Github user felixcheung commented on a diff in the pull request:
https://github.com/apache/spark/pull/22011#discussion_r208122669
--- Diff: python/pyspark/rdd.py ---
@@ -2429,6 +2441,29 @@ def _wrap_function(sc, func, deserializer,
serializer, profiler=None):
sc.pythonVer, broadcast_vars,
sc._javaAccumulator)
+class RDDBarrier(object):
+
+ """
+ .. note:: Experimental
+
+ An RDDBarrier turns an RDD into a barrier RDD, which forces Spark to
launch tasks of the stage
+ contains this RDD together.
+ """
+
+ def __init__(self, rdd):
+ self.rdd = rdd
+ self._jrdd = rdd._jrdd
+
+ def mapPartitions(self, f, preservesPartitioning=False):
--- End diff --
docstring?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
