We try to upgrade Spark version for our application from Spark version 2.4.0 to 3.1.2 version. I tried Spark version 3.0.1, 3.0.3, 3.1.1 and 3.1.2. Spark version 3.0.1 and 3.0.3 work fine, but for 3.1.1 and 3.1.2, I got the following SparkException. I cannot find the class (org.apache.spark.sql.execution.columnar.CachedBatch) from any spark package. But I do find another similar class (org.apache.spark.sql.columnar.CachedBatch) (without execution in the class path) in package spark-sql_2.12-3.1.2.jar. Please let me how to get rid of the following exception. Thanks!
The following is the stacktrace when run our application:
org.apache.spark.SparkException: Failed to register classes with Kryo
at org.apache.spark.serializer.KryoSerializer.$anonfun$newKryo$5(KryoSerializer.scala:173)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.util.Utils$.withContextClassLoader(Utils.scala:222)
at org.apache.spark.serializer.KryoSerializer.newKryo(KryoSerializer.scala:161)
at org.apache.spark.serializer.KryoSerializer$$anon$1.create(KryoSerializer.scala:102)
at com.esotericsoftware.kryo.pool.KryoPoolQueueImpl.borrow(KryoPoolQueueImpl.java:48)
at org.apache.spark.serializer.KryoSerializer$PoolWrapper.borrow(KryoSerializer.scala:109)
at org.apache.spark.serializer.KryoSerializerInstance.borrowKryo(KryoSerializer.scala:336)
at org.apache.spark.serializer.KryoSerializationStream.<init>(KryoSerializer.scala:256)
at org.apache.spark.serializer.KryoSerializerInstance.serializeStream(KryoSerializer.scala:422)
at org.apache.spark.broadcast.TorrentBroadcast$.blockifyObject(TorrentBroadcast.scala:317)
at org.apache.spark.broadcast.TorrentBroadcast.writeBlocks(TorrentBroadcast.scala:138)
at org.apache.spark.broadcast.TorrentBroadcast.<init>(TorrentBroadcast.scala:91)
at org.apache.spark.broadcast.TorrentBroadcastFactory.newBroadcast(TorrentBroadcastFactory.scala:35)
at org.apache.spark.broadcast.BroadcastManager.newBroadcast(BroadcastManager.scala:77)
at org.apache.spark.SparkContext.broadcast(SparkContext.scala:1509)
at org.apache.spark.sql.execution.datasources.text.TextFileFormat.buildReader(TextFileFormat.scala:106)
at org.apache.spark.sql.execution.datasources.FileFormat.buildReaderWithPartitionValues(FileFormat.scala:130)
at org.apache.spark.sql.execution.datasources.FileFormat.buildReaderWithPartitionValues$(FileFormat.scala:121)
at org.apache.spark.sql.execution.datasources.TextBasedFileFormat.buildReaderWithPartitionValues(FileFormat.scala:170)
at org.apache.spark.sql.execution.FileSourceScanExec.inputRDD$lzycompute(DataSourceScanExec.scala:407)
at org.apache.spark.sql.execution.FileSourceScanExec.inputRDD(DataSourceScanExec.scala:398)
at org.apache.spark.sql.execution.FileSourceScanExec.doExecute(DataSourceScanExec.scala:485)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:180)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:218)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:215)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:176)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:132)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:131)
at org.apache.spark.sql.execution.datasources.json.TextInputJsonDataSource$.inferFromDataset(JsonDataSource.scala:104)
at org.apache.spark.sql.execution.datasources.json.TextInputJsonDataSource$.infer(JsonDataSource.scala:99)
at org.apache.spark.sql.execution.datasources.json.JsonDataSource.inferSchema(JsonDataSource.scala:65)
at org.apache.spark.sql.execution.datasources.json.JsonFileFormat.inferSchema(JsonFileFormat.scala:58)
at org.apache.spark.sql.execution.datasources.DataSource.$anonfun$getOrInferFileFormatSchema$11(DataSource.scala:209)
at scala.Option.orElse(Option.scala:447)
at org.apache.spark.sql.execution.datasources.DataSource.getOrInferFileFormatSchema(DataSource.scala:206)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:419)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:325)
at org.apache.spark.sql.DataFrameReader.$anonfun$load$3(DataFrameReader.scala:307)
at scala.Option.getOrElse(Option.scala:189)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:307)
at org.apache.spark.sql.DataFrameReader.json(DataFrameReader.scala:519)
at org.apache.spark.sql.DataFrameReader.json(DataFrameReader.scala:428)
at com.modeln.revvy.calcengine.spark.CMnSparkModelGenerator.loadJsonEntity(CMnSparkModelGenerator.java:545)
at com.modeln.revvy.calcengine.spark.CMnSparkModelGenerator.loadEntity(CMnSparkModelGenerator.java:316)
at com.modeln.revvy.calcengine.spark.CMnSparkModelGenerator.loadEntityDataFrames(CMnSparkModelGenerator.java:196)
