[
https://issues.apache.org/jira/browse/SPARK-6772?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Aditya Parmar updated SPARK-6772:
---------------------------------
Description:
Hi all ,
I am getting an Arrayoutboundsindex error when i try to run a simple filtering
colums query on a file with 2.5 lac records.runs fine when running on a file
with 2k records .
15/04/09 12:19:01 WARN TaskSetManager: Lost task 1.0 in stage 0.0 (TID 1):
java.lang.ArrayIndexOutOfBoundsException: 1
at
org.apache.spark.sql.catalyst.expressions.GenericRow.apply(Row.scala:142)
at
org.apache.spark.sql.catalyst.expressions.BoundReference.eval(BoundAttribute.scala:37)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:68)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:52)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1060)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1047)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
15/04/09 12:19:01 INFO TaskSetManager: Starting task 1.1 in stage 0.0 (TID 2,
blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1349 bytes)
15/04/09 12:19:01 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0):
java.lang.ArrayIndexOutOfBoundsException
15/04/09 12:19:01 INFO TaskSetManager: Starting task 0.1 in stage 0.0 (TID 3,
blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1349 bytes)
15/04/09 12:19:01 INFO TaskSetManager: Lost task 1.1 in stage 0.0 (TID 2) on
executor :
java.lang.ArrayIndexOutOfBoundsException (null) [duplicate 1]
15/04/09 12:19:01 INFO TaskSetManager: Starting task 1.2 in stage 0.0 (TID 4,
blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1349 bytes)
15/04/09 12:19:01 INFO TaskSetManager: Lost task 1.2 in stage 0.0 (TID 4) on
executor : java.lang.ArrayIndexOutOfBoundsException (null) [duplicate 2]
15/04/09 12:19:01 INFO TaskSetManager: Starting task 1.3 in stage 0.0 (TID 5,
blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1349 bytes)
15/04/09 12:19:01 INFO TaskSetManager: Lost task 0.1 in stage 0.0 (TID 3) on
executor : java.lang.ArrayIndexOutOfBoundsException (null) [duplicate 3]
15/04/09 12:19:01 INFO TaskSetManager: Starting task 0.2 in stage 0.0 (TID 6,
blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1349 bytes)
15/04/09 12:19:02 INFO TaskSetManager: Lost task 1.3 in stage 0.0 (TID 5) on
executor : java.lang.ArrayIndexOutOfBoundsException (null) [duplicate 4]
15/04/09 12:19:02 ERROR TaskSetManager: Task 1 in stage 0.0 failed 4 times;
aborting job
15/04/09 12:19:02 INFO TaskSchedulerImpl: Cancelling stage 0
15/04/09 12:19:02 INFO TaskSchedulerImpl: Stage 0 was cancelled
15/04/09 12:19:02 INFO DAGScheduler: Job 0 failed: saveAsTextFile at
JavaSchemaRDD.scala:42, took 1.958621 s
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to
stage failure: Task 1 in stage 0.0 failed 4 times, most recent failure: Lost
task 1.3 in stage 0.0 (TID 5, ): java.lang.ArrayIndexOutOfBoundsException
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1214)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420)
at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1375)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
at akka.actor.ActorCell.invoke(ActorCell.scala:487)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
at akka.dispatch.Mailbox.run(Mailbox.scala:220)
at
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:393)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at
scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at
scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at
scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
15/04/09 12:19:02 WARN TaskSetManager: Lost task 0.2 in stage 0.0 (TID 6,
blrwfl11189.igatecorp.com): TaskKilled (killed intentionally)
15/04/09 12:19:02 INFO TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks have
all completed, from pool
[aditya@blrwfl11189 ~]$ spark-submit --class engineshow engineshow.jar
Spark assembly has been built with Hive, including Datanucleus jars on classpath
Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
15/04/09 12:22:30 INFO SecurityManager: Changing view acls to: aditya
15/04/09 12:22:30 INFO SecurityManager: Changing modify acls to: aditya
15/04/09 12:22:30 INFO SecurityManager: SecurityManager: authentication
disabled; ui acls disabled; users with view permissions: Set(aditya); users
with modify permissions: Set(aditya)
15/04/09 12:22:30 INFO Slf4jLogger: Slf4jLogger started
15/04/09 12:22:30 INFO Remoting: Starting remoting
15/04/09 12:22:31 INFO Remoting: Remoting started; listening on addresses
:[akka.tcp://sparkdri...@blrwfl11189.igatecorp.com:47121]
15/04/09 12:22:31 INFO Utils: Successfully started service 'sparkDriver' on
port 47121.
