You are viewing a plain text version of this content. The canonical link for it is here.
Posted to common-issues@hadoop.apache.org by "Cheng Wei (Jira)" <ji...@apache.org> on 2020/09/24 23:33:00 UTC
[jira] [Comment Edited] (HADOOP-17216) delta.io spark task commit
encountering S3 cached 404/FileNotFoundException
[ https://issues.apache.org/jira/browse/HADOOP-17216?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17199152#comment-17199152 ]
Cheng Wei edited comment on HADOOP-17216 at 9/24/20, 11:32 PM:
---------------------------------------------------------------
Hi [~stevel@apache.org] ,
I have tested with the latest version of hadoop 3.3.0 with spark 3.0.1. The exact issue is still there.
{code:java}
Caused by: java.io.FileNotFoundException: No such file or directory: s3a://[path]/part-00288-b9770d19-8bcf-4b22-ba4a-b40163c8e39a.c000.snappy.parquet
at org.apache.hadoop.fs.s3a.S3AFileSystem.s3GetFileStatus(S3AFileSystem.java:3049)
at org.apache.hadoop.fs.s3a.S3AFileSystem.innerGetFileStatus(S3AFileSystem.java:2888)
at org.apache.hadoop.fs.s3a.S3AFileSystem.getFileStatus(S3AFileSystem.java:2772)
at org.apache.spark.sql.delta.files.DelayedCommitProtocol.$anonfun$commitTask$1(DelayedCommitProtocol.scala:141)
at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:238)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at scala.collection.TraversableLike.map(TraversableLike.scala:238)
at scala.collection.TraversableLike.map$(TraversableLike.scala:231)
at scala.collection.AbstractTraversable.map(Traversable.scala:108)
at org.apache.spark.sql.delta.files.DelayedCommitProtocol.commitTask(DelayedCommitProtocol.scala:139)
at org.apache.spark.sql.execution.datasources.FileFormatDataWriter.commit(FileFormatDataWriter.scala:79)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$executeTask$1(FileFormatWriter.scala:275)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1411)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.executeTask(FileFormatWriter.scala:281)
... 9 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2059)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2008)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2007)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2007)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:973)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:973)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:973)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2239)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2188)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2177)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:775)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2099)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:195)
... 68 more
Caused by: org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.executeTask(FileFormatWriter.scala:291)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$write$15(FileFormatWriter.scala:205)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:127)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:446)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1377)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:449)
... 3 more
Caused by: java.io.FileNotFoundException: No such file or directory: s3a://[path]/part-00288-b9770d19-8bcf-4b22-ba4a-b40163c8e39a.c000.snappy.parquet
at org.apache.hadoop.fs.s3a.S3AFileSystem.s3GetFileStatus(S3AFileSystem.java:3049)
at org.apache.hadoop.fs.s3a.S3AFileSystem.innerGetFileStatus(S3AFileSystem.java:2888)
at org.apache.hadoop.fs.s3a.S3AFileSystem.getFileStatus(S3AFileSystem.java:2772)
at org.apache.spark.sql.delta.files.DelayedCommitProtocol.$anonfun$commitTask$1(DelayedCommitProtocol.scala:141)
at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:238)
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 scala.collection.TraversableLike.map(TraversableLike.scala:238)
at scala.collection.TraversableLike.map$(TraversableLike.scala:231)
at scala.collection.AbstractTraversable.map(Traversable.scala:108)
at org.apache.spark.sql.delta.files.DelayedCommitProtocol.commitTask(DelayedCommitProtocol.scala:139)
at org.apache.spark.sql.execution.datasources.FileFormatDataWriter.commit(FileFormatDataWriter.scala:79)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$executeTask$1(FileFormatWriter.scala:275)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1411)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.executeTask(FileFormatWriter.scala:281)
{code}
was (Author: weicheng112):
Hi [~stevel@apache.org] ,
I have tested with the latest version of hadoop 3.3.0 with spark 3.0.1. The exact issue is still there.
