Hive优化(六)-使用分区剪裁、列剪裁-查询速度快

create table ori(id bigint, time bigint, uid string, keyword string, url_rank int, click_num int, click_url string) row format delimited fields terminated by '\t';
 
create table bigtable(id bigint, time bigint, uid string, keyword string, url_rank int, click_num int, click_url string) row format delimited fields terminated by '\t';
 
load data local inpath '/home/admin/softwares/data/加递增id的原始数据/ori' into table ori;
 
load data local inpath '/home/admin/softwares/data/100万条大表数据（id除以10取整）/bigtable' into table bigtable;

先关联再Where：
【问题：如果将副表的过滤条件写在where后面，先关联后过滤】
SELECT a.id
FROM bigtable a
LEFT JOIN ori b ON a.id = b.id
WHERE b.id <= 10;

正确的写法是写在ON后面：先Where再关联
SELECT a.id
FROM ori a
LEFT JOIN bigtable b ON (a.id <= 10 AND a.id = b.id);

或者直接写成子查询：
SELECT a.id
FROM bigtable a
RIGHT JOIN (SELECT id
FROM ori
WHERE id <= 10
) b ON a.id = b.id;