hive表多种存储格式的文件大小差异，无重复数据

-- 重点，目标表无重复数据

-- dbName.num_result 无重复记录
-- 插入数据
CREATE TABLE dbName.test_textfile(
  `key` string,
  `value` string,
  `p_key` string,
  `p_key2` string)
STORED AS textfile
;
insert overwrite table dbName.test_textfile select * from dbName.num_result where p_key='' and p_key2='';

drop table dbName.test_orcfile;
CREATE TABLE dbName.test_orcfile(
  `key` string,
  `value` string,
  `p_key` string,
  `p_key2` string)
STORED AS orc
;
insert overwrite table dbName.test_orcfile select * from test_textfile;

CREATE TABLE dbName.test_rcfile(
  `key` string,
  `value` string,
  `p_key` string,
  `p_key2` string)
STORED AS rcfile
;
insert overwrite table dbName.test_rcfile select * from test_textfile;

CREATE TABLE dbName.test_parquet(
  `key` string,
  `value` string,
  `p_key` string,
  `p_key2` string)
STORED AS parquet
;
insert overwrite table dbName.test_parquet select * from test_textfile;

-- 统计数据量
select count(1) as cnt from dbName.test_textfile;
select count(1) as cnt from dbName.test_orcfile;
select count(1) as cnt from dbName.test_rcfile;
select count(1) as cnt from dbName.test_parquet;

-- 统计文件大小
dfs -du -s -h hdfs://nameservice1/user/hive/warehouse/dbName.db/test_text*;
dfs -du -s -h hdfs://nameservice1/user/hive/warehouse/dbName.db/test_par*;
dfs -du -s -h hdfs://nameservice1/user/hive/warehouse/dbName.db/test_rc*;
dfs -du -s -h hdfs://nameservice1/user/hive/warehouse/dbName.db/test_orc*;

1.0 G  3.1 G  hdfs://nameNode/user/hive/warehouse/dbName.db/test_textfile
1.1 G  3.3 G  hdfs://nameNode/user/hive/warehouse/dbName.db/test_parquet
984.0 M  2.9 G  hdfs://nameNode/user/hive/warehouse/dbName.db/test_rcfile
470.0 M  1.4 G  hdfs://nameNode/user/hive/warehouse/dbName.db/test_orcfile

从结果可以看出，在无重复数据的情况下，parquet的压缩无用武之地，占用空间比textfile还大，ORC是压缩最强的文件模式。

hive (dbName)> dfs -du -s hdfs://nameNode/user/hive/warehouse/dbName.db/test_text*;
1110741501  3332224503  hdfs://nameNode/user/hive/warehouse/dbName.db/test_textfile
hive (dbName)> dfs -du -s hdfs://nameNode/user/hive/warehouse/dbName.db/test_par*;
1167366639  3502099917  hdfs://nameNode/user/hive/warehouse/dbName.db/test_parquet
hive (dbName)> dfs -du -s hdfs://nameNode/user/hive/warehouse/dbName.db/test_rc*;
1031774688  3095324064  hdfs://nameNode/user/hive/warehouse/dbName.db/test_rcfile
hive (dbName)> dfs -du -s hdfs://nameNode/user/hive/warehouse/dbName.db/test_orc*;
492795434  1478386302  hdfs://nameNode/user/hive/warehouse/dbName.db/test_orcfile