You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Yin Huai (JIRA)" <ji...@apache.org> on 2016/11/21 18:17:58 UTC
[jira] [Comment Edited] (SPARK-15513) Bzip2Factory in Hadoop 2.7.1
is not thread safe
[ https://issues.apache.org/jira/browse/SPARK-15513?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15684302#comment-15684302 ]
Yin Huai edited comment on SPARK-15513 at 11/21/16 6:17 PM:
------------------------------------------------------------
I am closing this jira since the fix has been released with hadoop 2.7.2.
was (Author: yhuai):
I am closing this jira since the fix has been released with 2.7.2.
> Bzip2Factory in Hadoop 2.7.1 is not thread safe
> -----------------------------------------------
>
> Key: SPARK-15513
> URL: https://issues.apache.org/jira/browse/SPARK-15513
> Project: Spark
> Issue Type: Bug
> Components: Spark Core
> Environment: Hadoop 2.7.1
> Reporter: Yin Huai
>
> This is caused by https://issues.apache.org/jira/browse/HADOOP-12191. When we are loading the native bzip2 lib by one thread, other threads think that native bzip2 lib is not available and then throws exceptions.
> {code}
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 6.0 failed 1 times, most recent failure: Lost task 0.0 in stage 6.0 (TID 37, localhost): java.lang.UnsupportedOperationException
> at org.apache.hadoop.io.compress.bzip2.BZip2DummyCompressor.finished(BZip2DummyCompressor.java:48)
> at org.apache.hadoop.io.compress.CompressorStream.write(CompressorStream.java:65)
> at java.io.DataOutputStream.write(DataOutputStream.java:107)
> at org.apache.hadoop.mapred.TextOutputFormat$LineRecordWriter.writeObject(TextOutputFormat.java:81)
> at org.apache.hadoop.mapred.TextOutputFormat$LineRecordWriter.write(TextOutputFormat.java:102)
> at org.apache.spark.SparkHadoopWriter.write(SparkHadoopWriter.scala:95)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13$$anonfun$apply$7.apply$mcV$sp(PairRDDFunctions.scala:1205)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13$$anonfun$apply$7.apply(PairRDDFunctions.scala:1203)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13$$anonfun$apply$7.apply(PairRDDFunctions.scala:1203)
> at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1278)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13.apply(PairRDDFunctions.scala:1211)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13.apply(PairRDDFunctions.scala:1190)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
> at org.apache.spark.scheduler.Task.run(Task.scala:85)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Suppressed: java.lang.UnsupportedOperationException
> at org.apache.hadoop.io.compress.bzip2.BZip2DummyCompressor.finished(BZip2DummyCompressor.java:48)
> at org.apache.hadoop.io.compress.CompressorStream.finish(CompressorStream.java:89)
> at org.apache.hadoop.io.compress.CompressorStream.close(CompressorStream.java:106)
> at java.io.FilterOutputStream.close(FilterOutputStream.java:159)
> at org.apache.hadoop.mapred.TextOutputFormat$LineRecordWriter.close(TextOutputFormat.java:108)
> at org.apache.spark.SparkHadoopWriter.close(SparkHadoopWriter.scala:102)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13$$anonfun$apply$8.apply$mcV$sp(PairRDDFunctions.scala:1211)
> at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1296)
> ... 8 more
> Driver stacktrace:
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1450)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1438)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1437)
> at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1437)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
> at scala.Option.foreach(Option.scala:236)
> at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:811)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1659)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1618)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1607)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
> at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1863)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1876)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1896)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1219)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply(PairRDDFunctions.scala:1161)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply(PairRDDFunctions.scala:1161)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:357)
> at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopDataset(PairRDDFunctions.scala:1161)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply$mcV$sp(PairRDDFunctions.scala:1064)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply(PairRDDFunctions.scala:1030)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply(PairRDDFunctions.scala:1030)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:357)
> at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:1030)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$3.apply$mcV$sp(PairRDDFunctions.scala:1011)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$3.apply(PairRDDFunctions.scala:1011)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$3.apply(PairRDDFunctions.scala:1011)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:357)
> at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:1010)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$2.apply$mcV$sp(PairRDDFunctions.scala:968)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$2.apply(PairRDDFunctions.scala:966)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$2.apply(PairRDDFunctions.scala:966)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:357)
> at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:966)
> at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$2.apply$mcV$sp(RDD.scala:1448)
> at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$2.apply(RDD.scala:1436)
> at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$2.apply(RDD.scala:1436)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:357)
> at org.apache.spark.rdd.RDD.saveAsTextFile(RDD.scala:1436)
> Caused by: java.lang.UnsupportedOperationException
> at org.apache.hadoop.io.compress.bzip2.BZip2DummyCompressor.finished(BZip2DummyCompressor.java:48)
> at org.apache.hadoop.io.compress.CompressorStream.write(CompressorStream.java:65)
> at java.io.DataOutputStream.write(DataOutputStream.java:107)
> at org.apache.hadoop.mapred.TextOutputFormat$LineRecordWriter.writeObject(TextOutputFormat.java:81)
> at org.apache.hadoop.mapred.TextOutputFormat$LineRecordWriter.write(TextOutputFormat.java:102)
> at org.apache.spark.SparkHadoopWriter.write(SparkHadoopWriter.scala:95)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13$$anonfun$apply$7.apply$mcV$sp(PairRDDFunctions.scala:1205)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13$$anonfun$apply$7.apply(PairRDDFunctions.scala:1203)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13$$anonfun$apply$7.apply(PairRDDFunctions.scala:1203)
> at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1278)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13.apply(PairRDDFunctions.scala:1211)
> at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13.apply(PairRDDFunctions.scala:1190)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
> at org.apache.spark.scheduler.Task.run(Task.scala:85)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> {code}
> I am opening this jira to discuss how to workaround this issue in spark side.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org