[ https://issues.apache.org/jira/browse/SPARK-23004?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Tathagata Das updated SPARK-23004: ---------------------------------- Description: {code:java} java.lang.IllegalStateException: Cannot remove after already committed or aborted at org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider.org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$verify(HDFSBackedStateStoreProvider.scala:659 ) at org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider$HDFSBackedStateStore.remove(HDFSBackedStateStoreProvider.scala:143) at org.apache.spark.sql.execution.streaming.StateStoreSaveExec$$anonfun$doExecute$3$$anon$1.hasNext(statefulOperators.scala:233) at org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.processInputs(ObjectAggregationIterator.scala:191) at org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.<init>(ObjectAggregationIterator.scala:80) at org.apache.spark.sql.execution.aggregate.ObjectHashAggregateExec$$anonfun$doExecute$1$$anonfun$2.apply(ObjectHashAggregateExec.scala:111) at org.apache.spark.sql.execution.aggregate.ObjectHashAggregateExec$$anonfun$doExecute$1$$anonfun$2.apply(ObjectHashAggregateExec.scala:103) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:108) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) 18-01-05 13:29:57 WARN TaskSetManager:66 Lost task 68.0 in stage 1933.0 (TID 196171, localhost, executor driver): java.lang.IllegalStateException: Cannot remove after already committed or aborted at org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider.org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$verify(HDFSBackedStateStoreProvider.scala:659) {code} was: {code} java.lang.IllegalStateException: Cannot remove after already committed or aborted at org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider.org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$verify(HDFSBackedStateStoreProvider.scala:659 ) at org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider$HDFSBackedStateStore.remove(HDFSBackedStateStoreProvider.scala:143) at org.apache.spark.sql.execution.streaming.StateStoreSaveExec$$anonfun$doExecute$3$$anon$1.hasNext(statefulOperators.scala:233) at org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.processInputs(ObjectAggregationIterator.scala:191) at org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.<init>(ObjectAggregationIterator.scala:80) at org.apache.spark.sql.execution.aggregate.ObjectHashAggregateExec$$anonfun$doExecute$1$$anonfun$2.apply(ObjectHashAggregateExec.scala:111) at org.apache.spark.sql.execution.aggregate.ObjectHashAggregateExec$$anonfun$doExecute$1$$anonfun$2.apply(ObjectHashAggregateExec.scala:103) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:108) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) 18-01-05 13:29:57 WARN TaskSetManager:66 Lost task 68.0 in stage 1933.0 (TID 196171, localhost, executor driver): java.lang.IllegalStateException: Cannot remove after already committed or aborted at org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider.org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$verify(HDFSBackedStateStoreProvider.scala:659) {code} > Structured Streaming raise "llegalStateException: Cannot remove after already > committed or aborted" > --------------------------------------------------------------------------------------------------- > > Key: SPARK-23004 > URL: https://issues.apache.org/jira/browse/SPARK-23004 > Project: Spark > Issue Type: Bug > Components: Input/Output > Affects Versions: 2.2.1 > Environment: Run on yarn or local both raise the exception. > Reporter: secfree > Priority: Major > > > > > > {code:java} > java.lang.IllegalStateException: Cannot remove after already committed or > aborted > at > org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider.org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$verify(HDFSBackedStateStoreProvider.scala:659 > ) > at > org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider$HDFSBackedStateStore.remove(HDFSBackedStateStoreProvider.scala:143) > at > org.apache.spark.sql.execution.streaming.StateStoreSaveExec$$anonfun$doExecute$3$$anon$1.hasNext(statefulOperators.scala:233) > at > org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.processInputs(ObjectAggregationIterator.scala:191) > at > org.apache.spark.sql.execution.aggregate.ObjectAggregationIterator.<init>(ObjectAggregationIterator.scala:80) > at > org.apache.spark.sql.execution.aggregate.ObjectHashAggregateExec$$anonfun$doExecute$1$$anonfun$2.apply(ObjectHashAggregateExec.scala:111) > at > org.apache.spark.sql.execution.aggregate.ObjectHashAggregateExec$$anonfun$doExecute$1$$anonfun$2.apply(ObjectHashAggregateExec.scala:103) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) > at > org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) > at > org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:287) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) > at org.apache.spark.scheduler.Task.run(Task.scala:108) > at > org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) > at java.lang.Thread.run(Thread.java:745) > 18-01-05 13:29:57 WARN TaskSetManager:66 Lost task 68.0 in stage 1933.0 (TID > 196171, localhost, executor driver): java.lang.IllegalStateException: Cannot > remove after already committed or aborted > at > org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider.org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$verify(HDFSBackedStateStoreProvider.scala:659) > {code} -- This message was sent by Atlassian JIRA (v7.6.3#76005) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org