15/04/09 12:22:31 INFO SparkEnv: Registering MapOutputTracker
15/04/09 12:22:31 INFO SparkEnv: Registering BlockManagerMaster
15/04/09 12:22:31 INFO DiskBlockManager: Created local directory at
/tmp/spark-local-20150409122231-c0ed
15/04/09 12:22:31 INFO MemoryStore: MemoryStore started with capacity 265.4 MB
15/04/09 12:22:31 INFO HttpFileServer: HTTP File server directory is
/tmp/spark-6813688b-502e-41e4-ab21-27eb4544986f
15/04/09 12:22:31 INFO HttpServer: Starting HTTP Server
15/04/09 12:22:31 INFO Utils: Successfully started service 'HTTP file server'
on port 37771.
15/04/09 12:22:31 INFO Utils: Successfully started service 'SparkUI' on port
4040.
15/04/09 12:22:31 INFO SparkUI: Started SparkUI at
http://blrwfl11189.igatecorp.com:4040
15/04/09 12:22:31 INFO SparkContext: Added JAR file:/home/aditya/engineshow.jar
at http://10.212.51.39:37771/jars/engineshow.jar with timestamp 1428562351299
15/04/09 12:22:31 INFO AkkaUtils: Connecting to HeartbeatReceiver:
akka.tcp://sparkdri...@blrwfl11189.igatecorp.com:47121/user/HeartbeatReceiver
15/04/09 12:22:31 INFO NettyBlockTransferService: Server created on 50256
15/04/09 12:22:31 INFO BlockManagerMaster: Trying to register BlockManager
15/04/09 12:22:31 INFO BlockManagerMasterActor: Registering block manager
localhost:50256 with 265.4 MB RAM, BlockManagerId(<driver>, localhost, 50256)
15/04/09 12:22:31 INFO BlockManagerMaster: Registered BlockManager
15/04/09 12:22:31 INFO MemoryStore: ensureFreeSpace(32768) called with
curMem=0, maxMem=278302556
15/04/09 12:22:31 INFO MemoryStore: Block broadcast_0 stored as values in
memory (estimated size 32.0 KB, free 265.4 MB)
15/04/09 12:22:31 INFO MemoryStore: ensureFreeSpace(4959) called with
curMem=32768, maxMem=278302556
15/04/09 12:22:31 INFO MemoryStore: Block broadcast_0_piece0 stored as bytes in
memory (estimated size 4.8 KB, free 265.4 MB)
15/04/09 12:22:31 INFO BlockManagerInfo: Added broadcast_0_piece0 in memory on
localhost:50256 (size: 4.8 KB, free: 265.4 MB)
15/04/09 12:22:31 INFO BlockManagerMaster: Updated info of block
broadcast_0_piece0
15/04/09 12:22:31 INFO SparkContext: Created broadcast 0 from textFile at
engineshow.java:32
15/04/09 12:22:32 INFO HiveMetaStore: 0: Opening raw store with implemenation
class:org.apache.hadoop.hive.metastore.ObjectStore
15/04/09 12:22:32 INFO ObjectStore: ObjectStore, initialize called
15/04/09 12:22:32 INFO Persistence: Property datanucleus.cache.level2 unknown -
will be ignored
15/04/09 12:22:32 INFO Persistence: Property
hive.metastore.integral.jdo.pushdown unknown - will be ignored
15/04/09 12:22:32 WARN Connection: BoneCP specified but not present in
CLASSPATH (or one of dependencies)
15/04/09 12:22:32 WARN Connection: BoneCP specified but not present in
CLASSPATH (or one of dependencies)
15/04/09 12:22:33 INFO ObjectStore: Setting MetaStore object pin classes with
hive.metastore.cache.pinobjtypes="Table,StorageDescriptor,SerDeInfo,Partition,Database,Type,FieldSchema,Order"
15/04/09 12:22:33 INFO MetaStoreDirectSql: MySQL check failed, assuming we are
not on mysql: Lexical error at line 1, column 5. Encountered: "@" (64), after
: "".
