You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Sean Owen (JIRA)" <ji...@apache.org> on 2019/04/05 19:04:00 UTC
[jira] [Resolved] (SPARK-26936) On yarn-client mode, insert
overwrite local directory can not create temporary path in local staging
directory
[ https://issues.apache.org/jira/browse/SPARK-26936?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sean Owen resolved SPARK-26936.
-------------------------------
Resolution: Fixed
Fix Version/s: 3.0.0
Issue resolved by pull request 23841
[https://github.com/apache/spark/pull/23841]
> On yarn-client mode, insert overwrite local directory can not create temporary path in local staging directory
> --------------------------------------------------------------------------------------------------------------
>
> Key: SPARK-26936
> URL: https://issues.apache.org/jira/browse/SPARK-26936
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.3.0, 2.4.0, 3.0.0
> Reporter: jiaan.geng
> Assignee: jiaan.geng
> Priority: Major
> Fix For: 3.0.0
>
>
> Let me introduce bug of 'insert overwrite local directory'.
> If I execute the SQL mentioned before, a HiveException will appear as follows:
> {code:java}
> Driver stacktrace:
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1599)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1587)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1586)
> at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
> at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1586)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
> at scala.Option.foreach(Option.scala:257)
> at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:831)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1820)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1769)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1758)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
> at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:642)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:2037)
> at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:194)
> ... 36 more
> Caused by: org.apache.spark.SparkException: Task failed while writing rows.
> at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:285)
> at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:197)
> at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:196)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
> at org.apache.spark.scheduler.Task.run(Task.scala:109)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: java.io.IOException: Mkdirs failed to create file:/home/xitong/hive/stagingdir_hive_2019-02-19_17-31-00_678_1816816774691551856-1/-ext-10000/_temporary/0/_temporary/attempt_20190219173233_0002_m_000000_3 (exists=false, cwd=file:/data10/yarn/nm-local-dir/usercache/xitong/appcache/application_1543893582405_6126857/container_e124_1543893582405_6126857_01_000011)
> at org.apache.hadoop.hive.ql.io.HiveFileFormatUtils.getHiveRecordWriter(HiveFileFormatUtils.java:249)
> at org.apache.spark.sql.hive.execution.HiveOutputWriter.<init>(HiveFileFormat.scala:123)
> at org.apache.spark.sql.hive.execution.HiveFileFormat$$anon$1.newInstance(HiveFileFormat.scala:103)
> at org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.newOutputWriter(FileFormatWriter.scala:367)
> at org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.execute(FileFormatWriter.scala:378)
> at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:269)
> at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:267)
> at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1411)
> at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:272)
> ... 8 more
> Caused by: java.io.IOException: Mkdirs failed to create file:/home/xitong/hive/stagingdir_hive_2019-02-19_17-31-00_678_1816816774691551856-1/-ext-10000/_temporary/0/_temporary/attempt_20190219173233_0002_m_000000_3 (exists=false, cwd=file:/data10/yarn/nm-local-dir/usercache/xitong/appcache/application_1543893582405_6126857/container_e124_1543893582405_6126857_01_000011)
> at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:449)
> at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:435)
> at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:928)
> at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:821)
> at org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat.getHiveRecordWriter(HiveIgnoreKeyTextOutputFormat.java:80)
> at org.apache.hadoop.hive.ql.io.HiveFileFormatUtils.getRecordWriter(HiveFileFormatUtils.java:261)
> at org.apache.hadoop.hive.ql.io.HiveFileFormatUtils.getHiveRecordWriter(HiveFileFormatUtils.java:246)
> ... 16 more
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org