hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Owen O'Malley" <...@yahoo-inc.com>
Subject Re: Distribution of map tasks
Date Thu, 24 May 2007 04:43:30 GMT

On May 23, 2007, at 5:46 PM, Phantom wrote:

> Hi
>
> I am trying to run the Word Count sample against a file that is  
> 1.5GB. I
> have setup Hadoop to run on a cluster of 3 nodes. However I have a  
> reason to
> beleive that the map tasks are not being distributed to the slaves.  
> How do I
> check if this is the case and if it is how do I cause the Map tasks  
> to be
> distributed ? Please advice.

If you point a browser at your job tracker, you'll see the status of  
the jobs. The info port defaults to 50030, so it would look like:
   http://localhost:50030/
on the node with the JobTracker. If you expand out the list of tasks  
for a job, it will tell you where they are running.

-- Owen

Mime
View raw message