hive在把一张表的数据插入到另一张分区表时,经常会报这个创建文件数超出限制的错误
解决办法:set hive.exec.max.created.files=900000; 提高最大文件数
加上如下设置即可
set hive.input.format=org.apache.hadoop.hive.ql.io.CombineHiveInputFormat;
set mapred.max.split.size=256000000; -- 256M
set mapred.min.split.size.per.node=100000000; -- 100M
set mapred.min.split.size.per.rack=100000000; -- 100M
set hive.merge.mapfiles = true;
set hive.merge.mapredfiles = true;
set hive.merge.size.per.task = 256000000; -- 256M
set hive.merge.smallfiles.avgsize=16000000; -- 16M
set mapreduce.map.memory.mb=10240;
set mapreduce.reduce.memory.mb=10240;
set mapred.reduce.slowstart.completed.maps=1;
set hive.exec.dynamic.partition.mode=nonstrict;
set hive.exec.max.dynamic.partitions.pernode=20000;
set hive.exec.max.dynamic.partitions=20000;
set hive.exec.max.created.files=900000;