15/04/09 12:22:34 INFO Datastore: The class
"org.apache.hadoop.hive.metastore.model.MFieldSchema" is tagged as
"embedded-only" so does not have its own datastore table.
15/04/09 12:22:34 INFO Datastore: The class
"org.apache.hadoop.hive.metastore.model.MOrder" is tagged as "embedded-only" so
does not have its own datastore table.
15/04/09 12:22:34 INFO Datastore: The class
"org.apache.hadoop.hive.metastore.model.MFieldSchema" is tagged as
"embedded-only" so does not have its own datastore table.
15/04/09 12:22:34 INFO Datastore: The class
"org.apache.hadoop.hive.metastore.model.MOrder" is tagged as "embedded-only" so
does not have its own datastore table.
15/04/09 12:22:34 INFO Query: Reading in results for query
"org.datanucleus.store.rdbms.query.SQLQuery@0" since the connection used is
closing
15/04/09 12:22:34 INFO ObjectStore: Initialized ObjectStore
15/04/09 12:22:34 INFO HiveMetaStore: Added admin role in metastore
15/04/09 12:22:34 INFO HiveMetaStore: Added public role in metastore
15/04/09 12:22:34 INFO HiveMetaStore: No user is added in admin role, since
config is empty
15/04/09 12:22:34 INFO SessionState: No Tez session required at this point.
hive.execution.engine=mr.
15/04/09 12:22:35 INFO ParseDriver: Parsing command: select a,b from comp1
15/04/09 12:22:35 INFO ParseDriver: Parse Completed
15/04/09 12:22:35 WARN LoadSnappy: Snappy native library is available
15/04/09 12:22:35 WARN NativeCodeLoader: Unable to load native-hadoop library
for your platform... using builtin-java classes where applicable
15/04/09 12:22:35 WARN LoadSnappy: Snappy native library not loaded
15/04/09 12:22:35 INFO FileInputFormat: Total input paths to process : 1
15/04/09 12:22:35 INFO SparkContext: Starting job: saveAsTextFile at
JavaSchemaRDD.scala:42
15/04/09 12:22:35 INFO DAGScheduler: Got job 0 (saveAsTextFile at
JavaSchemaRDD.scala:42) with 2 output partitions (allowLocal=false)
15/04/09 12:22:35 INFO DAGScheduler: Final stage: Stage 0(saveAsTextFile at
JavaSchemaRDD.scala:42)
15/04/09 12:22:35 INFO DAGScheduler: Parents of final stage: List()
15/04/09 12:22:35 INFO DAGScheduler: Missing parents: List()
15/04/09 12:22:35 INFO DAGScheduler: Submitting Stage 0 (MappedRDD[8] at
saveAsTextFile at JavaSchemaRDD.scala:42), which has no missing parents
15/04/09 12:22:35 INFO MemoryStore: ensureFreeSpace(20896) called with
curMem=37727, maxMem=278302556
15/04/09 12:22:35 INFO MemoryStore: Block broadcast_1 stored as values in
memory (estimated size 20.4 KB, free 265.4 MB)
15/04/09 12:22:35 INFO MemoryStore: ensureFreeSpace(15057) called with
curMem=58623, maxMem=278302556
15/04/09 12:22:35 INFO MemoryStore: Block broadcast_1_piece0 stored as bytes in
memory (estimated size 14.7 KB, free 265.3 MB)
15/04/09 12:22:35 INFO BlockManagerInfo: Added broadcast_1_piece0 in memory on
localhost:50256 (size: 14.7 KB, free: 265.4 MB)
15/04/09 12:22:35 INFO BlockManagerMaster: Updated info of block
broadcast_1_piece0
15/04/09 12:22:35 INFO SparkContext: Created broadcast 1 from broadcast at
DAGScheduler.scala:838
15/04/09 12:22:35 INFO DAGScheduler: Submitting 2 missing tasks from Stage 0
(MappedRDD[8] at saveAsTextFile at JavaSchemaRDD.scala:42)
15/04/09 12:22:35 INFO TaskSchedulerImpl: Adding task set 0.0 with 2 tasks
15/04/09 12:22:35 INFO TaskSetManager: Starting task 0.0 in stage 0.0 (TID 0,
localhost, PROCESS_LOCAL, 1349 bytes)
15/04/09 12:22:35 INFO TaskSetManager: Starting task 1.0 in stage 0.0 (TID 1,
localhost, PROCESS_LOCAL, 1349 bytes)
15/04/09 12:22:35 INFO Executor: Running task 0.0 in stage 0.0 (TID 0)
15/04/09 12:22:35 INFO Executor: Running task 1.0 in stage 0.0 (TID 1)
15/04/09 12:22:35 INFO Executor: Fetching
http://10.212.51.39:37771/jars/engineshow.jar with timestamp 1428562351299
15/04/09 12:22:35 INFO Utils: Fetching
