David Lacalle Castillo created HUDI-1063:
--------------------------------------------
Summary: Save in Google Cloud Storage not working
Key: HUDI-1063
URL: https://issues.apache.org/jira/browse/HUDI-1063
Project: Apache Hudi
Issue Type: Bug
Components: Spark Integration
Reporter: David Lacalle Castillo
I added to spark submit the following properties:
{{--packages
org.apache.hudi:hudi-spark-bundle_2.11:0.5.3,org.apache.spark:spark-avro_2.11:2.4.4
\ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'}}
Spark version 2.4.5 and Hadoop version 3.2.1
I am trying to save a Dataframe as follows in Google Cloud Storage as follows:
tableName = "forecasts"
basePath = "gs://hudi-datalake/" + tableName
hudi_options = {
'hoodie.table.name': tableName,
'hoodie.datasource.write.recordkey.field': 'uuid',
'hoodie.datasource.write.partitionpath.field': 'partitionpath',
'hoodie.datasource.write.table.name': tableName,
'hoodie.datasource.write.operation': 'insert',
'hoodie.datasource.write.precombine.field': 'ts',
'hoodie.upsert.shuffle.parallelism': 2,
'hoodie.insert.shuffle.parallelism': 2
}
results = results.selectExpr(
"ds as date",
"store",
"item",
"y as sales",
"yhat as sales_predicted",
"yhat_upper as sales_predicted_upper",
"yhat_lower as sales_predicted_lower",
"training_date")
results.write.format("hudi"). \
options(**hudi_options). \
mode("overwrite"). \
save(basePath)
I am getting the following error:
Py4JJavaError: An error occurred while calling o312.save. :
java.lang.NoSuchMethodError:
org.eclipse.jetty.server.session.SessionHandler.setHttpOnly(Z)V at
io.javalin.core.util.JettyServerUtil.defaultSessionHandler(JettyServerUtil.kt:50)
at io.javalin.Javalin.<init>(Javalin.java:94) at
io.javalin.Javalin.create(Javalin.java:107) at
org.apache.hudi.timeline.service.TimelineService.startService(TimelineService.java:102)
at
org.apache.hudi.client.embedded.EmbeddedTimelineService.startServer(EmbeddedTimelineService.java:74)
at
org.apache.hudi.client.AbstractHoodieClient.startEmbeddedServerView(AbstractHoodieClient.java:102)
at
org.apache.hudi.client.AbstractHoodieClient.<init>(AbstractHoodieClient.java:69)
at
org.apache.hudi.client.AbstractHoodieWriteClient.<init>(AbstractHoodieWriteClient.java:83)
at org.apache.hudi.client.HoodieWriteClient.<init>(HoodieWriteClient.java:137)
at org.apache.hudi.client.HoodieWriteClient.<init>(HoodieWriteClient.java:124)
at org.apache.hudi.client.HoodieWriteClient.<init>(HoodieWriteClient.java:120)
at org.apache.hudi.DataSourceUtils.createHoodieClient(DataSourceUtils.java:195)
at org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:135)
at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:108) at
org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86)
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.saveToV1Source(DataFrameWriter.scala:285)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271) at
org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:229) 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) (<class 'py4j.protocol.Py4JJavaError'>,
Py4JJavaError('An error occurred while calling o312.save.\n', JavaObject
id=o313), <traceback object at 0x7f33e56e6048>)
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