at com.modeln.revvy.calcengine.spark.CMnSparkModelGenerator.generateAndRunSparkModel(CMnSparkModelGenerator.java:165)
at com.modeln.revvy.calcengine.spark.CMnCalcEngineDriver.main(CMnCalcEngineDriver.java:62)
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 org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:732)
**Caused by: java.lang.ClassNotFoundException: org.apache.spark.sql.execution.columnar.CachedBatch**
at java.net.URLClassLoader.findClass(URLClassLoader.java:387)
at java.lang.ClassLoader.loadClass(ClassLoader.java:418)
at java.lang.ClassLoader.loadClass(ClassLoader.java:351)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at org.apache.spark.util.Utils$.classForName(Utils.scala:209)
at org.apache.spark.serializer.KryoSerializer.$anonfun$newKryo$6(KryoSerializer.scala:164)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.serializer.KryoSerializer.$anonfun$newKryo$5(KryoSerializer.scala:163)
... 53 more
Related
I am trying to follow this guide https://spark.apache.org/docs/latest/quick-start.html (scala). However, I cant complete the last step when I'm supposed to submit the jar file to spark.
# Use spark-submit to run your application
$ YOUR_SPARK_HOME/bin/spark-submit \
--class "SimpleApp" \
--master local[4] \
target/scala-2.12/simple-project_2.12-1.0.jar
I get the following exception
Exception in thread "main" java.lang.BootstrapMethodError: java.lang.NoClassDefFoundError: scala/Serializable
at SimpleApp$.main(SimpleApp.scala:9)
at SimpleApp.main(SimpleApp.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:958)
at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1046)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1055)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.NoClassDefFoundError: scala/Serializable
... 14 more
Caused by: java.lang.ClassNotFoundException: scala.Serializable
at java.net.URLClassLoader.findClass(Unknown Source)
at java.lang.ClassLoader.loadClass(Unknown Source)
at java.lang.ClassLoader.loadClass(Unknown Source)
... 14 more
Any idea what is causing this?
You need to upgrade the dependencies to versions that are binary compatible to your Scala version.
Looks like 2.12 in this case.
I found the problem. I had the wrong Spark version installed. I had downloaded the "Pre-built for Apache Hadoop 3.3 and later (scala 2.13)" version. Installing the "Pre-built for Apache Hadoop 3.3 and later" spark version solved the problem.
I've Spark (2.4.4) Structure Streaming Job on Hortonworks (2.6.4), where I am reading messages from kafka topic , after schema validation streaming job is storing those messages into HBASE & HIVE.
After 6-7 hours of execution the Job dies because of STATUS_INVALID_HANDLE .
If I remove Hive Details, there is no such exception in the process.
The Path Mentioned below is already existing in HDFS.
Any Help on resolving this issue ??
Caused by: org.apache.hadoop.ipc.RemoteException(java.io.IOException): Unexpected error: STATUS_INVALID_HANDLE with path="/dev/projects/spark-checkpoint/hive/BLR_TOPIC_1-cash_blr_db_cash_streax_blr_table/offsets/.287.b53c5d5e-7f59-4aec-a6a7-015813d44b43.tmp", permission=666, clientname=DFSClient_NONMAPREDUCE_237312562_34
at org.apache.hadoop.ipc.Client.call(Client.java:1475)
at org.apache.hadoop.ipc.Client.call(Client.java:1412)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229)
at com.sun.proxy.$Proxy10.create(Unknown Source)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.create(ClientNamenodeProtocolTranslatorPB.java:296)
at sun.reflect.GeneratedMethodAccessor147.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:191)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102)
at com.sun.proxy.$Proxy11.create(Unknown Source)
at org.apache.hadoop.hdfs.DFSOutputStream.newStreamForCreate(DFSOutputStream.java:1648)
at org.apache.hadoop.hdfs.DFSClient.primitiveCreate(DFSClient.java:1750)
at org.apache.hadoop.fs.Hdfs.createInternal(Hdfs.java:102)
at org.apache.hadoop.fs.Hdfs.createInternal(Hdfs.java:58)
at org.apache.hadoop.fs.AbstractFileSystem.create(AbstractFileSystem.java:584)
at org.apache.hadoop.fs.FileContext$3.next(FileContext.java:686)
at org.apache.hadoop.fs.FileContext$3.next(FileContext.java:682)
at org.apache.hadoop.fs.FSLinkResolver.resolve(FSLinkResolver.java:90)
at org.apache.hadoop.fs.FileContext.create(FileContext.java:688)
at org.apache.spark.sql.execution.streaming.FileContextBasedCheckpointFileManager.createTempFile(CheckpointFileManager.scala:311)
