Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

  • If user specified partition function, internally, "partitioning job" is ran as a pre-processing step.
    • Each task of "partitioning job" reads its assigned data block and rewrite them to particular partition files.
    • Job Scheduler assigns partitions to proper task based on partition ID.
  • After pre-partitioning done, launch the BSP job.

  • 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 processorspre-processing step will be skipped because they supports range scan.

  • Job Scheduler assigns Scanner or tablet with its partition ID to proper task, launch the BSP job.

...