Query memory [id = 0f5b190e-09ff-43fd-8cc6-ead0f9484399, runId = d90a8480-455e-45c6-b48e-b5e46d325676] terminated with exception: Writing job aborted.
org.apache.spark.sql.streaming.StreamingQueryException: Writing job aborted.
=== Streaming Query ===
Identifier: memory [id = 0f5b190e-09ff-43fd-8cc6-ead0f9484399, runId = d90a8480-455e-45c6-b48e-b5e46d325676]
Current Committed Offsets: {KafkaSource[SubscribePattern[failOnDataLoss.*]]: {"failOnDataLoss-1":{"0":25}}}
Current Available Offsets: {}
Current State: ACTIVE
Thread State: RUNNABLE
Logical Plan:
SerializeFromObject [input[0, int, false] AS value#3369]
+- MapElements <function1>, class scala.Tuple2, [StructField(_1,StringType,true), StructField(_2,StringType,true)], obj#3368: int
+- DeserializeToObject newInstance(class scala.Tuple2), obj#3367: scala.Tuple2
+- Project [cast(key#3345 as string) AS key#3359, cast(value#3346 as string) AS value#3360]
+- ContinuousExecutionRelation org.apache.spark.sql.kafka010.KafkaSourceProvider@23595dd9, Map(kafka.metadata.max.age.ms -> 1, fetchOffset.retryIntervalMs -> 3000, failOnDataLoss -> false, kafka.bootstrap.servers -> localhost:44884, startingOffsets -> earliest, kafka.default.api.timeout.ms -> 3000, subscribePattern -> failOnDataLoss.*), [key#3345, value#3346, topic#3347, partition#3348, offset#3349L, timestamp#3350, timestampType#3351]
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)
Cause: org.apache.spark.SparkException: Writing job aborted.
at org.apache.spark.sql.execution.streaming.continuous.WriteToContinuousDataSourceExec.doExecute(WriteToContinuousDataSourceExec.scala:62)
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$$anonfun$apply$1.apply(ContinuousExecution.scala:260)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution$$anonfun$runContinuous$3$$anonfun$apply$1.apply(ContinuousExecution.scala:260)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution$$anonfun$runContinuous$3.apply(ContinuousExecution.scala:260)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution$$anonfun$runContinuous$3.apply(ContinuousExecution.scala:260)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:403)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution.runContinuous(ContinuousExecution.scala:258)
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)
Cause: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 2.0 failed 3 times, most recent failure: Lost task 0.2 in stage 2.0 (TID 5, localhost, executor driver): org.apache.spark.sql.execution.streaming.continuous.ContinuousTaskRetryException: Continuous execution does not support task retry
at org.apache.spark.sql.execution.streaming.continuous.ContinuousDataSourceRDD.compute(ContinuousDataSourceRDD.scala:68)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:48)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousWriteRDD$$anonfun$compute$1.apply$mcV$sp(ContinuousWriteRDD.scala:52)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousWriteRDD$$anonfun$compute$1.apply(ContinuousWriteRDD.scala:51)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousWriteRDD$$anonfun$compute$1.apply(ContinuousWriteRDD.scala:51)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1382)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousWriteRDD.compute(ContinuousWriteRDD.scala:76)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:128)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:367)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1763)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1751)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1750)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1750)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:894)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:894)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:894)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1984)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1933)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1922)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:705)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2052)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2073)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2092)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2117)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:939)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.collect(RDD.scala:938)
at org.apache.spark.sql.execution.streaming.continuous.WriteToContinuousDataSourceExec.doExecute(WriteToContinuousDataSourceExec.scala:53)
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$$anonfun$apply$1.apply(ContinuousExecution.scala:260)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution$$anonfun$runContinuous$3$$anonfun$apply$1.apply(ContinuousExecution.scala:260)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution$$anonfun$runContinuous$3.apply(ContinuousExecution.scala:260)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution$$anonfun$runContinuous$3.apply(ContinuousExecution.scala:260)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:403)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousExecution.runContinuous(ContinuousExecution.scala:258)
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)
Cause: org.apache.spark.sql.execution.streaming.continuous.ContinuousTaskRetryException: Continuous execution does not support task retry
at org.apache.spark.sql.execution.streaming.continuous.ContinuousDataSourceRDD.compute(ContinuousDataSourceRDD.scala:68)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:48)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousWriteRDD$$anonfun$compute$1.apply$mcV$sp(ContinuousWriteRDD.scala:52)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousWriteRDD$$anonfun$compute$1.apply(ContinuousWriteRDD.scala:51)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousWriteRDD$$anonfun$compute$1.apply(ContinuousWriteRDD.scala:51)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1382)
at org.apache.spark.sql.execution.streaming.continuous.ContinuousWriteRDD.compute(ContinuousWriteRDD.scala:76)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:128)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:367)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)