You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@giraph.apache.org by Avery Ching <av...@gmail.com> on 2012/10/27 17:14:16 UTC

Review Request: GIRAPH-389 Multithreading should intelligently allocate the thread pools

-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/7754/
-----------------------------------------------------------

Review request for giraph.


Description
-------

Do not create more input split loading threads than input splits to allow workers to equally load up input splits
Do not create more compute threads than partitions on the worker
Removed duplicate reserveInputSplit method in BspServiceWorker
Minor optimization to only get the input split zknodes once and pass to all threads.


This addresses bug GIRAPH-389.
    https://issues.apache.org/jira/browse/GIRAPH-389


Diffs
-----

  http://svn.apache.org/repos/asf/giraph/trunk/giraph/src/main/java/org/apache/giraph/graph/BspServiceWorker.java 1402363 
  http://svn.apache.org/repos/asf/giraph/trunk/giraph/src/main/java/org/apache/giraph/graph/GraphMapper.java 1402363 
  http://svn.apache.org/repos/asf/giraph/trunk/giraph/src/main/java/org/apache/giraph/graph/InputSplitPathOrganizer.java 1402363 
  http://svn.apache.org/repos/asf/giraph/trunk/giraph/src/main/java/org/apache/giraph/graph/InputSplitsCallable.java 1402363 

Diff: https://reviews.apache.org/r/7754/diff/


Testing
-------

passed unittests
ran pagerankbenchmark on a real cluster and observed that the limiting works


Thanks,

Avery Ching