在Centos上就是yum）来安装 Hive JDBC 驱动（包名叫  hive-jdbc）。
• 你也可以从Cloudera的官网上下载Cloudera JDBC 2.5驱动
• 两种驱动都可以提供稳定的速度提升（也就是说想用哪种看心情！说了跟没说一样）

<dependency>
	<groupId>org.apache.hive</groupId>
	<artifactId>hive-jdbc</artifactId>
	<version>0.14.0</version>
</dependency>
<dependency>
	<groupId>org.apache.hadoop</groupId>
	<artifactId>hadoop-common</artifactId>
	<version>2.2.0</version>
</dependency>