--TextFile

set hive.exec.compress.output=true;

set mapred.output.compress=true;

set mapred.output.compression.codec=org.apache.hadoop.io.compress.GzipCodec;

set io.compression.codecs=org.apache.hadoop.io.compress.GzipCodec;

INSERT OVERWRITE table hzr_test_text_table PARTITION(product='xxx',dt='2013-04-22')

SELECT xxx,xxx.... FROM xxxtable WHERE product='xxx' AND dt='2013-04-22';  

--SquenceFile

set hive.exec.compress.output=true;

set mapred.output.compress=true;

set mapred.output.compression.codec=org.apache.hadoop.io.compress.GzipCodec;

set io.compression.codecs=org.apache.hadoop.io.compress.GzipCodec;

set io.seqfile.compression.type=BLOCK;

INSERT OVERWRITE table hzr_test_sequence_table PARTITION(product='xxx',dt='2013-04-22')

SELECT xxx,xxx.... FROM xxxtable WHERE product='xxx' AND dt='2013-04-22';  

--RCFile

set hive.exec.compress.output=true;

set mapred.output.compress=true;

set mapred.output.compression.codec=org.apache.hadoop.io.compress.GzipCodec;

set io.compression.codecs=org.apache.hadoop.io.compress.GzipCodec;

INSERT OVERWRITE table hzr_test_rcfile_table PARTITION(product='xxx',dt='2013-04-22')

SELECT xxx,xxx.... FROM xxxtable WHERE product='xxx' AND dt='2013-04-22'; 

动态分区插入

set hive.exec.compress.output=true;

set mapred.output.compress=true;

SET hive.exec.dynamic.partition=true;

SET hive.exec.dynamic.partition.mode=nonstrict;

SET hive.exec.max.dynamic.partitions.pernode = 1000;

SET hive.exec.max.dynamic.partitions=1000;

INSERT overwrite TABLE t_lxw1234_partitioned PARTITION (month,day)

SELECT url,substr(day,1,7) AS month,day

FROM t_lxw1234;

注意：在PARTITION (month,day)中指定分区字段名即可；

在SELECT子句的最后两个字段，必须对应前面PARTITION (month,day)中指定的分区字段，包括顺序。

4 行转换列：  单表下写法

hive如何将

a       b       1

a       b       2

a       b       3

c       d       4

c       d       5

c       d       6

变为：

a       b       1,2,3

c       d       4,5,6

select col1,col2,concat_ws(',',collect_set(col3))

from tmp_jiangzl_test

group by col1,col2;    ----------------》 已经验证过  OK

添加metastore启动脚本bin/hive-metastore.sh

#!/bin/sh

nohup ./hive --service metastore >> metastore.log 2>&1 &

echo $! > hive-metastore.pid

添加hive server启动脚本bin/hive-server.sh

nohup ./hive --service hiveserver >> hiveserver.log 2>&1 &

echo $! > hive-server.pid

启动metastore和hive server

./hive-metastore.sh

./hive-server.sh

nohup ./hiveserver2 >> hiveserver.log 2>&1 &

beeline参数设置:https://cwiki.apache.org/confluence/display/Hive/HiveServer2+Clients