Suppose if we want to override the scheduling to force a reducer to
run on a particular machine.
Are there any particular classes in Hadoop that we can override to achieve that?
Thanks,
Felix Halim
On Fri, Aug 5, 2011 at 1:27 PM, Arun C Murthy wrote:
> Nope, currently we don't do a
Hi Arun,
Ah yes.. the first comment by Owen O'Malley is exactly what I have in mind.
Thanks,
Felix Halim
On Wed, Feb 10, 2010 at 3:04 AM, Arun C Murthy wrote:
> Felix, you might want to follow
> https://issues.apache.org/jira/browse/MAPREDUCE-1434.
> We are discussing ideas v
ately even when r(i) is not finished.
The termination condition is when some counter after r(i) is finished is zero.
Thus the result of m(i+1) is discarded.
I don't know how to make it clearer than this...
Felix Halim
On Tue, Feb 9, 2010 at 1:41 PM, Amogh Vasekar wrote:
> Hi,
>>
AFAIK, the chaining has to be defined before the job is started, right?
But because I don't know the value of K beforehand,
I want the chain to continue forever until some counter in reduce task is zero.
Felix Halim
On Thu, Feb 4, 2010 at 3:53 PM, Amogh Vasekar wrote:
>
>>>How
over until it discover that some counter in ri is zero
(so the result of m(K+1) is discarded, and the final result of rK is
taken).
Felix Halim
On Thu, Feb 4, 2010 at 12:25 PM, Ed Mazur wrote:
> Felix,
>
> You can use ChainMapper and ChainReducer to create jobs of the form
> M+RM
there a setting in Hadoop to do that?
Felix Halim
