hadoop-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Agarwal, Nikhil" <Nikhil.Agar...@netapp.com>
Subject RE: MapReduce on Local FileSystem
Date Fri, 31 May 2013 07:12:34 GMT
Hi Rahul,

Can you please explain what do you mean by “filer directory mounted to all the DN” ? Do
you mean a NFS-mount? If yes then I want to avoid NFS-mount. With NFS-mount it is possible
to do it.

Thanks & Regards,

From: Rahul Bhattacharjee [mailto:rahul.rec.dgp@gmail.com]
Sent: Friday, May 31, 2013 12:33 PM
To: user@hadoop.apache.org
Subject: Re: MapReduce on Local FileSystem

Just a hunch. Can have a filer directory mounted to all the DN and then file:///<file:///\\>
should be usuable in a distributed fashion. (Just a guess)

On Fri, May 31, 2013 at 12:07 PM, Agarwal, Nikhil <Nikhil.Agarwal@netapp.com<mailto:Nikhil.Agarwal@netapp.com>>

Is it possible to run MapReduce on multiple nodes using Local File system (file:///<file:///\\>)
I am able to run it in single node setup but in a multiple node setup the “slave” nodes
are not able to access the “jobtoken” file which is present in the Hadoop.tmp.dir in “master”

Please let me know if it is possible to do this.

Thanks & Regards,

View raw message