[SPARK-32784] java.lang.NoClassDefFoundError: parquet/hadoop/ParquetOutputFormat

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Incomplete
• Affects Version/s: 2.4.5
• Component/s: PySpark

Environment

Run Context ubuntu:16.04 in Docker for EKS

 

Python 3.5.2

Spark 2.4.5

hadoop 2.9.2

 

 

py4j-0.10.7.jar
parquet-column-1.10.1.jar
parquet-common-1.10.1.jar
parquet-encoding-1.10.1.jar
parquet-format-2.4.0.jar
parquet-hadoop-1.10.1.jar
parquet-jackson-1.10.1.jar

 

• Assignee: Unassigned
• Reporter: clock
• Created: 03/Sep/20 06:47
• Updated: 07/Sep/20 05:53
• Resolved: 07/Sep/20 05:49

Description

Code:

 

spark = SparkSession.builder \ 
        .master("yarn") \ 
        .enableHiveSupport() \ 
        .getOrCreate()
 
test_data_path = 's3a://ph-stream/common/public/prod/15' 
test_data_df = spark.read.parquet(test_data_path).limit(1)
 
test_data_df.write 
            .mode('overwrite') 
            .option('path', test_data_df) 
            .saveAsTable('prod15')

 

Error Info:

 

2020-09-03 14:31:47,900 WARN util.Utils: Truncated the string representation of a plan since it was too large. This behavior can be adjusted by setting 'spark.debug.maxToStringFields' in SparkEnv.conf.
Traceback (most recent call last):                                              
  File "main.py", line 82, in <module>
    test_data_df.write.mode('overwrite').option('path', test_data_path).saveAsTable('prod15')
  File "/usr/local/lib/python3.5/dist-packages/pyspark/sql/readwriter.py", line 778, in saveAsTable
    self._jwrite.saveAsTable(name)
  File "/usr/local/lib/python3.5/dist-packages/py4j/java_gateway.py", line 1257, in __call__
    answer, self.gateway_client, self.target_id, self.name)
  File "/usr/local/lib/python3.5/dist-packages/pyspark/sql/utils.py", line 63, in deco
    return f(*a, **kw)
  File "/usr/local/lib/python3.5/dist-packages/py4j/protocol.py", line 328, in get_return_value
    format(target_id, ".", name), value)
py4j.protocol.Py4JJavaError: An error occurred while calling o102.saveAsTable.
: java.lang.NoClassDefFoundError: parquet/hadoop/ParquetOutputFormat
        at java.lang.Class.forName0(Native Method)
        at java.lang.Class.forName(Class.java:348)
        at org.apache.spark.util.Utils$.classForName(Utils.scala:238)
        at org.apache.spark.sql.hive.client.HiveClientImpl$.org$apache$spark$sql$hive$client$HiveClientImpl$$toOutputFormat(HiveClientImpl.scala:915)
        at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$toHiveTable$8.apply(HiveClientImpl.scala:949)
        at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$toHiveTable$8.apply(HiveClientImpl.scala:949)
        at scala.Option.map(Option.scala:146)
        at org.apache.spark.sql.hive.client.HiveClientImpl$.toHiveTable(HiveClientImpl.scala:949)
        at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$createTable$1.apply$mcV$sp(HiveClientImpl.scala:484)
        at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$createTable$1.apply(HiveClientImpl.scala:482)
        at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$createTable$1.apply(HiveClientImpl.scala:482)
        at org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$withHiveState$1.apply(HiveClientImpl.scala:277)
        at org.apache.spark.sql.hive.client.HiveClientImpl.liftedTree1$1(HiveClientImpl.scala:215)
        at org.apache.spark.sql.hive.client.HiveClientImpl.retryLocked(HiveClientImpl.scala:214)
        at org.apache.spark.sql.hive.client.HiveClientImpl.withHiveState(HiveClientImpl.scala:260)
        at org.apache.spark.sql.hive.client.HiveClientImpl.createTable(HiveClientImpl.scala:482)
        at org.apache.spark.sql.hive.HiveExternalCatalog.saveTableIntoHive(HiveExternalCatalog.scala:499)
        at org.apache.spark.sql.hive.HiveExternalCatalog.org$apache$spark$sql$hive$HiveExternalCatalog$$createDataSourceTable(HiveExternalCatalog.scala:387)
        at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$createTable$1.apply$mcV$sp(HiveExternalCatalog.scala:263)
        at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$createTable$1.apply(HiveExternalCatalog.scala:236)
        at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$createTable$1.apply(HiveExternalCatalog.scala:236)
        at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:97)
        at org.apache.spark.sql.hive.HiveExternalCatalog.createTable(HiveExternalCatalog.scala:236)
        at org.apache.spark.sql.catalyst.catalog.ExternalCatalogWithListener.createTable(ExternalCatalogWithListener.scala:94)
        at org.apache.spark.sql.catalyst.catalog.SessionCatalog.createTable(SessionCatalog.scala:324)
        at org.apache.spark.sql.execution.command.CreateDataSourceTableAsSelectCommand.run(createDataSourceTables.scala:185)
        at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104)
        at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102)
        at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:122)
        at org.apache.spark.sql.execution.SparkPlan$$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.QueryExecution.toRdd$lzycompute(QueryExecution.scala:83)
        at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:81)
        at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676)
        at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676)
        at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:80)
        at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127)
        at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75)
        at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676)
        at org.apache.spark.sql.DataFrameWriter.createTable(DataFrameWriter.scala:474)
        at org.apache.spark.sql.DataFrameWriter.saveAsTable(DataFrameWriter.scala:453)
        at org.apache.spark.sql.DataFrameWriter.saveAsTable(DataFrameWriter.scala:409)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:498)
        at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
        at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
        at py4j.Gateway.invoke(Gateway.java:282)
        at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
        at py4j.commands.CallCommand.execute(CallCommand.java:79)
        at py4j.GatewayConnection.run(GatewayConnection.java:238)
        at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.ClassNotFoundException: parquet.hadoop.ParquetOutputFormat
        at java.net.URLClassLoader.findClass(URLClassLoader.java:382)
        at java.lang.ClassLoader.loadClass(ClassLoader.java:418)
        at org.apache.spark.sql.hive.client.IsolatedClientLoader$$anon$1.doLoadClass(IsolatedClientLoader.scala:226)
        at org.apache.spark.sql.hive.client.IsolatedClientLoader$$anon$1.loadClass(IsolatedClientLoader.scala:215)
        at java.lang.ClassLoader.loadClass(ClassLoader.java:351)
        ... 57 more