hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Roberto Fonti <roberto.fo...@buongiorno.com>
Subject HDFS assumptions
Date Sun, 24 Sep 2006 14:23:50 GMT
Hi all,

Hadoop DFS in inspired to Google FS. Do they share all the assumptions 
listed in the Google File System documentation? 
(http://labs.google.com/papers/gfs.html : par. 2.1)

In particular:
 > The system stores a modest number of large files. [...] Small files 
must be supported, but we need not optimize for them.

Does anyone have experience using hadoop as a reliable filesystem to 
store a very large number of small/medium size files?



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