[
https://issues.apache.org/jira/browse/HADOOP-13857?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15715282#comment-15715282
]
Steve Loughran commented on HADOOP-13857:
-----------------------------------------
before
{code}
2016-12-02 11:59:22,623 [JobGenerator] WARN dstream.FileInputDStream
(Logging.scala:logWarning(87)) - Error finding new files
org.apache.hadoop.fs.s3a.AWSClientIOException: getFileStatus on
s3a://hwdev-steve-new/spark-cloud/S3AStreamingSuite/streaming/streaming:
com.amazonaws.AbortedException: :
at
org.apache.hadoop.fs.s3a.S3AUtils.translateException(S3AUtils.java:116)
at
org.apache.hadoop.fs.s3a.S3AUtils.translateException(S3AUtils.java:93)
at
org.apache.hadoop.fs.s3a.S3AFileSystem.getFileStatus(S3AFileSystem.java:1636)
at
org.apache.hadoop.fs.s3a.S3AFileSystem.innerListStatus(S3AFileSystem.java:1427)
at
org.apache.hadoop.fs.s3a.S3AFileSystem.listStatus(S3AFileSystem.java:1403)
at org.apache.hadoop.fs.Globber.listStatus(Globber.java:76)
at org.apache.hadoop.fs.Globber.doGlob(Globber.java:234)
at org.apache.hadoop.fs.Globber.glob(Globber.java:148)
at org.apache.hadoop.fs.FileSystem.globStatus(FileSystem.java:1978)
at
org.apache.hadoop.fs.s3a.S3AFileSystem.globStatus(S3AFileSystem.java:2119)
at
org.apache.spark.streaming.dstream.FileInputDStream.findNewFiles(FileInputDStream.scala:205)
at
org.apache.spark.streaming.dstream.FileInputDStream.compute(FileInputDStream.scala:149)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341)
at
org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:416)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:336)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:334)
at scala.Option.orElse(Option.scala:289)
at
org.apache.spark.streaming.dstream.DStream.getOrCompute(DStream.scala:331)
at
org.apache.spark.streaming.dstream.MappedDStream.compute(MappedDStream.scala:36)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341)
at
org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:416)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:336)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:334)
at scala.Option.orElse(Option.scala:289)
at
org.apache.spark.streaming.dstream.DStream.getOrCompute(DStream.scala:331)
at
org.apache.spark.streaming.dstream.FilteredDStream.compute(FilteredDStream.scala:36)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341)
at
org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:416)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:336)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:334)
at scala.Option.orElse(Option.scala:289)
at
org.apache.spark.streaming.dstream.DStream.getOrCompute(DStream.scala:331)
at
org.apache.spark.streaming.dstream.MappedDStream.compute(MappedDStream.scala:36)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341)
at
org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:416)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:336)
at
org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:334)
at scala.Option.orElse(Option.scala:289)
at
org.apache.spark.streaming.dstream.DStream.getOrCompute(DStream.scala:331)
at
org.apache.spark.streaming.dstream.ForEachDStream.generateJob(ForEachDStream.scala:48)
at
org.apache.spark.streaming.DStreamGraph$$anonfun$1.apply(DStreamGraph.scala:117)
at
org.apache.spark.streaming.DStreamGraph$$anonfun$1.apply(DStreamGraph.scala:116)
at
scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241)
at
scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at
scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:241)
at scala.collection.AbstractTraversable.flatMap(Traversable.scala:104)
at
org.apache.spark.streaming.DStreamGraph.generateJobs(DStreamGraph.scala:116)
at
org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$3.apply(JobGenerator.scala:249)
at
org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$3.apply(JobGenerator.scala:247)
at scala.util.Try$.apply(Try.scala:192)
at
org.apache.spark.streaming.scheduler.JobGenerator.generateJobs(JobGenerator.scala:247)
at
org.apache.spark.streaming.scheduler.JobGenerator.org$apache$spark$streaming$scheduler$JobGenerator$$processEvent(JobGenerator.scala:183)
at
org.apache.spark.streaming.scheduler.JobGenerator$$anon$1.onReceive(JobGenerator.scala:89)
at
org.apache.spark.streaming.scheduler.JobGenerator$$anon$1.onReceive(JobGenerator.scala:88)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
Caused by: com.amazonaws.AbortedException:
at
com.amazonaws.http.AmazonHttpClient$RequestExecutor.handleInterruptedException(AmazonHttpClient.java:710)
at
com.amazonaws.http.AmazonHttpClient$RequestExecutor.execute(AmazonHttpClient.java:620)
at
com.amazonaws.http.AmazonHttpClient$RequestExecutor.access$300(AmazonHttpClient.java:586)
at
com.amazonaws.http.AmazonHttpClient$RequestExecutionBuilderImpl.execute(AmazonHttpClient.java:573)
at
com.amazonaws.http.AmazonHttpClient.execute(AmazonHttpClient.java:445)
at
com.amazonaws.services.s3.AmazonS3Client.invoke(AmazonS3Client.java:4041)
at
com.amazonaws.services.s3.AmazonS3Client.getObjectMetadata(AmazonS3Client.java:1175)
at
com.amazonaws.services.s3.AmazonS3Client.getObjectMetadata(AmazonS3Client.java:1150)
at
org.apache.hadoop.fs.s3a.S3AFileSystem.getObjectMetadata(S3AFileSystem.java:940)
at
org.apache.hadoop.fs.s3a.S3AFileSystem.getFileStatus(S3AFileSystem.java:1616)
... 70 more
Caused by: com.amazonaws.http.timers.client.SdkInterruptedException
at
com.amazonaws.http.AmazonHttpClient$RequestExecutor.checkInterrupted(AmazonHttpClient.java:754)
at
com.amazonaws.http.AmazonHttpClient$RequestExecutor.checkInterrupted(AmazonHttpClient.java:740)
at
com.amazonaws.http.AmazonHttpClient$RequestExecutor.executeHelper(AmazonHttpClient.java:919)
at
com.amazonaws.http.AmazonHttpClient$RequestExecutor.doExecute(AmazonHttpClient.java:661)
at
com.amazonaws.http.AmazonHttpClient$RequestExecutor.executeWithTimer(AmazonHttpClient.java:635)
at
com.amazonaws.http.AmazonHttpClient$RequestExecutor.execute(AmazonHttpClient.java:618)
... 78 more
{code}
> S3AUtils.translateException to map (wrapped) InterruptedExceptions to
> InterruptedIOEs
> -------------------------------------------------------------------------------------
>
> Key: HADOOP-13857
> URL: https://issues.apache.org/jira/browse/HADOOP-13857
> Project: Hadoop Common
> Issue Type: Sub-task
> Components: fs/s3
> Affects Versions: 2.8.0
> Reporter: Steve Loughran
> Assignee: Steve Loughran
>
> Currently {{S3AUtils.translateException}} doesn't recognise interruptions; it
> just sees an AmazonClientException chain which is then relayed up.
> Proposed: look for an {{InterruptedIOException}} at the base of the chain of
> exceptions, map it to an {{InterruptedIOException}}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