http://10.212.51.39:37771/jars/engineshow.jar to
/tmp/fetchFileTemp3748447218639833283.tmp
15/04/09 12:22:35 INFO Executor: Adding
file:/tmp/spark-0ed71155-55db-48dd-ac02-7a56fe33381b/engineshow.jar to class
loader
15/04/09 12:22:35 INFO HadoopRDD: Input split:
file:/home/aditya/stocks1.csv:0+6708709
15/04/09 12:22:35 INFO HadoopRDD: Input split:
file:/home/aditya/stocks1.csv:6708709+6708709
15/04/09 12:22:36 ERROR Executor: Exception in task 1.0 in stage 0.0 (TID 1)
java.lang.ArrayIndexOutOfBoundsException: 1
at
org.apache.spark.sql.catalyst.expressions.GenericRow.apply(Row.scala:142)
at
org.apache.spark.sql.catalyst.expressions.BoundReference.eval(BoundAttribute.scala:37)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:68)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:52)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1060)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1047)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
15/04/09 12:22:36 WARN TaskSetManager: Lost task 1.0 in stage 0.0 (TID 1,
localhost): java.lang.ArrayIndexOutOfBoundsException: 1
at
org.apache.spark.sql.catalyst.expressions.GenericRow.apply(Row.scala:142)
at
org.apache.spark.sql.catalyst.expressions.BoundReference.eval(BoundAttribute.scala:37)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:68)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:52)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1060)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1047)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
15/04/09 12:22:36 ERROR TaskSetManager: Task 1 in stage 0.0 failed 1 times;
aborting job
15/04/09 12:22:36 INFO TaskSchedulerImpl: Cancelling stage 0
15/04/09 12:22:36 INFO Executor: Executor is trying to kill task 0.0 in stage
0.0 (TID 0)
15/04/09 12:22:36 INFO TaskSchedulerImpl: Stage 0 was cancelled
15/04/09 12:22:36 INFO Executor: Executor killed task 0.0 in stage 0.0 (TID 0)
15/04/09 12:22:36 INFO DAGScheduler: Job 0 failed: saveAsTextFile at
JavaSchemaRDD.scala:42, took 0.616858 s
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to
stage failure: Task 1 in stage 0.0 failed 1 times, most recent failure: Lost
task 1.0 in stage 0.0 (TID 1, localhost):
java.lang.ArrayIndexOutOfBoundsException: 1
at
org.apache.spark.sql.catalyst.expressions.GenericRow.apply(Row.scala:142)
at
org.apache.spark.sql.catalyst.expressions.BoundReference.eval(BoundAttribute.scala:37)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:68)
at
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:52)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1060)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1047)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1214)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420)
at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1375)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
at akka.actor.ActorCell.invoke(ActorCell.scala:487)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
at akka.dispatch.Mailbox.run(Mailbox.scala:220)
at
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:393)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at
scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at
scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at
scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
15/04/09 12:22:36 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0,
localhost): TaskKilled (killed intentionally)
15/04/09 12:22:36 INFO TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks have
all completed, from pool
was:
Hi all ,
I am getting an Arrayoutboundsindex error when i try to run a simple filtering
colums query on a file with 2.5 lac records.runs fine when running on a file
with 2k records .
