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 replicate it.
Thanks Servesh On 1/10/07, Gautam Kowshik <[EMAIL PROTECTED]> wrote:
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 does copy > the blocks locally and then recover that. Therefore due to copy > operation it > takes 7-10 minutes for my test case. To me it looks to be more. Can we > have > fastest failover and resume the operation > quickly? Is there anyway to tweak the configuration?? > > Thanks > Servesh >