at org.apache.spark.sql.execution.streaming.CheckpointFileManager$RenameBasedFSDataOutputStream.<init>(CheckpointFileManager.scala:133)
at org.apache.spark.sql.execution.streaming.CheckpointFileManager$RenameBasedFSDataOutputStream.<init>(CheckpointFileManager.scala:136)
at org.apache.spark.sql.execution.streaming.FileContextBasedCheckpointFileManager.createAtomic(CheckpointFileManager.scala:318)
at org.apache.spark.sql.execution.streaming.HDFSMetadataLog.org$apache$spark$sql$execution$streaming$HDFSMetadataLog$$writeBatchToFile(HDFSMetadataLog.scala:123)
at org.apache.spark.sql.execution.streaming.HDFSMetadataLog$$anonfun$add$1.apply$mcZ$sp(HDFSMetadataLog.scala:112)
at org.apache.spark.sql.execution.streaming.HDFSMetadataLog$$anonfun$add$1.apply(HDFSMetadataLog.scala:110)
at org.apache.spark.sql.execution.streaming.HDFSMetadataLog$$anonfun$add$1.apply(HDFSMetadataLog.scala:110)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.sql.execution.streaming.HDFSMetadataLog.add(HDFSMetadataLog.scala:110)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1$$anonfun$apply$mcZ$sp$3.apply$mcV$sp(MicroBatchExecution.scala:382)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1$$anonfun$apply$mcZ$sp$3.apply(MicroBatchExecution.scala:381)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1$$anonfun$apply$mcZ$sp$3.apply(MicroBatchExecution.scala:381)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:351)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1.apply$mcZ$sp(MicroBatchExecution.scala:381)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1.apply(MicroBatchExecution.scala:337)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1.apply(MicroBatchExecution.scala:337)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.withProgressLocked(MicroBatchExecution.scala:557)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch(MicroBatchExecution.scala:337)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply$mcV$sp(MicroBatchExecution.scala:183)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:166)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:166)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:351)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1.apply$mcZ$sp(MicroBatchExecution.scala:166)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:56)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:160)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:281) ```
We tried Running the same on couple of spark versions like 2.2.0 , 2.4.0 , 2.4.6.
Spark 2.4.6 serve my purpose , I'm not seeing STATUS_INVALID_HANDLE exception.
Cluster configuration:
Hadoop: CDH-6.2.1
Spark: 2.4.0
Hbase: 2.0
What I do: Read HBase data through Spark
When I use IntelliJ and local mode everything works fine, but when I change mode to
spark-submit --master yarn, the following stacktrace happens:
20/05/20 11:00:46 ERROR mapreduce.TableInputFormat: java.io.IOException: java.lang.reflect.InvocationTargetException
at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:221)
at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:114)
at org.apache.hadoop.hbase.mapreduce.TableInputFormat.initialize(TableInputFormat.java:200)
at org.apache.hadoop.hbase.mapreduce.TableInputFormatBase.getSplits(TableInputFormatBase.java:243)
at org.apache.hadoop.hbase.mapreduce.TableInputFormat.getSplits(TableInputFormat.java:254)
at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:131)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2146)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:945)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.collect(RDD.scala:944)
at com.song.HbaseOnSpark1$.main(HbaseOnSpark1.scala:32)
at com.song.HbaseOnSpark1.main(HbaseOnSpark1.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:673)
Caused by: java.lang.reflect.InvocationTargetException
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:219)
... 27 more
Caused by: java.lang.NullPointerException
at org.apache.hadoop.hbase.client.ConnectionImplementation.close(ConnectionImplementation.java:1938)
at org.apache.hadoop.hbase.client.ConnectionImplementation.<init>(ConnectionImplementation.java:310)
... 32 more
20/05/20 11:00:46 ERROR yarn.ApplicationMaster: User class threw exception: java.io.IOException: Cannot create a record reader because of a previous error. Please look at the previous logs lines from the task's full log for more details.
java.io.IOException: Cannot create a record reader because of a previous error. Please look at the previous logs lines from the task's full log for more details.