{code}
15/04/08 16:54:06 INFO TaskSetManager: Starting task 0.1 in stage 0.0 (TID 3,
blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1350 bytes)
15/04/08 16:54:06 INFO TaskSetManager: Lost task 1.1 in stage 0.0 (TID 2) on
executor blrwfl11189.igatecorp.com: java.lang.ArrayIndexOutOfBoundsException
(null) [duplicate 1]
15/04/08 16:54:06 INFO TaskSetManager: Starting task 1.2 in stage 0.0 (TID 4,
blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1350 bytes)
15/04/08 16:54:06 INFO TaskSetManager: Lost task 1.2 in stage 0.0 (TID 4) on
executor blrwfl11189.igatecorp.com: java.lang.ArrayIndexOutOfBoundsException
(null) [duplicate 2]
15/04/08 16:54:06 INFO TaskSetManager: Starting task 1.3 in stage 0.0 (TID 5,
blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1350 bytes)
15/04/08 16:54:06 INFO TaskSetManager: Lost task 0.1 in stage 0.0 (TID 3) on
executor blrwfl11189.igatecorp.com: java.lang.ArrayIndexOutOfBoundsException
(null) [duplicate 3]
15/04/08 16:54:06 INFO TaskSetManager: Starting task 0.2 in stage 0.0 (TID 6,
blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1350 bytes)
15/04/08 16:54:06 INFO TaskSetManager: Lost task 1.3 in stage 0.0 (TID 5) on
executor blrwfl11189.igatecorp.com: java.lang.ArrayIndexOutOfBoundsException
(null) [duplicate 4]
15/04/08 16:54:06 ERROR TaskSetManager: Task 1 in stage 0.0 failed 4 times;
aborting job
15/04/08 16:54:06 INFO TaskSchedulerImpl: Cancelling stage 0
15/04/08 16:54:06 INFO TaskSchedulerImpl: Stage 0 was cancelled
15/04/08 16:54:06 INFO DAGScheduler: Job 0 failed: saveAsTextFile at
JavaSchemaRDD.scala:42, took 1.914477 s
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to
stage failure: Task 1 in stage 0.0 failed 4 times, most recent failure: Lost
task 1.3 in stage 0.0 (TID 5, blrwfl11189.igatecorp.com):
java.lang.ArrayIndexOutOfBoundsException
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1214)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420)
at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1375)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
at akka.actor.ActorCell.invoke(ActorCell.scala:487)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
at akka.dispatch.Mailbox.run(Mailbox.scala:220)
at
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:393)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at
scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at
scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at
scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
[aditya@blrwfl11189 ~]$
{code}
> spark sql error when running code on large number of records
> ------------------------------------------------------------
>
> Key: SPARK-6772
> URL: https://issues.apache.org/jira/browse/SPARK-6772
> Project: Spark
> Issue Type: Test
> Components: SQL
> Affects Versions: 1.2.0
> Reporter: Aditya Parmar
>
> Hi all ,
> I am getting an Arrayoutboundsindex error when i try to run a simple
> filtering colums query on a file with 2.5 lac records.runs fine when running
> on a file with 2k records .
