diff options
Diffstat (limited to 'python/pyspark/rdd.py')
-rw-r--r-- | python/pyspark/rdd.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 37574cea0b..cd1f64e8aa 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -2299,14 +2299,14 @@ class RDD(object): """ Return an iterator that contains all of the elements in this RDD. The iterator will consume as much memory as the largest partition in this RDD. + >>> rdd = sc.parallelize(range(10)) >>> [x for x in rdd.toLocalIterator()] [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] """ - for partition in range(self.getNumPartitions()): - rows = self.context.runJob(self, lambda x: x, [partition]) - for row in rows: - yield row + with SCCallSiteSync(self.context) as css: + port = self.ctx._jvm.PythonRDD.toLocalIteratorAndServe(self._jrdd.rdd()) + return _load_from_socket(port, self._jrdd_deserializer) def _prepare_for_python_RDD(sc, command): |