How to debug

[Anfernee Xu <an...@gmail.com>]

Hi,

I'm using Spark 1.5.0, I wrote a custom Hadoop InputFormat to load data
from 3rdparty datasource, the data type mapping has been taken care of in
my code, but when I issued below query,

SELECT * FROM ( SELECT count(*) as failures from test WHERE state !=
'success' ) as tmp WHERE  ( COALESCE(failures , 0) > 10   )

I got such exception, it seems some column has invalid data, but from the
exception I cannot tell which one is culprit. Any suggestion is appreciated.

org.apache.spark.SparkException: Job aborted due to stage failure: Task 0
in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage
0.0 (TID 3, slc00tuw): java.lang.ClassCastException: java.lang.String
cannot be cast to java.lang.Long
at scala.runtime.BoxesRunTime.unboxToLong(BoxesRunTime.java:110)
at
org.apache.spark.sql.catalyst.expressions.BaseGenericInternalRow$class.getLong(rows.scala:41)
at
org.apache.spark.sql.catalyst.expressions.GenericInternalRow.getLong(rows.scala:220)
at
org.apache.spark.sql.columnar.LongColumnStats.gatherStats(ColumnStats.scala:161)
at
org.apache.spark.sql.columnar.NullableColumnBuilder$class.appendFrom(NullableColumnBuilder.scala:56)
at org.apache.spark.sql.columnar.NativeColumnBuilder.org
$apache$spark$sql$columnar$compression$CompressibleColumnBuilder$$super$appendFrom(ColumnBuilder.scala:87)
at
org.apache.spark.sql.columnar.compression.CompressibleColumnBuilder$class.appendFrom(CompressibleColumnBuilder.scala:78)
at
org.apache.spark.sql.columnar.NativeColumnBuilder.appendFrom(ColumnBuilder.scala:87)
at
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:142)
at
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:120)
at org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:278)
at org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:171)
at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:78)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:262)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
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$$failJobAndIndependentStages(DAGScheduler.scala:1280)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1839)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1910)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:905)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:306)
at org.apache.spark.rdd.RDD.collect(RDD.scala:904)
at
org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:177)
at
org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1386)
at
org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1386)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1904)
at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1385)
at org.apache.spark.sql.DataFrame.count(DataFrame.scala:1403)
Caused by: java.lang.ClassCastException: java.lang.String cannot be cast to
java.lang.Long
at scala.runtime.BoxesRunTime.unboxToLong(BoxesRunTime.java:110)
at
org.apache.spark.sql.catalyst.expressions.BaseGenericInternalRow$class.getLong(rows.scala:41)
at
org.apache.spark.sql.catalyst.expressions.GenericInternalRow.getLong(rows.scala:220)
at
org.apache.spark.sql.columnar.LongColumnStats.gatherStats(ColumnStats.scala:161)
at
org.apache.spark.sql.columnar.NullableColumnBuilder$class.appendFrom(NullableColumnBuilder.scala:56)
at org.apache.spark.sql.columnar.NativeColumnBuilder.org
$apache$spark$sql$columnar$compression$CompressibleColumnBuilder$$super$appendFrom(ColumnBuilder.scala:87)
at
org.apache.spark.sql.columnar.compression.CompressibleColumnBuilder$class.appendFrom(CompressibleColumnBuilder.scala:78)
at
org.apache.spark.sql.columnar.NativeColumnBuilder.appendFrom(ColumnBuilder.scala:87)
at
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:142)
at
org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:120)
at org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:278)
at org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:171)
at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:78)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:262)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
-- 
--Anfernee