No I am talking about task tracker failover and I saw block copy/replication
happening there too,
and it is possible because the failedover instance has to access block which
may be on victim instance. For map/reduce to work fast, it may want to store
the block locally, therefore trying to replica
I guess ur confusing data node with task tracker. If a task tracker
fails the job tracker assigns the task to other task trackers.. and the
block copy/replication ur refering to, is related datanodes.
-G.
Sarvesh Singh wrote:
Hi,
Task tracker failover happens but alive slave instance firstly
