Skip to content

[SPARK-40874][PYTHON] Fix broadcasts in Python UDFs when encryption enabled #38334

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
peter-toth wants to merge 1 commit into from
Closed

[SPARK-40874][PYTHON] Fix broadcasts in Python UDFs when encryption enabled #38334

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -403,6 +403,7 @@ private[spark] abstract class BasePythonRunner[IN, OUT](
// the decrypted data to python
val idsAndFiles = broadcastVars.flatMap { broadcast =>
if (!oldBids.contains(broadcast.id)) {
oldBids.add(broadcast.id)
Some((broadcast.id, broadcast.value.path))
} else {
None
Expand All @@ -416,7 +417,6 @@ private[spark] abstract class BasePythonRunner[IN, OUT](
idsAndFiles.foreach { case (id, _) =>
// send new broadcast
dataOut.writeLong(id)
oldBids.add(id)
}
dataOut.flush()
logTrace("waiting for python to read decrypted broadcast data from server")
Expand Down
14 changes: 14 additions & 0 deletions python/pyspark/tests/test_broadcast.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
from pyspark import SparkConf, SparkContext, Broadcast
from pyspark.java_gateway import launch_gateway
from pyspark.serializers import ChunkedStream
from pyspark.sql import SparkSession, Row


class BroadcastTest(unittest.TestCase):
Expand Down Expand Up @@ -126,6 +127,19 @@ def test_broadcast_for_error_condition(self):
with self.assertRaisesRegex(Py4JJavaError, "RuntimeError.*Broadcast.*unpersisted.*driver"):
self.sc.parallelize([1]).map(lambda x: bs.unpersist()).collect()

def test_broadcast_in_udfs_with_encryption(self):
conf = SparkConf()
conf.set("spark.io.encryption.enabled", "true")
conf.setMaster("local-cluster[2,1,1024]")
self.sc = SparkContext(conf=conf)
bar = {"a": "aa", "b": "bb"}
foo = self.sc.broadcast(bar)
spark = SparkSession(self.sc)
spark.udf.register("MYUDF", lambda x: foo.value[x] if x else "")
sel = spark.sql("SELECT MYUDF('a') AS a, MYUDF('b') AS b")
self.assertEqual(sel.collect(), [Row(a="aa", b="bb")])
spark.stop()


class BroadcastFrameProtocolTest(unittest.TestCase):
@classmethod
Expand Down