hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From deneche abdelhakim <a_dene...@yahoo.fr>
Subject DistributedCache or not ?
Date Mon, 07 Jul 2008 08:54:06 GMT
I am using Hadoop in a recursive application, for each iteration a new job is launched and
a large bunch of data, a big List variable, is passed using the job parameters in a form of
a single xml string. The data is different for each iteration.

My question is : is there any advantage of using the distributed cache in this particular
case ? for example : writing the data to a file and passing the file with the distributed

Envoyez avec Yahoo! Mail. Une boite mail plus intelligente http://mail.yahoo.fr
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message