[ https://issues.apache.org/jira/browse/HIVE-7916?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14175712#comment-14175712 ]
Suhas Satish commented on HIVE-7916: ------------------------------------ I also hit the following snappy lib exceptions - I am using snappy snappy-java-1.0.5.jar. Let me try upgrading to snappy 1.1.1.3 2014-10-17 16:18:01,977 ERROR [Executor task launch worker-0]: executor.Executor (Logging.scala:logError(96)) - Exception in task 0.0 in stage 0.0 (TID 0) org.xerial.snappy.SnappyError: [FAILED_TO_LOAD_NATIVE_LIBRARY] null at org.xerial.snappy.SnappyLoader.load(SnappyLoader.java:229) at org.xerial.snappy.Snappy.<clinit>(Snappy.java:44) at org.xerial.snappy.SnappyOutputStream.<init>(SnappyOutputStream.java:79) at org.apache.spark.io.SnappyCompressionCodec.compressedOutputStream(CompressionCodec.scala:125) at org.apache.spark.storage.BlockManager.wrapForCompression(BlockManager.scala:1083) at org.apache.spark.storage.BlockManager$$anonfun$7.apply(BlockManager.scala:579) at org.apache.spark.storage.BlockManager$$anonfun$7.apply(BlockManager.scala:579) at org.apache.spark.storage.DiskBlockObjectWriter.open(BlockObjectWriter.scala:126) at org.apache.spark.storage.DiskBlockObjectWriter.write(BlockObjectWriter.scala:192) at org.apache.spark.util.collection.ExternalSorter$$anonfun$writePartitionedFile$4$$anonfun$apply$2.apply(ExternalSorter.scala:732) at org.apache.spark.util.collection.ExternalSorter$$anonfun$writePartitionedFile$4$$anonfun$apply$2.apply(ExternalSorter.scala:731) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at org.apache.spark.util.collection.ExternalSorter$IteratorForPartition.foreach(ExternalSorter.scala:789) at org.apache.spark.util.collection.ExternalSorter$$anonfun$writePartitionedFile$4.apply(ExternalSorter.scala:731) at org.apache.spark.util.collection.ExternalSorter$$anonfun$writePartitionedFile$4.apply(ExternalSorter.scala:727) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at org.apache.spark.util.collection.ExternalSorter.writePartitionedFile(ExternalSorter.scala:727) at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:70) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:56) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:181) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) ---------- 2014-10-17 16:18:02,021 INFO [main]: scheduler.DAGScheduler (Logging.scala:logInfo(59)) - Job 0 failed: foreach at SparkPlan.java:80, took 3.389683 s 2014-10-17 16:18:02,021 ERROR [main]: spark.SparkClient (SparkClient.java:execute(166)) - Error executing Spark Plan 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): org.xerial.snappy.SnappyError: [FAILED_TO_LOAD_NATIVE_LIBRARY] null org.xerial.snappy.SnappyLoader.load(SnappyLoader.java:229) org.xerial.snappy.Snappy.<clinit>(Snappy.java:44) org.xerial.snappy.SnappyOutputStream.<init>(SnappyOutputStream.java:79) org.apache.spark.io.SnappyCompressionCodec.compressedOutputStream(CompressionCodec.scala:125) org.apache.spark.storage.BlockManager.wrapForCompression(BlockManager.scala:1083) org.apache.spark.storage.BlockManager$$anonfun$7.apply(BlockManager.scala:579) org.apache.spark.storage.BlockManager$$anonfun$7.apply(BlockManager.scala:579) org.apache.spark.storage.DiskBlockObjectWriter.open(BlockObjectWriter.scala:126) org.apache.spark.storage.DiskBlockObjectWriter.write(BlockObjectWriter.scala:192) org.apache.spark.util.collection.ExternalSorter$$anonfun$writePartitionedFile$4$$anonfun$apply$2.apply(ExternalSorter.scala:732) org.apache.spark.util.collection.ExternalSorter$$anonfun$writePartitionedFile$4$$anonfun$apply$2.apply(ExternalSorter.scala:731) scala.collection.Iterator$class.foreach(Iterator.scala:727) org.apache.spark.util.collection.ExternalSorter$IteratorForPartition.foreach(ExternalSorter.scala:789) org.apache.spark.util.collection.ExternalSorter$$anonfun$writePartitionedFile$4.apply(ExternalSorter.scala:731) org.apache.spark.util.collection.ExternalSorter$$anonfun$writePartitionedFile$4.apply(ExternalSorter.scala:727) scala.collection.Iterator$class.foreach(Iterator.scala:727) scala.collection.AbstractIterator.foreach(Iterator.scala:1157) org.apache.spark.util.collection.ExternalSorter.writePartitionedFile(ExternalSorter.scala:727) org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:70) org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68) org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) org.apache.spark.scheduler.Task.run(Task.scala:56) org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:181) java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1191) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1180) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1179) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1179) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:694) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:694) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:694) at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1397) at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498) at akka.actor.ActorCell.invoke(ActorCell.scala:456) at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237) at akka.dispatch.Mailbox.run(Mailbox.scala:219) at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386) at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339) at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107) > Snappy-java error when running hive query on spark [Spark Branch] > ----------------------------------------------------------------- > > Key: HIVE-7916 > URL: https://issues.apache.org/jira/browse/HIVE-7916 > Project: Hive > Issue Type: Bug > Components: Spark > Reporter: Xuefu Zhang > Labels: Spark-M1 > > Recently spark branch upgraded its dependency on Spark to 1.1.0-SNAPSHOT. > While the new version addressed some lib conflicts (such as guava), I'm > afraid that it also introduced new problems. The following might be one, when > I set the master URL to be a spark standalone cluster: > {code} > hive> set hive.execution.engine=spark; > hive> set spark.serializer=org.apache.spark.serializer.KryoSerializer; > hive> set spark.master=spark://xzdt:7077; > hive> select name, avg(value) from dec group by name; > 14/08/28 16:41:52 INFO storage.MemoryStore: Block broadcast_0 stored as > values in memory (estimated size 333.0 KB, free 128.0 MB) > java.lang.reflect.InvocationTargetException > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:601) > at org.xerial.snappy.SnappyLoader.loadNativeLibrary(SnappyLoader.java:317) > at org.xerial.snappy.SnappyLoader.load(SnappyLoader.java:219) > at org.xerial.snappy.Snappy.<clinit>(Snappy.java:44) > at org.xerial.snappy.SnappyOutputStream.<init>(SnappyOutputStream.java:79) > at > org.apache.spark.io.SnappyCompressionCodec.compressedOutputStream(CompressionCodec.scala:124) > at > org.apache.spark.broadcast.TorrentBroadcast$.blockifyObject(TorrentBroadcast.scala:207) > at > org.apache.spark.broadcast.TorrentBroadcast.writeBlocks(TorrentBroadcast.scala:83) > at > org.apache.spark.broadcast.TorrentBroadcast.<init>(TorrentBroadcast.scala:68) > at > org.apache.spark.broadcast.TorrentBroadcastFactory.newBroadcast(TorrentBroadcastFactory.scala:36) > at > org.apache.spark.broadcast.TorrentBroadcastFactory.newBroadcast(TorrentBroadcastFactory.scala:29) > at > org.apache.spark.broadcast.BroadcastManager.newBroadcast(BroadcastManager.scala:62) > at org.apache.spark.SparkContext.broadcast(SparkContext.scala:809) > at org.apache.spark.rdd.HadoopRDD.<init>(HadoopRDD.scala:116) > at org.apache.spark.SparkContext.hadoopRDD(SparkContext.scala:541) > at > org.apache.spark.api.java.JavaSparkContext.hadoopRDD(JavaSparkContext.scala:318) > at > org.apache.hadoop.hive.ql.exec.spark.SparkPlanGenerator.generateRDD(SparkPlanGenerator.java:160) > at > org.apache.hadoop.hive.ql.exec.spark.SparkPlanGenerator.generate(SparkPlanGenerator.java:88) > at > org.apache.hadoop.hive.ql.exec.spark.SparkClient.execute(SparkClient.java:156) > at > org.apache.hadoop.hive.ql.exec.spark.session.SparkSessionImpl.submit(SparkSessionImpl.java:52) > at > org.apache.hadoop.hive.ql.exec.spark.SparkTask.execute(SparkTask.java:77) > at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:161) > at > org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:85) > at