[
https://issues.apache.org/jira/browse/SPARK-19677?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15875594#comment-15875594
]
Apache Spark commented on SPARK-19677:
--------------------------------------
User 'vitillo' has created a pull request for this issue:
https://github.com/apache/spark/pull/17012
> HDFSBackedStateStoreProvider fails to overwrite existing file
> -------------------------------------------------------------
>
> Key: SPARK-19677
> URL: https://issues.apache.org/jira/browse/SPARK-19677
> Project: Spark
> Issue Type: Bug
> Components: Structured Streaming
> Affects Versions: 2.1.0
> Reporter: Roberto Agostino Vitillo
> Priority: Critical
>
> I got the exception below after restarting a crashed Structured Streaming
> application. This seems to be due to the fact that
> {{/tmp/checkpoint/state/0/0/214451.delta}} already exists in HDFS.
> {code}
> 17/02/20 14:14:26 ERROR StreamExecution: Query [id =
> 5023231c-2433-4013-a8b9-d54bb5751445, runId =
> 4168cf31-7d0b-4435-9b58-28919abd937b] terminated with error
> org.apache.spark.SparkException: Job aborted.
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply$mcV$sp(FileFormatWriter.scala:147)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:121)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:121)
> at
> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:121)
> at
> org.apache.spark.sql.execution.streaming.FileStreamSink.addBatch(FileStreamSink.scala:78)
> at
> org.apache.spark.sql.execution.streaming.StreamExecution$$anonfun$org$apache$spark$sql$execution$streaming$StreamExecution$$runBatch$1.apply$mcV$sp(StreamExecution.scala:503)
> at
> org.apache.spark.sql.execution.streaming.StreamExecution$$anonfun$org$apache$spark$sql$execution$streaming$StreamExecution$$runBatch$1.apply(StreamExecution.scala:503)
> at
> org.apache.spark.sql.execution.streaming.StreamExecution$$anonfun$org$apache$spark$sql$execution$streaming$StreamExecution$$runBatch$1.apply(StreamExecution.scala:503)
> at
> org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:262)
> at
> org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:46)
> at
> org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runBatch(StreamExecution.scala:502)
> at
> org.apache.spark.sql.execution.streaming.StreamExecution$$anonfun$org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches$1$$anonfun$1.apply$mcV$sp(StreamExecution.scala:255)
> at
> org.apache.spark.sql.execution.streaming.StreamExecution$$anonfun$org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches$1$$anonfun$1.apply(StreamExecution.scala:244)
> at
> org.apache.spark.sql.execution.streaming.StreamExecution$$anonfun$org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches$1$$anonfun$1.apply(StreamExecution.scala:244)
> at
> org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:262)
> at
> org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:46)
> at
> org.apache.spark.sql.execution.streaming.StreamExecution$$anonfun$org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches$1.apply$mcZ$sp(StreamExecution.scala:244)
> at
> org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:43)
> at
> org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches(StreamExecution.scala:239)
> at
> org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:177)
> Caused by: org.apache.spark.SparkException: Job aborted due to stage failure:
> Task 0 in stage 1.0 failed 1 times, most recent failure: Lost task 0.0 in
> stage 1.0 (TID 100, localhost, executor driver):
> org.apache.spark.SparkException: Task failed while writing rows
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:204)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1$$anonfun$3.apply(FileFormatWriter.scala:129)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1$$anonfun$3.apply(FileFormatWriter.scala:128)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
> at org.apache.spark.scheduler.Task.run(Task.scala:99)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.IllegalStateException: Error committing version 214451
> into HDFSStateStore[id = (op=0, part=0), dir = /tmp/checkpoint/state/0/0]
> at
> org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider$HDFSBackedStateStore.commit(HDFSBackedStateStoreProvider.scala:162)
> at
> org.apache.spark.sql.execution.streaming.StateStoreSaveExec$$anonfun$doExecute$3.apply(StatefulAggregate.scala:173)
> at
> org.apache.spark.sql.execution.streaming.StateStoreSaveExec$$anonfun$doExecute$3.apply(StatefulAggregate.scala:123)
> at
> org.apache.spark.sql.execution.streaming.state.StateStoreRDD.compute(StateStoreRDD.scala:64)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
> at
> org.apache.spark.rdd.CoalescedRDD$$anonfun$compute$1.apply(CoalescedRDD.scala:100)
> at
> org.apache.spark.rdd.CoalescedRDD$$anonfun$compute$1.apply(CoalescedRDD.scala:99)
> at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434)
> at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$DynamicPartitionWriteTask.execute(FileFormatWriter.scala:365)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:190)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:188)
> at
> org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1341)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:193)
> ... 8 more
> Caused by: java.io.IOException: Failed to rename
> /tmp/checkpoint/state/0/0/temp--6958924364117377568 to
> /tmp/checkpoint/state/0/0/214451.delta
> at
> org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider.org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$commitUpdates(HDFSBackedStateStoreProvider.scala:259)
> at
> org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider$HDFSBackedStateStore.commit(HDFSBackedStateStoreProvider.scala:156)
> ... 25 more
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
