hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Amogh Vasekar <am...@yahoo-inc.com>
Subject RE: last map task taking too long
Date Wed, 30 Sep 2009 05:28:01 GMT
Can you provide info on the input like compression etc? Also, are you using cached files in
your map tasks? It might be helpful if you paste the logs here after blanking your system
specific info., as then one can find out where till the reduce it went or if the copy phase
started at all.


-----Original Message-----
From: achilles852 [mailto:faheemkhan@gmail.com] 
Sent: Wednesday, September 30, 2009 6:38 AM
To: core-dev@hadoop.apache.org
Subject: Re: last map task taking too long

Basically, it finishes what it is supposed to do (I view the logs to find
out), but does not move onto the reduce stage.

Ted Dunning wrote:
> Is that last map task actually running, or is it pending?
> On Tue, Sep 29, 2009 at 5:57 PM, achilles852 <faheemkhan@gmail.com> wrote:
>> Hey.. I am trying to write a small mapreduce program. I launch a few map
>> tasks, each of which should complete within a certain time (say 5
>> minutes)... all the tasks complete within 5 minutes except the last one -
>> which takes around 10 times more the time taken by all other map
>> tasks.....any idea why this is happening?
>> I am using Hadoop version 0.19.2, tried running it locally as well as on
>> EC2.
>> --
>> View this message in context:
>> http://www.nabble.com/last-map-task-taking-too-long-tp25673359p25673359.html
>> Sent from the Hadoop core-dev mailing list archive at Nabble.com.
> -- 
> Ted Dunning, CTO
> DeepDyve

View this message in context: http://www.nabble.com/last-map-task-taking-too-long-tp25673359p25673431.html
Sent from the Hadoop core-dev mailing list archive at Nabble.com.

View raw message