at org.apache.hadoop.hbase.mapreduce.TableInputFormatBase.getSplits(TableInputFormatBase.java:254)
at org.apache.hadoop.hbase.mapreduce.TableInputFormat.getSplits(TableInputFormat.java:254)
at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:131)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2146)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:945)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.collect(RDD.scala:944)
at com.song.HbaseOnSpark1$.main(HbaseOnSpark1.scala:32)
at com.song.HbaseOnSpark1.main(HbaseOnSpark1.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:673)
Caused by: java.lang.IllegalStateException: The input format instance has not been properly initialized. Ensure you call initializeTable either in your constructor or initialize method
at org.apache.hadoop.hbase.mapreduce.TableInputFormatBase.getTable(TableInputFormatBase.java:558)
at org.apache.hadoop.hbase.mapreduce.TableInputFormatBase.getSplits(TableInputFormatBase.java:249)
... 24 more
This is my code:
val conf: SparkConf = new SparkConf().setAppName("spark1")
val spark = new SparkContext(conf)
val hbaseConf: Configuration = HBaseConfiguration.create()
hbaseConf.set("hbase.zookeeper.quorum","hadoop01,hadoop02,hadoop03")
hbaseConf.set(TableInputFormat.INPUT_TABLE,"idx_name")
hbaseConf.set("hbase.defaults.for.version.skip", "true")
val rdd: RDD[(ImmutableBytesWritable, Result)] = spark.newAPIHadoopRDD(
hbaseConf,
classOf[TableInputFormat],
classOf[ImmutableBytesWritable],
classOf[Result]
)
its hbase classpatth issue in your cluster but you need to add hbase jars to your classpath like this
export SPARK_CLASSPATH=$SPARK_CLASSPATH:`hbase classpath`
hbase classpath will give all the jars for hbase connections and etc....
Why its working in local mode ?
Since all the jars required are there in ide lib
If you are using maven do a mvn depdency:tree to understand what jars are needed in the cluster. based on that you can adjust your spark-submit script.
if you are using --jars option see that all jars passed correctly or uber jar has correct dependencies when packing jar..
There might be jar conflict also check that carefully with local mode environment since thats working fine.
Further reading Spark spark-submit --jars arguments wants comma list, how to declare a directory of jars?
I am trying to save a model learning to S3 from my Spark Standalone cluster. But I have this error :
java.util.ServiceConfigurationError: org.apache.hadoop.fs.FileSystem: Provider org.apache.hadoop.fs.s3a.S3AFileSystem could not be instantiated
at java.util.ServiceLoader.fail(ServiceLoader.java:232)
at java.util.ServiceLoader.access$100(ServiceLoader.java:185)
at java.util.ServiceLoader$LazyIterator.nextService(ServiceLoader.java:384)
at java.util.ServiceLoader$LazyIterator.next(ServiceLoader.java:404)
at java.util.ServiceLoader$1.next(ServiceLoader.java:480)
at org.apache.hadoop.fs.FileSystem.loadFileSystems(FileSystem.java:2631)
at org.apache.hadoop.fs.FileSystem.getFileSystemClass(FileSystem.java:2650)
at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:2667)
at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:94)
at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:2703)
at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:2685)
at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:373)
at org.apache.spark.util.Utils$.getHadoopFileSystem(Utils.scala:1853)
at org.apache.spark.scheduler.EventLoggingListener.<init>(EventLoggingListener.scala:68)
at org.apache.spark.SparkContext.<init>(SparkContext.scala:529)
at ALS$.main(ALS.scala:32)
at ALS.main(ALS.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:775)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:119)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.NoClassDefFoundError: com/amazonaws/event/ProgressListener
at java.lang.Class.getDeclaredConstructors0(Native Method)
at java.lang.Class.privateGetDeclaredConstructors(Class.java:2671)
at java.lang.Class.getConstructor0(Class.java:3075)
at java.lang.Class.newInstance(Class.java:412)
at java.util.ServiceLoader$LazyIterator.nextService(ServiceLoader.java:380)
... 23 more
Caused by: java.lang.ClassNotFoundException:com.amazonaws.event.ProgressListener
at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:338)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
... 28 more
I have added Hadoop-aws aws-sdk in extraClassPath in spark-defaults.conf
What I have tried so far : I send my spark-submit with a fat jar compiled by sbt assembly (I have also added those dependencies in the sbt). My AWS Credentials are exported in the master environnement
Any idea on where I need to explore to fix this ?
Thanks !
That's an aws class, so you are going to need to make sure your CP has *the exact set of aws-java JARs your hadoop-aws JAR was built against.
mvnrepository lists those dependencies.
I have a project whose whole aim in life is to work out WTF is wrong with blobstore connector bindings, cloudstore. You can use that in spark-shell or real spark queries to help diagnose things.
