分区的值是非确定的,由输入数据来确定
1、动态分区的相关属性:
hive.exec.dynamic.partition=true :是否允许动态分区
hive.exec.dynamic.partition.mode=strict :分区模式设置
strict:最少需要有一个是静态分区
nostrict:可以全部是动态分区
hive.exec.max.dynamic.partitions=1000 :允许动态分区的最大数量
hive.exec.max.dynamic.partitions.pernode =100 :单个节点上的mapper/reducer允许创建的最大分区
2、动态分区的操作
##创建临时表
create table if not exists tmp
(uid int,
commentid bigint,
recommentid bigint,
year int,
month int,
day int)
row format delimited fields terminated by '\t';
##加载数据
load data local inpath '/root/Desktop/comm' into table tmp;
##创建动态分区表
create table if not exists dyp1
(uid int,
commentid bigint,
recommentid bigint)
partitioned by(year int,month int,day int)
row format delimited fields terminated by '\t';
##严格模式
insert into table dyp1 partition(year=2016,month,day)
select uid,commentid,recommentid,month,day from tmp;
##非严格模式
##设置非严格模式动态分区
set hive.exec.dynamic.partition.mode=nostrict;
##创建动态分区表
create table if not exists dyp2
(uid int,
commentid bigint,
recommentid bigint)
partitioned by(year int,month int,day int)
row format delimited fields terminated by '\t';
##为非严格模式动态分区加载数据
insert into table dyp2 partition(year,month,day)
select uid,commentid,recommentid,year,month,day from tmp;