You are viewing a plain text version of this content. The canonical link for it is here.

Posted to mapreduce-user@hadoop.apache.org by zhangyujian1984 <zh...@gmail.com> on 2014/12/04 09:40:10 UTC

Reliability of Hadoop

hi,
 
       hadoop uses rank-aware data placement policy, blocks are randomly placed in datanodes.
I wonder how to measure the reliability of the cluster. if i changed data placement policy, how 
can i compare the reliability of the two policies.

Best Regards


Yu-jian Zhang