After quite some time, can't figure out how to identify root cause of below error when running spark-sql binary:
15/12/08 14:48:41 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Exception in thread "main" java.lang.RuntimeException: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.metastore.HiveMetaStoreClient
at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:346)
at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:109)
at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
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:497)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:665)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:170)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:193)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:112)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.metastore.HiveMetaStoreClient
at org.apache.hadoop.hive.metastore.MetaStoreUtils.newInstance(MetaStoreUtils.java:1412)
at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.<init>(RetryingMetaStoreClient.java:62)
at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.getProxy(RetryingMetaStoreClient.java:72)
at org.apache.hadoop.hive.ql.metadata.Hive.createMetaStoreClient(Hive.java:2453)
at org.apache.hadoop.hive.ql.metadata.Hive.getMSC(Hive.java:2465)
at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:340)
... 11 more
Caused by: java.lang.reflect.InvocationTargetException
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:422)
at org.apache.hadoop.hive.metastore.MetaStoreUtils.newInstance(MetaStoreUtils.java:1410)
... 16 more
Caused by: javax.jdo.JDOFatalUserException: Class org.datanucleus.api.jdo.JDOPersistenceManagerFactory was not found.
NestedThrowables:
java.lang.ClassNotFoundException: org.datanucleus.api.jdo.JDOPersistenceManagerFactory
at javax.jdo.JDOHelper.invokeGetPersistenceManagerFactoryOnImplementation(JDOHelper.java:1175)
at javax.jdo.JDOHelper.getPersistenceManagerFactory(JDOHelper.java:808)
at javax.jdo.JDOHelper.getPersistenceManagerFactory(JDOHelper.java:701)
at org.apache.hadoop.hive.metastore.ObjectStore.getPMF(ObjectStore.java:310)
at org.apache.hadoop.hive.metastore.ObjectStore.getPersistenceManager(ObjectStore.java:339)
at org.apache.hadoop.hive.metastore.ObjectStore.initialize(ObjectStore.java:248)
at org.apache.hadoop.hive.metastore.ObjectStore.setConf(ObjectStore.java:223)
at org.apache.hadoop.util.ReflectionUtils.setConf(ReflectionUtils.java:73)
at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:133)
at org.apache.hadoop.hive.metastore.RawStoreProxy.<init>(RawStoreProxy.java:58)
at org.apache.hadoop.hive.metastore.RawStoreProxy.getProxy(RawStoreProxy.java:67)
at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.newRawStore(HiveMetaStore.java:497)
at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.getMS(HiveMetaStore.java:475)
at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.createDefaultDB(HiveMetaStore.java:523)
at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.init(HiveMetaStore.java:397)
at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.<init>(HiveMetaStore.java:356)
at org.apache.hadoop.hive.metastore.RetryingHMSHandler.<init>(RetryingHMSHandler.java:54)
at org.apache.hadoop.hive.metastore.RetryingHMSHandler.getProxy(RetryingHMSHandler.java:59)
at org.apache.hadoop.hive.metastore.HiveMetaStore.newHMSHandler(HiveMetaStore.java:4944)
at org.apache.hadoop.hive.metastore.HiveMetaStoreClient.<init>(HiveMetaStoreClient.java:171)
... 21 more
Caused by: java.lang.ClassNotFoundException: org.datanucleus.api.jdo.JDOPersistenceManagerFactory
at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at javax.jdo.JDOHelper$18.run(JDOHelper.java:2018)
at javax.jdo.JDOHelper$18.run(JDOHelper.java:2016)
at java.security.AccessController.doPrivileged(Native Method)
at javax.jdo.JDOHelper.forName(JDOHelper.java:2015)
at javax.jdo.JDOHelper.invokeGetPersistenceManagerFactoryOnImplementation(JDOHelper.java:1162)
... 40 more
You are missing datanucleus-api-jdo.jar in your class path. This jar is used by hive. Try to figure out which version of this jar you need (probably latest will do). You can download it then from here: http://repo1.maven.org/maven2/org/datanucleus/datanucleus-api-jdo/
And add it to hive permanently by adding this to your .hiverc file:
add jar datanucleus-api-jdo.jar
For spark versions > 2.0, you can approach below solutions:
Make sure the $HIVE_HOME/conf/hive-site.xml configuration which is pointing to complete path of metastore.
javax.jdo.option.ConnectionURL
jdbc:derby:;databaseName=/home/hive/metastore_db;create=true
JDBC connect string for a JDBC metastore
Place the hive-site.xml file in $SPARK_HOME/confto point SparkR to the same metastore as Hive Hope this solves your issue.