关闭

Hadoop Mapreduce

85人阅读 评论(0) 收藏 举报
  • What happens if the value list for 1 key is largerfor 1 reduce task?
    • Before reduce, framework will sort it first. It should be able to be processed in memory. Otherwise, External Sorting is needed. To avoid this, more machines for reduce task should be added.
    • So it may only happen during very extreme cases when values for one key is very large
  • How to deploy a map-reduce job on Hadoop?
0
0

查看评论
* 以上用户言论只代表其个人观点,不代表CSDN网站的观点或立场
    个人资料
    • 访问:6328次
    • 积分:151
    • 等级:
    • 排名:千里之外
    • 原创:12篇
    • 转载:1篇
    • 译文:0篇
    • 评论:0条
    文章分类