schematool -dbType mysql -initSchema;
describe formatted test;
create table test (id int,name string) clustered buy(id) into 12 buckets;
create table test(id int,name string,zipcode int) skewed by (zipcode) on (223003,200099) stored as directories;
set hive.exec.mode.local.auto.tasks.max=10;
set hive.cli.print.header = True;
set mapreduce.job.reduces=2;
set mapred.reduce.tasks=<number>;
set hive.cli.print.header=true;
hive -f myscript.hive -hiveconf mapreduce.job.reduces=2;
beeline> !connect jdbc:hive2://myservername1:2181,myhiveservername2:2222/;serviceDiscoveryMode=zooKeeper;zooKeeperNamespace=hiveserver2
beeline -u url -n username -p pass;
select * from names where age =${age};
hive -f myscript.hive -hivevar age =33;
select /*+MAPJOIN(static)*/ customers.*,states.* from customers join states on(customers.state=states.state);
select a.key from a left outer join b on a.key=b.key where b.key1 is null --(not in)
set hive.exec.parallel=true; //打开任务并行执行
set hive.exec.parallel.thread.number=16; //同一个sql允许最大并行度,默认为8。
//更多命令:
//http://blog.csdn.net/joseph_happy/article/details/50428858
满足如下条件才能真正使用本地模式:
set hive.exec.mode.local.auto=true; //开启本地mr
//设置local mr的最大输入数据量,当输入数据量小于这个值的时候会采用local mr的方式
set hive.exec.mode.local.auto.inputbytes.max=50000000;
//设置local mr的最大输入文件个数,当输入文件个数小于这个值的时候会采用local mr的方式
网友评论