hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Sarvesh Singh" <serve...@gmail.com>
Subject Re: Task tracker failover
Date Wed, 10 Jan 2007 12:54:57 GMT
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 <gautamk@yahoo-inc.com> 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
> >
>
>

Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message