存储文件压缩比总结：
ORC > Parquet > textFile
存储文件的查询速度总结：（select count（*））
ORC > TextFile > Parquet
存储方式和压缩总结：
在实际的项目开发当中，hive表的数据存储格式一般选择：orc或parquet。压缩方式一般选择snappy。
1.hive创建表：
create table log_text (
track_time string,
url string,
session_id string,
referer string,
ip string,
end_user_id string,
city_id string
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘\t’
STORED AS TEXTFILE ;
//分割–orc 有默认压缩方式是ZLIB
create table log_orc(
track_time string,
url string,
session_id string,
referer string,
ip string,
end_user_id string,
city_id string
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘\t’
STORED AS orc ;
//分割
create table log_parquet(
track_time string,
url string,
session_id string,
referer string,
ip string,
end_user_id string,
city_id string
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘\t’
STORED AS PARQUET ;
//分割–创建一个非压缩的的ORC存储方式
create table log_orc_none(
track_time string,
url string,
session_id string,
referer string,
ip string,
end_user_id string,
city_id string
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘\t’
STORED AS orc tblproperties (“orc.compress”=“NONE”);
//分割–创建一个SNAPPY压缩的ORC存储方式，SNAPPY的压缩和解压速度很快
create table log_orc_snappy(
track_time string,
url string,
session_id string,
referer string,
ip string,
end_user_id string,
city_id string
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘\t’
STORED AS orc tblproperties (“orc.compress”=“SNAPPY”);
2.装载数据到表
load data local inpath ‘/export/servers/hivedatas/log.data’ into table log_text；
insert into table log_orc select * from log_text ;
insert into table log_parquet select * from log_text ;
insert into table log_orc_none select * from log_text ;
insert into table log_orc_snappy select * from log_text ;
3.查看文件压缩比：
hadoop fs -du -h /user/hive/warehouse/test.db/log_text;
hadoop fs -du -h /user/hive/warehouse/test.db/log_orc;
hadoop fs -du -h /user/hive/warehouse/test.db/log_parquet;
hadoop fs -du -h /user/hive/warehouse/test.db/log_orc_none;
hadoop fs -du -h /user/hive/warehouse/test.db/log_orc_snappy;
