Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
/usr/local/Cellar/python/3.6.5/Frameworks/Python.framework/Versions/3.6/lib/python3.6/subprocess.py:766: ResourceWarning: subprocess 27563 is still running
ResourceWarning, source=self)
[Stage 0:> (0 + 1) / 1]objc[27586]: +[__NSPlaceholderDictionary initialize] may have been in progress in another thread when fork() was called.
objc[27586]: +[__NSPlaceholderDictionary initialize] may have been in progress in another thread when fork() was called. We cannot safely call it or ignore it in the fork() child process. Crashing instead. Set a breakpoint on objc_initializeAfterForkError to debug.
ERROR
======================================================================
ERROR: test_streaming_foreach_with_simple_function (pyspark.sql.tests.SQLTests)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/.../spark/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/.../spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
format(target_id, ".", name), value)
py4j.protocol.Py4JJavaError: An error occurred while calling o54.processAllAvailable.
: org.apache.spark.sql.streaming.StreamingQueryException: Writing job aborted.
=== Streaming Query ===
Identifier: [id = f508d634-407c-4232-806b-70e54b055c42, runId = 08d1435b-5358-4fb6-b167-811584a3163e]
Current Committed Offsets: {}
Current Available Offsets: {FileStreamSource[file:/var/folders/71/484zt4z10ks1vydt03bhp6hr0000gp/T/tmpolebys1s]: {"logOffset":0}}
Current State: ACTIVE
Thread State: RUNNABLE
Logical Plan:
FileStreamSource[file:/var/folders/71/484zt4z10ks1vydt03bhp6hr0000gp/T/tmpolebys1s]
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:295)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:189)
Caused by: org.apache.spark.SparkException: Writing job aborted.
at org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2Exec.scala:91)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:247)
at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:294)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:3384)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2783)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2783)
at org.apache.spark.sql.Dataset$$anonfun$53.apply(Dataset.scala:3365)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3364)
at org.apache.spark.sql.Dataset.collect(Dataset.scala:2783)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$5$$anonfun$apply$18.apply(MicroBatchExecution.scala:538)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$5.apply(MicroBatchExecution.scala:533)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:323)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch(MicroBatchExecution.scala:532)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply$mcV$sp(MicroBatchExecution.scala:195)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:163)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:163)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:323)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1.apply$mcZ$sp(MicroBatchExecution.scala:163)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:56)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:157)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:279)
... 1 more
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost, executor driver): org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$3.applyOrElse(PythonRunner.scala:485)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$3.applyOrElse(PythonRunner.scala:474)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:36)
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:592)
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:570)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:404)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at org.apache.spark.sql.execution.python.PythonForeachWriter.close(PythonForeachWriter.scala:66)
at org.apache.spark.sql.execution.streaming.sources.ForeachDataWriter.commit(ForeachWriteSupportProvider.scala:130)
at org.apache.spark.sql.execution.datasources.v2.DataWritingSparkTask$$anonfun$run$3.apply(WriteToDataSourceV2Exec.scala:125)
at org.apache.spark.sql.execution.datasources.v2.DataWritingSparkTask$$anonfun$run$3.apply(WriteToDataSourceV2Exec.scala:114)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1381)
at org.apache.spark.sql.execution.datasources.v2.DataWritingSparkTask$.run(WriteToDataSourceV2Exec.scala:144)
at org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec$$anonfun$doExecute$2.apply(WriteToDataSourceV2Exec.scala:66)
at org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec$$anonfun$doExecute$2.apply(WriteToDataSourceV2Exec.scala:65)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:121)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$8.apply(Executor.scala:372)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1347)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:378)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(DataInputStream.java:392)
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:577)
... 19 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1882)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1870)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1869)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1869)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:929)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:929)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:929)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2103)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2052)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2041)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:740)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2073)
at org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2Exec.scala:63)
... 35 more
Caused by: org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$3.applyOrElse(PythonRunner.scala:485)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$3.applyOrElse(PythonRunner.scala:474)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:36)
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:592)
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:570)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:404)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at org.apache.spark.sql.execution.python.PythonForeachWriter.close(PythonForeachWriter.scala:66)
at org.apache.spark.sql.execution.streaming.sources.ForeachDataWriter.commit(ForeachWriteSupportProvider.scala:130)
at org.apache.spark.sql.execution.datasources.v2.DataWritingSparkTask$$anonfun$run$3.apply(WriteToDataSourceV2Exec.scala:125)
at org.apache.spark.sql.execution.datasources.v2.DataWritingSparkTask$$anonfun$run$3.apply(WriteToDataSourceV2Exec.scala:114)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1381)
at org.apache.spark.sql.execution.datasources.v2.DataWritingSparkTask$.run(WriteToDataSourceV2Exec.scala:144)
at org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec$$anonfun$doExecute$2.apply(WriteToDataSourceV2Exec.scala:66)
at org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec$$anonfun$doExecute$2.apply(WriteToDataSourceV2Exec.scala:65)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:121)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$8.apply(Executor.scala:372)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1347)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:378)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(DataInputStream.java:392)
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:577)
... 19 more
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/.../spark/python/pyspark/sql/tests.py", line 1977, in test_streaming_foreach_with_simple_function
tester.run_streaming_query_on_writer(foreach_func, 2)
File "/.../spark/python/pyspark/sql/tests.py", line 1924, in run_streaming_query_on_writer
sq.processAllAvailable()
File "/.../spark/python/pyspark/sql/streaming.py", line 146, in processAllAvailable
return self._jsq.processAllAvailable()
File "/.../spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
answer, self.gateway_client, self.target_id, self.name)
File "/...d/spark/python/pyspark/sql/utils.py", line 75, in deco
raise StreamingQueryException(s.split(': ', 1)[1], stackTrace)
pyspark.sql.utils.StreamingQueryException: 'Writing job aborted.\n=== Streaming Query ===\nIdentifier: [id = f508d634-407c-4232-806b-70e54b055c42, runId = 08d1435b-5358-4fb6-b167-811584a3163e]\nCurrent Committed Offsets: {}\nCurrent Available Offsets: {FileStreamSource[file:/var/folders/71/484zt4z10ks1vydt03bhp6hr0000gp/T/tmpolebys1s]: {"logOffset":0}}\n\nCurrent State: ACTIVE\nThread State: RUNNABLE\n\nLogical Plan:\nFileStreamSource[file:/var/folders/71/484zt4z10ks1vydt03bhp6hr0000gp/T/tmpolebys1s]'
----------------------------------------------------------------------
Ran 1 test in 8.268s
FAILED (errors=1)
Bug
Major
