Optimize Python foreach() to not return as many objects

1 files changed, 5 insertions, 1 deletions

diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
index 6efa61aa66..4aafe35d13 100644
--- a/python/pyspark/rdd.py
+++ b/python/pyspark/rdd.py
@@ -267,7 +267,11 @@ class RDD(object):
         >>> def f(x): print x
         >>> sc.parallelize([1, 2, 3, 4, 5]).foreach(f)
         """
-        self.map(f).collect()  # Force evaluation
+        def processPartition(iterator):
+            for x in iterator:
+                f(x)
+            yield None
+        self.mapPartitions(processPartition).collect()  # Force evaluation
 
     def collect(self):
         """