hama-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Apache Wiki <wikidi...@apache.org>
Subject [Hama Wiki] Update of "Partitioning" by edwardyoon
Date Sat, 28 Dec 2013 10:45:26 GMT
Dear Wiki user,

You have subscribed to a wiki page or wiki category on "Hama Wiki" for change notification.

The "Partitioning" page has been changed by edwardyoon:
https://wiki.apache.org/hama/Partitioning?action=diff&rev1=29&rev2=30

    * Job Scheduler assigns partitions to proper task based on partition ID.
   * After pre-partitioning done, launch the BSP job.
  
+ In NoSQLs table input case (which supports range or random access by sorted key), pre-processing
step will be skipped because they supports range scan.
- --
-  * ''Instead of running a separate job, we inject a partitioning superstep before the first
superstep of the job. (This has a dependency on the Superstep API) For graph jobs, we can
configure this partitioning superstep class specific to graph partitioning class that partitions
and loads vertices. - Suraj Menon''
-   * ''Since scaling the number of BSP tasks between supersteps in single job, is not possible,
the key is "how to launch the number of tasks differently with the number of file blocks".
and Even though graph use own graph partitioning class, the fact that parsing vertex structure
should be done at loadVertices() method hasn't changed to avoid unnecessary IO overheads.
So, advantage is that additional job can be removed, and disadvantage is: we have to manage
two BSP and Graph partitioning classes. - Edward J. Yoon''
-  * ''The partitions instead of being written to HDFS, which is creating a copy of input
files in HDFS Cluster (too costly I believe), should be written to local files and read from.
- Suraj Menon''
-   * ''If we want to run multiple jobs on same input, for example, friendship graph is input
and want to run PageRank job and SSSP job, ...., etc., reuse of partitions should be considered.
If partitions are written on local fs, metadata should be managed to reuse them. - Edward
J. Yoon''
- 
- In NoSQLs table input case (which supports range or random access by sorted key), partitions
doesn't need to be rewritten. In addition, Scanner instead of basic 'region' or 'tablet' splits
can be used for forcing the number of processors. 
  
   * Job Scheduler assigns Scanner or tablet with its partition ID to proper task, launch
the BSP job.
  

Mime
View raw message