A possible bug? Must call persist to make code run

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

A possible bug? Must call persist to make code run

kwunlyou
I prepare a simple example (python) as follows to illustrate what I found:

- The code works well by calling a persist beforehand under all Spark
versions

- Without calling persist, the code works well under Spark 2.2.0 but doesn't
work under Spark 2.1.1 and Spark 2.1.2

- It really looks like a bug in Spark. Does anyone know which solved Spark
issues are related?


========================== CODE ==========================
from __future__ import absolute_import, division, print_function
import pyspark.sql.types as T
import pyspark.sql.functions as F

# 2.1.1, 2.1.2 doesn't work
# 2.2.0 works
print(spark.version)

df = spark.createDataFrame(
    [{'name': 'a', 'scores': ['1', '2']}, {'name': 'b', 'scores': None}],
    T.StructType(
        [T.StructField('name', T.StringType(), True),
T.StructField('scores', T.ArrayType(T.StringType()), True)]
    )
)

print(df.collect())
df.printSchema()

def loop_array(l):
    for e in l:
        pass
    return "pass"


# should work with persist
# tmp = df.filter(F.col('scores').isNotNull()).withColumn(
#     'new_col',
#     F.udf(loop_array)('scores')
# ).persist()

# won't work
tmp = df.filter(F.col('scores').isNotNull()).withColumn(
    'new_col',
    F.udf(loop_array)('scores')
)

print(tmp.collect())
tmp.filter(F.col('new_col').isNotNull()).count()
======================== CODE END ========================

====================== ERROR MESSAGE ======================
---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-9-572fb022ddab> in <module>()
----> 1 tmp.filter(F.col('new_col').isNotNull()).count()

/databricks/spark/python/pyspark/sql/dataframe.py in count(self)
    378         2
    379         """
--> 380         return int(self._jdf.count())
    381
    382     @ignore_unicode_prefix

/databricks/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py in
__call__(self, *args)
   1131         answer = self.gateway_client.send_command(command)
   1132         return_value = get_return_value(
-> 1133             answer, self.gateway_client, self.target_id, self.name)
   1134
   1135         for temp_arg in temp_args:

/databricks/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
     61     def deco(*a, **kw):
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:
     65             s = e.java_exception.toString()

/databricks/spark/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py in
get_return_value(answer, gateway_client, target_id, name)
    317                 raise Py4JJavaError(
    318                     "An error occurred while calling {0}{1}{2}.\n".
--> 319                     format(target_id, ".", name), value)
    320             else:
    321                 raise Py4JError(

Py4JJavaError: An error occurred while calling o235.count.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 3
in stage 2.0 failed 4 times, most recent failure: Lost task 3.3 in stage 2.0
(TID 14, 10.179.231.249, executor 0):
org.apache.spark.api.python.PythonException: Traceback (most recent call
last):
  File "/databricks/spark/python/pyspark/worker.py", line 171, in main
    process()
  File "/databricks/spark/python/pyspark/worker.py", line 166, in process
    serializer.dump_stream(func(split_index, iterator), outfile)
  File "/databricks/spark/python/pyspark/worker.py", line 103, in <lambda>
    func = lambda _, it: map(mapper, it)
  File "<string>", line 1, in <lambda>
  File "/databricks/spark/python/pyspark/worker.py", line 70, in <lambda>
    return lambda *a: f(*a)
  File "<ipython-input-6-bb6d09a4128f>", line 2, in loop_array
TypeError: 'NoneType' object is not iterable

    at
org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193)
    at
org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:234)
    at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152)
    at
org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1.apply(BatchEvalPythonExec.scala:144)
    at
org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1.apply(BatchEvalPythonExec.scala:87)
    at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:797)
    at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:797)
    at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
    at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
    at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
    at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
    at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
    at org.apache.spark.scheduler.Task.run(Task.scala:99)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322)
    at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:745)

Driver stacktrace:
    at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1442)
    at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1430)
    at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1429)
    at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
    at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1429)
    at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:803)
    at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:803)
    at scala.Option.foreach(Option.scala:257)
    at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:803)
    at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1657)
    at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1612)
    at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1601)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
    at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1937)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1950)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1963)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1977)
    at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:936)
    at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
    at org.apache.spark.rdd.RDD.collect(RDD.scala:935)
    at
org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:275)
    at
org.apache.spark.sql.Dataset$$anonfun$count$1.apply(Dataset.scala:2409)
    at
org.apache.spark.sql.Dataset$$anonfun$count$1.apply(Dataset.scala:2408)
    at org.apache.spark.sql.Dataset$$anonfun$60.apply(Dataset.scala:2791)
    at
org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:87)
    at
org.apache.spark.sql.execution.SQLExecution$.withFileAccessAudit(SQLExecution.scala:53)
    at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:70)
    at org.apache.spark.sql.Dataset.withAction(Dataset.scala:2790)
    at org.apache.spark.sql.Dataset.count(Dataset.scala:2408)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
    at py4j.Gateway.invoke(Gateway.java:280)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:214)
    at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most
recent call last):
  File "/databricks/spark/python/pyspark/worker.py", line 171, in main
    process()
  File "/databricks/spark/python/pyspark/worker.py", line 166, in process
    serializer.dump_stream(func(split_index, iterator), outfile)
  File "/databricks/spark/python/pyspark/worker.py", line 103, in <lambda>
    func = lambda _, it: map(mapper, it)
  File "<string>", line 1, in <lambda>
  File "/databricks/spark/python/pyspark/worker.py", line 70, in <lambda>
    return lambda *a: f(*a)
  File "<ipython-input-6-bb6d09a4128f>", line 2, in loop_array
TypeError: 'NoneType' object is not iterable

    at
org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193)
    at
org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:234)
    at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152)
    at
org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1.apply(BatchEvalPythonExec.scala:144)
    at
org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1.apply(BatchEvalPythonExec.scala:87)
    at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:797)
    at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$23.apply(RDD.scala:797)
    at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
    at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
    at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
    at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
    at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
    at org.apache.spark.scheduler.Task.run(Task.scala:99)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322)
    at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    ... 1 more
==================== ERROR MESSAGE END ====================




--
Sent from: http://apache-spark-user-list.1001560.n3.nabble.com/

---------------------------------------------------------------------
To unsubscribe e-mail: [hidden email]