[SPARK-20847] Error reading NULL int[] element from postgres -- null pointer exception. - ASF JIRA

XML

Word

Printable

JSON

Details

Type: Bug
Status: Resolved
Priority: Major
Resolution: Incomplete
Affects Version/s: 2.1.0
Fix Version/s: None
Component/s: SQL
Labels:
- bulk-closed

Description

– maybe fixed already? https://github.com/apache/spark/commit/f174cdc7478d0b81f9cfa896284a5ec4c6bb952d

def query_int_array():
    import pandas as pd
    from pyspark.sql import SQLContext

    user,password = ... , ....
    hostname = ....
    dbName = ...

    url = "jdbc:postgresql://{hostname}:5432/{dbName}".format(**locals())
    properties = {'user': user, 'password': password}

    sql_create = """DROP TABLE IF EXISTS public._df10;
CREATE TABLE IF NOT EXISTS public._df10 (
    id  integer,
        f_21 integer[]
);

INSERT INTO public._df10(id, f_21) VALUES
    (1, ARRAY[1,2])   --OK
   ,(2, ARRAY[3,NULL])  --OK
   ,(3, NULL)  --FAIL   *****<<<<< PROBLEM
;"""

    engine = sqlalchemy.create_engine('postgresql+psycopg2://{user}:{password}@{hostname}:5432/{dbName}'.format(**locals()))
    with engine.connect().execution_options(autocommit=True) as con:
        con.execute(sql_create)


    # Export postgres _df10 to spark as table df10
    sc = get_spark_context(master="local")
    sqlContext = SQLContext(sc)
    df10 = sqlContext.read.format("jdbc"). \
        option("url", url). \
        option("driver", "org.postgresql.Driver"). \
        option("useUnicode", "true"). \
        option("continueBatchOnError","true"). \
        option("useSSL", "false"). \
        option("user", user). \
        option("password", password). \
        option("dbtable", "_df10"). \
        load()
    df10.registerTempTable("df10")

    print "DF inferred from postgres:"
    df10.printSchema()
    df10.show()

    print "DF queried from postgres:"
    df10 = sqlContext.sql("select * from df10")
    df10.printSchema()
    df10.show()
    print df10.collect()

Explodes with:

DF inferred from postgres:
root
 |-- id: integer (nullable = true)
 |-- f_21: array (nullable = true)
 |    |-- element: integer (containsNull = true)

17/05/22 15:46:30 ERROR Executor: Exception in task 0.0 in stage 0.0 (TID 0)
java.lang.NullPointerException
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$13.apply(JdbcUtils.scala:427)
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$13.apply(JdbcUtils.scala:425)
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:286)
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:268)
	at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
	at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:32)
	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
	at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
	at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:377)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:231)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:225)
	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
	at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
	at org.apache.spark.scheduler.Task.run(Task.scala:99)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
	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)
17/05/22 15:46:30 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0, localhost, executor driver): java.lang.NullPointerException
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$13.apply(JdbcUtils.scala:427)
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$13.apply(JdbcUtils.scala:425)
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:286)
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:268)
	at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
	at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:32)
	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
	at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
	at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:377)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:231)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:225)
	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
	at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
	at org.apache.spark.scheduler.Task.run(Task.scala:99)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
	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)

17/05/22 15:46:30 ERROR TaskSetManager: Task 0 in stage 0.0 failed 1 times; aborting job
Traceback (most recent call last):
  File "/home/builder/.IdeaIC2017.1/config/plugins/python-ce/helpers/pydev/pydevd.py", line 1578, in <module>
    globals = debugger.run(setup['file'], None, None, is_module)
  File "/home/builder/.IdeaIC2017.1/config/plugins/python-ce/helpers/pydev/pydevd.py", line 1015, in run
    pydev_imports.execfile(file, globals, locals)  # execute the script
  File "/home/builder/runSparkTest.py", line 476, in <module>
    query_int_array()
  File "/home/builder/runSparkTest.py", line 381, in query_int_array
    df10.show()
  File "/usr/local/lib/python2.7/dist-packages/pyspark-2.1.0+hadoop2.7-py2.7.egg/pyspark/sql/dataframe.py", line 318, in show
    print(self._jdf.showString(n, 20))
  File "/usr/local/lib/python2.7/dist-packages/py4j/java_gateway.py", line 1133, in __call__
    answer, self.gateway_client, self.target_id, self.name)
  File "/usr/local/lib/python2.7/dist-packages/pyspark-2.1.0+hadoop2.7-py2.7.egg/pyspark/sql/utils.py", line 63, in deco
    return f(*a, **kw)
  File "/usr/local/lib/python2.7/dist-packages/py4j/protocol.py", line 319, in get_return_value
    format(target_id, ".", name), value)
py4j.protocol.Py4JJavaError: An error occurred while calling o37.showString.
: 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): java.lang.NullPointerException
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$13.apply(JdbcUtils.scala:427)
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$13.apply(JdbcUtils.scala:425)
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:286)
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:268)
	at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
	at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:32)
	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
	at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
	at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:377)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:231)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:225)
	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
	at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
	at org.apache.spark.scheduler.Task.run(Task.scala:99)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
	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$$failJobAndIndependentStages(DAGScheduler.scala:1435)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422)
	at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
	at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
	at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
	at scala.Option.foreach(Option.scala:257)
	at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594)
	at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
	at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1918)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1931)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1944)
	at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:333)
	at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
	at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2371)
	at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
	at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2765)
	at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2370)
	at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2377)
	at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2113)
	at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2112)
	at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2795)
	at org.apache.spark.sql.Dataset.head(Dataset.scala:2112)
	at org.apache.spark.sql.Dataset.take(Dataset.scala:2327)
	at org.apache.spark.sql.Dataset.showString(Dataset.scala:248)
	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: java.lang.NullPointerException
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$13.apply(JdbcUtils.scala:427)
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$org$apache$spark$sql$execution$datasources$jdbc$JdbcUtils$$makeGetter$13.apply(JdbcUtils.scala:425)
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:286)
	at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:268)
	at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
	at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:32)
	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
	at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
	at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:377)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:231)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:225)
	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
	at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
	at org.apache.spark.scheduler.Task.run(Task.scala:99)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
	... 1 more

Attachments

Activity

People

Assignee:: Unassigned

Reporter:: Stuart Reynolds

Votes:: 0 Vote for this issue

Watchers:: 3 Start watching this issue

Dates

Created:: 22/May/17 22:50

Updated:: 21/May/19 04:16

Resolved:: 21/May/19 04:16