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