{code:java}
Caused by: java.io.FileNotFoundException: No such file or directory: s3a://[path]/part-00288-b9770d19-8bcf-4b22-ba4a-b40163c8e39a.c000.snappy.parquet
at org.apache.hadoop.fs.s3a.S3AFileSystem.s3GetFileStatus(S3AFileSystem.java:3049)
at org.apache.hadoop.fs.s3a.S3AFileSystem.innerGetFileStatus(S3AFileSystem.java:2888)
at org.apache.hadoop.fs.s3a.S3AFileSystem.getFileStatus(S3AFileSystem.java:2772)
at org.apache.spark.sql.delta.files.DelayedCommitProtocol.$anonfun$commitTask$1(DelayedCommitProtocol.scala:141)
at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:238)
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 scala.collection.TraversableLike.map(TraversableLike.scala:238)
at scala.collection.TraversableLike.map$(TraversableLike.scala:231)
at scala.collection.AbstractTraversable.map(Traversable.scala:108)
at org.apache.spark.sql.delta.files.DelayedCommitProtocol.commitTask(DelayedCommitProtocol.scala:139)
at org.apache.spark.sql.execution.datasources.FileFormatDataWriter.commit(FileFormatDataWriter.scala:79)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$executeTask$1(FileFormatWriter.scala:275)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1411)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.executeTask(FileFormatWriter.scala:281)
... 9 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2059)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2008)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2007)
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.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2007)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:973)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:973)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:973)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2239)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2188)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2177)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:775)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2099)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:195)
... 68 more
Caused by: org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.executeTask(FileFormatWriter.scala:291)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$write$15(FileFormatWriter.scala:205)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:127)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:446)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1377)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:449)
... 3 more
Caused by: java.io.FileNotFoundException: No such file or directory: s3a://dataresourceprod-databuckete3889a50-wxhu1djfk7ac/GuestDecrypt/date=2020-09-19/part-00288-b9770d19-8bcf-4b22-ba4a-b40163c8e39a.c000.snappy.parquet
at org.apache.hadoop.fs.s3a.S3AFileSystem.s3GetFileStatus(S3AFileSystem.java:3049)
at org.apache.hadoop.fs.s3a.S3AFileSystem.innerGetFileStatus(S3AFileSystem.java:2888)
at org.apache.hadoop.fs.s3a.S3AFileSystem.getFileStatus(S3AFileSystem.java:2772)
at org.apache.spark.sql.delta.files.DelayedCommitProtocol.$anonfun$commitTask$1(DelayedCommitProtocol.scala:141)
at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:238)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at scala.collection.TraversableLike.map(TraversableLike.scala:238)
at scala.collection.TraversableLike.map$(TraversableLike.scala:231)
at scala.collection.AbstractTraversable.map(Traversable.scala:108)
at org.apache.spark.sql.delta.files.DelayedCommitProtocol.commitTask(DelayedCommitProtocol.scala:139)
at org.apache.spark.sql.execution.datasources.FileFormatDataWriter.commit(FileFormatDataWriter.scala:79)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$executeTask$1(FileFormatWriter.scala:275)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1411)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.executeTask(FileFormatWriter.scala:281)
{code}
> delta.io spark task commit encountering S3 cached 404/FileNotFoundException
> ---------------------------------------------------------------------------
>
> Key: HADOOP-17216
> URL: https://issues.apache.org/jira/browse/HADOOP-17216
> Project: Hadoop Common
> Issue Type: Bug
> Components: fs/s3
> Affects Versions: 3.1.2
> Environment: hadoop = "3.1.2"
> hadoop-aws = "3.1.2"
> spark = "2.4.5"
> spark-on-k8s-operator = "v1beta2-1.1.2-2.4.5"
> deployed into AWS EKS kubernates. Version information below:
> Server Version: version.Info\{Major:"1", Minor:"16+", GitVersion:"v1.16.8-eks-e16311", GitCommit:"e163110a04dcb2f39c3325af96d019b4925419eb", GitTreeState:"clean", BuildDate:"2020-03-27T22:37:12Z", GoVersion:"go1.13.8", Compiler:"gc", Platform:"linux/amd64"}
> Reporter: Cheng Wei
> Priority: Major
> Fix For: 3.3.0
>
>
> Hi,
> When using spark streaming with deltalake, I got the following exception occasionally, something like 1 out of 100. Thanks.
> {code:java}
> Caused by: java.io.FileNotFoundException: No such file or directory: s3a://[pathToFolder]/date=2020-07-29/part-00005-046af631-7198-422c-8cc8-8d3adfb4413e.c000.snappy.parquet
> at org.apache.hadoop.fs.s3a.S3AFileSystem.s3GetFileStatus(S3AFileSystem.java:2255)
> at org.apache.hadoop.fs.s3a.S3AFileSystem.innerGetFileStatus(S3AFileSystem.java:2149)
> at org.apache.hadoop.fs.s3a.S3AFileSystem.getFileStatus(S3AFileSystem.java:2088)
> at org.apache.spark.sql.delta.files.DelayedCommitProtocol$$anonfun$8.apply(DelayedCommitProtocol.scala:141)
> at org.apache.spark.sql.delta.files.DelayedCommitProtocol$$anonfun$8.apply(DelayedCommitProtocol.scala:139)
> at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.AbstractTraversable.map(Traversable.scala:104)
> at org.apache.spark.sql.delta.files.DelayedCommitProtocol.commitTask(DelayedCommitProtocol.scala:139)
> at org.apache.spark.sql.execution.datasources.FileFormatDataWriter.commit(FileFormatDataWriter.scala:78)
> at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:247)
> at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:242){code}
>
> -----Environment----
> hadoop = "3.1.2"
> hadoop-aws = "3.1.2"
> spark = "2.4.5"
> spark-on-k8s-operator = "v1beta2-1.1.2-2.4.5"
>
> deployed into AWS EKS kubernates. Version information below:
> Server Version: version.Info\{Major:"1", Minor:"16+", GitVersion:"v1.16.8-eks-e16311", GitCommit:"e163110a04dcb2f39c3325af96d019b4925419eb", GitTreeState:"clean", BuildDate:"2020-03-27T22:37:12Z", GoVersion:"go1.13.8", Compiler:"gc", Platform:"linux/amd64"}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: common-issues-help@hadoop.apache.org