Jose Torres created SPARK-23416:
-----------------------------------
Summary: flaky test:
org.apache.spark.sql.kafka010.KafkaSourceStressForDontFailOnDataLossSuite.stress
test for failOnDataLoss=false
Key: SPARK-23416
URL: https://issues.apache.org/jira/browse/SPARK-23416
Project: Spark
Issue Type: Bug
Components: Structured Streaming
Affects Versions: 2.4.0
Reporter: Jose Torres
I suspect this is a race condition latent in the DataSourceV2 write path, or at
least the interaction of that write path with StreamTest.
[https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/87241/testReport/org.apache.spark.sql.kafka010/KafkaSourceStressForDontFailOnDataLossSuite/stress_test_for_failOnDataLoss_false/]
h3. Error Message
org.apache.spark.sql.streaming.StreamingQueryException: Query [id =
16b2a2b1-acdd-44ec-902f-531169193169, runId =
9567facb-e305-4554-8622-830519002edb] terminated with exception: Writing job
aborted.
h3. Stacktrace
sbt.ForkMain$ForkError: org.apache.spark.sql.streaming.StreamingQueryException:
Query [id = 16b2a2b1-acdd-44ec-902f-531169193169, runId =
9567facb-e305-4554-8622-830519002edb] terminated with exception: Writing job
aborted. at
org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:295)
at
org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:189)
Caused by: sbt.ForkMain$ForkError: org.apache.spark.SparkException: Writing
job aborted. at
org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2.scala:108)
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$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127) at
org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:247)
at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:294)
at
org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:3272)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2722)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2722) at
org.apache.spark.sql.Dataset$$anonfun$52.apply(Dataset.scala:3253) at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3252) at
org.apache.spark.sql.Dataset.collect(Dataset.scala:2722) at
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$3$$anonfun$apply$15.apply(MicroBatchExecution.scala:488)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$3.apply(MicroBatchExecution.scala:483)
at
org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:271)
at
org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution.org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch(MicroBatchExecution.scala:482)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply$mcV$sp(MicroBatchExecution.scala:133)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:121)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:121)
at
org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:271)
at
org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1.apply$mcZ$sp(MicroBatchExecution.scala:121)
at
org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:56)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:117)
at
org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:279)
... 1 more Caused by: sbt.ForkMain$ForkError: java.lang.InterruptedException:
null at
java.util.concurrent.locks.AbstractQueuedSynchronizer.doAcquireSharedInterruptibly(AbstractQueuedSynchronizer.java:998)
at
java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1304)
at scala.concurrent.impl.Promise$DefaultPromise.tryAwait(Promise.scala:202) at
scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:218) at
scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:153) at
org.apache.spark.util.ThreadUtils$.awaitReady(ThreadUtils.scala:222) at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:633) at
org.apache.spark.SparkContext.runJob(SparkContext.scala:2027) at
org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2.scala:79)
... 31 more
--
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
