Github user yanlin-Lynn commented on a diff in the pull request:
https://github.com/apache/spark/pull/20529#discussion_r167173873
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2.scala
---
@@ -92,12 +92,14 @@ case class WriteToDataSourceV2Exec(writer:
DataSourceWriter, query: SparkPlan) e
logInfo(s"Data source writer $writer committed.")
}
} catch {
- case _: InterruptedException if writer.isInstanceOf[StreamWriter] =>
- // Interruption is how continuous queries are ended, so accept and
ignore the exception.
+ case _: SparkException if writer.isInstanceOf[StreamWriter] =>
--- End diff --
I found that when stopping continuous processing application using Ctrl-C,
it always throws a SparkException.
What I am trying to fix is to remove this exception when stopping a CP
application.
But this indeed is not a good way to fix it, I will try another way.
----------- The SparkException is as follows -----------
18/02/02 16:12:57 ERROR ContinuousExecution: Query yanlin-CP-job [id =
007f1f44-771a-4097-aaa3-28ae35c16dd9, runId =
3e1ab7c1-4d6f-475a-9d2c-45577643b0dd] terminated with error
org.apache.spark.SparkException: Writing job failed.
at
org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2.scala:105)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at
org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution$$anonfun$runContinuous$3$$anonfun$apply$1.apply(ContinuousExecution.scala:268)
at
org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution$$anonfun$runContinuous$3$$anonfun$apply$1.apply(ContinuousExecution.scala:268)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at
org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution$$anonfun$runContinuous$3.apply(ContinuousExecution.scala:268)
at
org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution$$anonfun$runContinuous$3.apply(ContinuousExecution.scala:268)
at
org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:271)
at
org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at
org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution.runContinuous(ContinuousExecution.scala:266)
at
org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution.runActivatedStream(ContinuousExecution.scala:90)
at
org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:279)
at
org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:189)
Caused by: org.apache.spark.SparkException: Job 0 cancelled because
SparkContext was shut down
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$cleanUpAfterSchedulerStop$1.apply(DAGScheduler.scala:837)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$cleanUpAfterSchedulerStop$1.apply(DAGScheduler.scala:835)
at scala.collection.mutable.HashSet.foreach(HashSet.scala:78)
at
org.apache.spark.scheduler.DAGScheduler.cleanUpAfterSchedulerStop(DAGScheduler.scala:835)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onStop(DAGScheduler.scala:1831)
at org.apache.spark.util.EventLoop.stop(EventLoop.scala:83)
at org.apache.spark.scheduler.DAGScheduler.stop(DAGScheduler.scala:1743)
at
org.apache.spark.SparkContext$$anonfun$stop$8.apply$mcV$sp(SparkContext.scala:1924)
at org.apache.spark.util.Utils$.tryLogNonFatalError(Utils.scala:1357)
at org.apache.spark.SparkContext.stop(SparkContext.scala:1923)
at
org.apache.spark.SparkContext$$anonfun$2.apply$mcV$sp(SparkContext.scala:572)
at
org.apache.spark.util.SparkShutdownHook.run(ShutdownHookManager.scala:216)
at
org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(ShutdownHookManager.scala:188)
at
org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1$$anonfun$apply$mcV$sp$1.apply(ShutdownHookManager.scala:188)
at
org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1$$anonfun$apply$mcV$sp$1.apply(ShutdownHookManager.scala:188)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1988)
at
org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1.apply$mcV$sp(ShutdownHookManager.scala:188)
at
org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1.apply(ShutdownHookManager.scala:188)
at
org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1.apply(ShutdownHookManager.scala:188)
at scala.util.Try$.apply(Try.scala:192)
at
org.apache.spark.util.SparkShutdownHookManager.runAll(ShutdownHookManager.scala:188)
at
org.apache.spark.util.SparkShutdownHookManager$$anon$2.run(ShutdownHookManager.scala:178)
at
org.apache.hadoop.util.ShutdownHookManager$1.run(ShutdownHookManager.java:54)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:642)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2027)
at
org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2.scala:79)
... 19 more
Suppressed: java.lang.UnsupportedOperationException: Abort without epoch
should not be called with StreamWriter
at
org.apache.spark.sql.sources.v2.streaming.writer.StreamWriter.abort(StreamWriter.java:69)
at
org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2.scala:100)
... 19 more
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
