clear query| facets| time Search criteria: .   Results from 1 to 6 from 6 (0.0s).
Loading phrases to help you
refine your search...
Understanding Network Utilization of TeraSort - HDFS - [mail # dev]
...My goal is to see how the performance and network utilization of TeraSortis affected by varying the replication factor from 1-3 on my 16-nodecluster. (I have modified TeraSort such that it u...
   Author: Eitan Rosenfeld , 2015-01-10, 02:33
[expand - 1 more] - Why do reads take as long as replicated writes? - HDFS - [mail # dev]
...Daemeon - Indeed, I neglected to mention that I am clearing the cachesthroughout my cluster before running the read benchmark. My expectationwas to ideally get results that were proportionat...
   Author: Eitan Rosenfeld , 2014-11-06, 00:10
Can I move block data directly? - HDFS - [mail # dev]
...Hi Azurry, I'd also like to be able to manually move blocks.  One piece that is missing in your current approach is updating any block mappings that the cluster relies on. The namenode ...
   Author: Eitan Rosenfeld , 2013-07-08, 13:23
Block deletion after benchmarks - HDFS - [mail # dev]
...Hi all,  In my two-datanode cluster, I require that file operations on the underlying filesystem take place in the same order.  Essentially, I wish for blocks to be created, writte...
   Author: Eitan Rosenfeld , 2013-06-10, 22:33
The current/ directory - HDFS - [mail # dev]
...Hi all,  Two questions:  1. I'd like to store groups of blk_ and .meta files within different partitions alongside the data/current/ folder. I'd like to store only the blk and .met...
   Author: Eitan Rosenfeld , 2013-04-24, 14:16