Tandoy opened a new issue #2668:
URL: https://github.com/apache/hudi/issues/2668
**Steps to reproduce the behavior:**
1. `spark-shell \
--packages org.apache.spark:spark-avro_2.11:2.4.0 \
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
--jars
/opt/apps/hudi/packaging/hudi-spark-bundle/target/hudi-spark-bundle_2.11-0.7.0.jar`
2.run spark code and insert data
import org.apache.hudi.QuickstartUtils._
import scala.collection.JavaConversions._
import org.apache.spark.sql.SaveMode._
import org.apache.hudi.DataSourceReadOptions._
import org.apache.hudi.DataSourceWriteOptions._
import org.apache.hudi.config.HoodieWriteConfig._
val tableName = "hudi_trips_cow"
val basePath = "file:///tmp/hudi_trips_cow"
val dataGen = new DataGenerator
val inserts = convertToStringList(dataGen.generateInserts(10))
val df = spark.read.json(spark.sparkContext.parallelize(inserts, 2))
df.write.format("org.apache.hudi").
options(getQuickstartWriteConfigs).
option(PRECOMBINE_FIELD_OPT_KEY, "ts").
option(RECORDKEY_FIELD_OPT_KEY, "uuid").
option(PARTITIONPATH_FIELD_OPT_KEY, "partitionpath").
option(TABLE_NAME, tableName).
mode(Overwrite).
save(basePath)
**Expected behavior**
Generate some new trips, load them into a DataFrame and write the
DataFrame into the Hudi table as below.
**Environment Description**
- Hudi version : 0.7.0
- Spark version : 2.4.0.cloudera2
- Hadoop version : 2.6.0-cdh5.13.3
- Hive version : 1.1.0-cdh5.13.3
- Storage (HDFS/S3/GCS..) : HDFS
- Running on Docker? (yes/no) :no
**Stacktrace**
` 21/03/12 15:49:08 WARN hudi.HoodieSparkSqlWriter$: hoodie table at
file:/tmp/hudi_trips_cow already exists. Deleting existing data & overwriting
with new data.
21/03/12 15:49:08 WARN util.NativeCodeLoader: Unable to load native-hadoop
library for your platform... using builtin-java classes where applicable
org.apache.hudi.exception.HoodieUpsertException: Failed to upsert for commit
time 20210312154907
at
org.apache.hudi.table.action.commit.AbstractWriteHelper.write(AbstractWriteHelper.java:62)
at
org.apache.hudi.table.action.commit.SparkUpsertCommitActionExecutor.execute(SparkUpsertCommitActionExecutor.java:46)
at
org.apache.hudi.table.HoodieSparkCopyOnWriteTable.upsert(HoodieSparkCopyOnWriteTable.java:92)
at
org.apache.hudi.table.HoodieSparkCopyOnWriteTable.upsert(HoodieSparkCopyOnWriteTable.java:82)
at
org.apache.hudi.client.SparkRDDWriteClient.upsert(SparkRDDWriteClient.java:146)
at
org.apache.hudi.DataSourceUtils.doWriteOperation(DataSourceUtils.java:214)
at
org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:181)
at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:134)
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$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at
org.apache.spark.sql.DataFrameWriter$$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$1.apply(SQLExecution.scala:78)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at
org.apache.spark.sql.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)
... 68 elided
Caused by: java.lang.NoClassDefFoundError:
org/apache/parquet/hadoop/metadata/CompressionCodecName
at java.lang.Class.getDeclaredMethods0(Native Method)
at java.lang.Class.privateGetDeclaredMethods(Class.java:2701)
at java.lang.Class.getDeclaredMethod(Class.java:2128)
at java.io.ObjectStreamClass.getPrivateMethod(ObjectStreamClass.java:1629)
at java.io.ObjectStreamClass.access$1700(ObjectStreamClass.java:79)
at java.io.ObjectStreamClass$3.run(ObjectStreamClass.java:520)
at java.io.ObjectStreamClass$3.run(ObjectStreamClass.java:494)
at java.security.AccessController.doPrivileged(Native Method)
at java.io.ObjectStreamClass.<init>(ObjectStreamClass.java:494)
at java.io.ObjectStreamClass.lookup(ObjectStreamClass.java:391)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1134)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1378)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1378)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at
org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:43)
at
org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:100)
at
org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:400)
at
org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:393)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:162)
at org.apache.spark.SparkContext.clean(SparkContext.scala:2326)
at org.apache.spark.rdd.RDD$$anonfun$flatMap$1.apply(RDD.scala:380)
at org.apache.spark.rdd.RDD$$anonfun$flatMap$1.apply(RDD.scala:379)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.flatMap(RDD.scala:379)
at
org.apache.spark.api.java.JavaRDDLike$class.flatMap(JavaRDDLike.scala:126)
at
org.apache.spark.api.java.AbstractJavaRDDLike.flatMap(JavaRDDLike.scala:45)
at
org.apache.hudi.client.common.HoodieSparkEngineContext.flatMap(HoodieSparkEngineContext.java:78)
at
org.apache.hudi.index.HoodieIndexUtils.getLatestBaseFilesForAllPartitions(HoodieIndexUtils.java:52)
at
org.apache.hudi.index.bloom.SparkHoodieBloomIndex.loadInvolvedFiles(SparkHoodieBloomIndex.java:169)
at
org.apache.hudi.index.bloom.SparkHoodieBloomIndex.lookupIndex(SparkHoodieBloomIndex.java:119)
at
org.apache.hudi.index.bloom.SparkHoodieBloomIndex.tagLocation(SparkHoodieBloomIndex.java:84)
at
org.apache.hudi.index.bloom.SparkHoodieBloomIndex.tagLocation(SparkHoodieBloomIndex.java:60)
at
org.apache.hudi.table.action.commit.AbstractWriteHelper.tag(AbstractWriteHelper.java:69)
at
org.apache.hudi.table.action.commit.AbstractWriteHelper.write(AbstractWriteHelper.java:51)
... 96 more
Caused by: java.lang.ClassNotFoundException:
org.apache.parquet.hadoop.metadata.CompressionCodecName
at java.net.URLClassLoader.findClass(URLClassLoader.java:382)
at java.lang.ClassLoader.loadClass(ClassLoader.java:418)
at java.lang.ClassLoader.loadClass(ClassLoader.java:351)
... 150 more`
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
