hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From kartik <ekar...@huawei.com>
Subject RE: Jobtrackers scalability
Date Wed, 03 Mar 2010 08:54:45 GMT
 

hai geeks,

 

 

The functionality of the job tracker is to divide the job among the
tasktrackers and monitor the progress of the task, and even the job also...

 

Do we address a situation where we have similar commodity hardware deployed
suppose of 2GB RAM and there are some 10000 nodes and we have to submit a
single batch job ... (That is think of a scenario where we do not have any
high end computer which alone would be configured as a JobTracker )..  Which
requires to coordinate all the 10000 TaskTrackers.. I think this will surely
degrade the performance of the JobTracker.... 

 

For applications now-a-days it is impractical to think of a similar
scenario, but just to confirm whether the job tracker will run under such
scenarios..

 

Was just curious to know what would be the limit in terms of RAM size and
CPU speed of a Job Tracker to support such a application.

 

 

Thanks and Regards

Kartik

 

 

 

 

****************************************************************************
***********
This e-mail and attachments contain confidential information from HUAWEI,
which is intended only for the person or entity whose address is listed
above. Any use of the information contained herein in any way (including,
but not limited to, total or partial disclosure, reproduction, or
dissemination) by persons other than the intended recipient's) is
prohibited. If you receive this e-mail in error, please notify the sender by
phone or email immediately and delete it!

 


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