i think hadoop treats a node as a  minimal unit, which means a internal failure 
will be regards as a node failure.
datanode uses heartbeat to keep block alive, if any block failure was detected 
by namenode, it will be recovered 
in another datanode.



Yujian Zhang
Southeast University, Nanjing, China
 
From: [email protected]
Date: 2014-12-17 14:05
To: <[email protected]>
CC: [email protected]
Subject: How will Hadoop handle it when a datanode server with total hardware 
failure?
Hi,
 
If each of  my datanode servers has 8 hard disks (a 10-node cluster) and I use 
the default replication factor of 3, how will Hadoop handle it when a datanode 
with total hardware failure suddenly?  
 
Regards
Arthur

Reply via email to