org.apache.hadoop.hive.ql.Driver.launchTask(Driver.java:1537) > at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:1304) > at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1116) > at org.apache.hadoop.hive.ql.Driver.run(Driver.java:940) > at org.apache.hadoop.hive.ql.Driver.run(Driver.java:930) > at > org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:246) > at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:198) > at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:408) > at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:781) > at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:675) > at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:614) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:601) > at org.apache.hadoop.util.RunJar.main(RunJar.java:212) > Caused by: java.lang.UnsatisfiedLinkError: no snappyjava in java.library.path > at java.lang.ClassLoader.loadLibrary(ClassLoader.java:1860) > at java.lang.Runtime.loadLibrary0(Runtime.java:845) > at java.lang.System.loadLibrary(System.java:1084) > at > org.xerial.snappy.SnappyNativeLoader.loadLibrary(SnappyNativeLoader.java:52) > ... 42 more > org.xerial.snappy.SnappyError: [FAILED_TO_LOAD_NATIVE_LIBRARY] null > at org.xerial.snappy.SnappyLoader.load(SnappyLoader.java:229) > at org.xerial.snappy.Snappy.<clinit>(Snappy.java:44) > at org.xerial.snappy.SnappyOutputStream.<init>(SnappyOutputStream.java:79) > at > org.apache.spark.io.SnappyCompressionCodec.compressedOutputStream(CompressionCodec.scala:124) > at > org.apache.spark.broadcast.TorrentBroadcast$.blockifyObject(TorrentBroadcast.scala:207) > at > org.apache.spark.broadcast.TorrentBroadcast.writeBlocks(TorrentBroadcast.scala:83) > at > org.apache.spark.broadcast.TorrentBroadcast.<init>(TorrentBroadcast.scala:68) > at > org.apache.spark.broadcast.TorrentBroadcastFactory.newBroadcast(TorrentBroadcastFactory.scala:36) > at > org.apache.spark.broadcast.TorrentBroadcastFactory.newBroadcast(TorrentBroadcastFactory.scala:29) > at > org.apache.spark.broadcast.BroadcastManager.newBroadcast(BroadcastManager.scala:62) > at org.apache.spark.SparkContext.broadcast(SparkContext.scala:809) > at org.apache.spark.rdd.HadoopRDD.<init>(HadoopRDD.scala:116) > at org.apache.spark.SparkContext.hadoopRDD(SparkContext.scala:541) > at > org.apache.spark.api.java.JavaSparkContext.hadoopRDD(JavaSparkContext.scala:318) > at > org.apache.hadoop.hive.ql.exec.spark.SparkPlanGenerator.generateRDD(SparkPlanGenerator.java:160) > at > org.apache.hadoop.hive.ql.exec.spark.SparkPlanGenerator.generate(SparkPlanGenerator.java:88) > at > org.apache.hadoop.hive.ql.exec.spark.SparkClient.execute(SparkClient.java:156) > at > org.apache.hadoop.hive.ql.exec.spark.session.SparkSessionImpl.submit(SparkSessionImpl.java:52) > at > org.apache.hadoop.hive.ql.exec.spark.SparkTask.execute(SparkTask.java:77) > at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:161) > at > org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:85) > at org.apache.hadoop.hive.ql.Driver.launchTask(Driver.java:1537) > at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:1304) > at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1116) > at org.apache.hadoop.hive.ql.Driver.run(Driver.java:940) > at org.apache.hadoop.hive.ql.Driver.run(Driver.java:930) > at > org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:246) > at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:198) > at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:408) > at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:781) > at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:675) > at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:614) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:601) > at org.apache.hadoop.util.RunJar.main(RunJar.java:212) > FAILED: Execution Error, return code -101 from > org.apache.hadoop.hive.ql.exec.spark.SparkTask. > [FAILED_TO_LOAD_NATIVE_LIBRARY] null > 14/08/28 16:41:52 ERROR ql.Driver: FAILED: Execution Error, return code -101 > from org.apache.hadoop.hive.ql.exec.spark.SparkTask. > [FAILED_TO_LOAD_NATIVE_LIBRARY] null > {code} > It could be a setup issue. Nevertheless, we need to take a look to be sure. -- This message was sent by Atlassian JIRA (v6.3.4#6332)