HDFS in MapReduce

Leave a Comment / Architecture / October 29, 2012

1. Map的输入数据一般放在HDFS中

2. Map的输出数据放在本地硬盘上，因为它们只是中间结果，不需要冗余，所以不需要用HDFS

3. Reduce的输出数据放在HDFS中，以实现冗余

Leave a Comment

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.