Skip to content

[SPARK-6294] fix hang when call take() in JVM on PythonRDD #4987

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
wants to merge 1 commit into from
Closed

[SPARK-6294] fix hang when call take() in JVM on PythonRDD #4987

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
9 changes: 6 additions & 3 deletions core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,6 @@ private[spark] class PythonRDD(

context.addTaskCompletionListener { context =>
writerThread.shutdownOnTaskCompletion()
writerThread.join()
if (!reuse_worker || !released) {
try {
worker.close()
Expand Down Expand Up @@ -248,13 +247,17 @@ private[spark] class PythonRDD(
} catch {
case e: Exception if context.isCompleted || context.isInterrupted =>
logDebug("Exception thrown after task completion (likely due to cleanup)", e)
Utils.tryLog(worker.shutdownOutput())
if (!worker.isClosed) {
Utils.tryLog(worker.shutdownOutput())
}

case e: Exception =>
// We must avoid throwing exceptions here, because the thread uncaught exception handler
// will kill the whole executor (see org.apache.spark.executor.Executor).
_exception = e
Utils.tryLog(worker.shutdownOutput())
if (!worker.isClosed) {
Utils.tryLog(worker.shutdownOutput())
}
} finally {
// Release memory used by this thread for shuffles
env.shuffleMemoryManager.releaseMemoryForThisThread()
Expand Down
5 changes: 4 additions & 1 deletion python/pyspark/daemon.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,10 @@ def worker(sock):
except SystemExit as exc:
exit_code = compute_real_exit_code(exc.code)
finally:
outfile.flush()
try:
outfile.flush()
except Exception:
pass
return exit_code


Expand Down
5 changes: 5 additions & 0 deletions python/pyspark/tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -782,6 +782,11 @@ def test_narrow_dependency_in_join(self):
jobId = tracker.getJobIdsForGroup("test4")[0]
self.assertEqual(3, len(tracker.getJobInfo(jobId).stageIds))

# Regression test for SPARK-6294
def test_take_on_jrdd(self):
rdd = self.sc.parallelize(range(1 << 20)).map(lambda x: str(x))
rdd._jrdd.first()


class ProfilerTests(PySparkTestCase):

Expand Down