> 15/04/09 12:19:01 WARN TaskSetManager: Lost task 1.0 in stage 0.0 (TID 1):
> java.lang.ArrayIndexOutOfBoundsException: 1
> at
> org.apache.spark.sql.catalyst.expressions.GenericRow.apply(Row.scala:142)
> at
> org.apache.spark.sql.catalyst.expressions.BoundReference.eval(BoundAttribute.scala:37)
> at
> org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:68)
> at
> org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:52)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at
> org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1060)
> at
> org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1047)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 15/04/09 12:19:01 INFO TaskSetManager: Starting task 1.1 in stage 0.0 (TID 2,
> blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1349 bytes)
> 15/04/09 12:19:01 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0):
> java.lang.ArrayIndexOutOfBoundsException
> 15/04/09 12:19:01 INFO TaskSetManager: Starting task 0.1 in stage 0.0 (TID 3,
> blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1349 bytes)
> 15/04/09 12:19:01 INFO TaskSetManager: Lost task 1.1 in stage 0.0 (TID 2) on
> executor :
> java.lang.ArrayIndexOutOfBoundsException (null) [duplicate 1]
> 15/04/09 12:19:01 INFO TaskSetManager: Starting task 1.2 in stage 0.0 (TID 4,
> blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1349 bytes)
> 15/04/09 12:19:01 INFO TaskSetManager: Lost task 1.2 in stage 0.0 (TID 4) on
> executor : java.lang.ArrayIndexOutOfBoundsException (null) [duplicate 2]
> 15/04/09 12:19:01 INFO TaskSetManager: Starting task 1.3 in stage 0.0 (TID 5,
> blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1349 bytes)
> 15/04/09 12:19:01 INFO TaskSetManager: Lost task 0.1 in stage 0.0 (TID 3) on
> executor : java.lang.ArrayIndexOutOfBoundsException (null) [duplicate 3]
> 15/04/09 12:19:01 INFO TaskSetManager: Starting task 0.2 in stage 0.0 (TID 6,
> blrwfl11189.igatecorp.com, PROCESS_LOCAL, 1349 bytes)
> 15/04/09 12:19:02 INFO TaskSetManager: Lost task 1.3 in stage 0.0 (TID 5) on
> executor : java.lang.ArrayIndexOutOfBoundsException (null) [duplicate 4]
> 15/04/09 12:19:02 ERROR TaskSetManager: Task 1 in stage 0.0 failed 4 times;
> aborting job
> 15/04/09 12:19:02 INFO TaskSchedulerImpl: Cancelling stage 0
> 15/04/09 12:19:02 INFO TaskSchedulerImpl: Stage 0 was cancelled
> 15/04/09 12:19:02 INFO DAGScheduler: Job 0 failed: saveAsTextFile at
> JavaSchemaRDD.scala:42, took 1.958621 s
> Exception in thread "main" org.apache.spark.SparkException: Job aborted due
> to stage failure: Task 1 in stage 0.0 failed 4 times, most recent failure:
> Lost task 1.3 in stage 0.0 (TID 5, ): java.lang.ArrayIndexOutOfBoundsException
> Driver stacktrace:
> at
> org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1214)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at
> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
> at scala.Option.foreach(Option.scala:236)
> at
> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420)
> at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1375)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
> at akka.actor.ActorCell.invoke(ActorCell.scala:487)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
> at akka.dispatch.Mailbox.run(Mailbox.scala:220)
> at
> akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:393)
> at
> scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> at
> scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> at
> scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> at
> scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
> 15/04/09 12:19:02 WARN TaskSetManager: Lost task 0.2 in stage 0.0 (TID 6,
> blrwfl11189.igatecorp.com): TaskKilled (killed intentionally)
> 15/04/09 12:19:02 INFO TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks
> have all completed, from pool
> [aditya@blrwfl11189 ~]$ spark-submit --class engineshow engineshow.jar
> Spark assembly has been built with Hive, including Datanucleus jars on
> classpath
> Using Spark's default log4j profile:
> org/apache/spark/log4j-defaults.properties
> 15/04/09 12:22:30 INFO SecurityManager: Changing view acls to: aditya
> 15/04/09 12:22:30 INFO SecurityManager: Changing modify acls to: aditya
> 15/04/09 12:22:30 INFO SecurityManager: SecurityManager: authentication
> disabled; ui acls disabled; users with view permissions: Set(aditya); users
> with modify permissions: Set(aditya)
> 15/04/09 12:22:30 INFO Slf4jLogger: Slf4jLogger started
> 15/04/09 12:22:30 INFO Remoting: Starting remoting
> 15/04/09 12:22:31 INFO Remoting: Remoting started; listening on addresses
> :[akka.tcp://sparkdri...@blrwfl11189.igatecorp.com:47121]
> 15/04/09 12:22:31 INFO Utils: Successfully started service 'sparkDriver' on
> port 47121.
> 15/04/09 12:22:31 INFO SparkEnv: Registering MapOutputTracker
> 15/04/09 12:22:31 INFO SparkEnv: Registering BlockManagerMaster
> 15/04/09 12:22:31 INFO DiskBlockManager: Created local directory at
> /tmp/spark-local-20150409122231-c0ed
> 15/04/09 12:22:31 INFO MemoryStore: MemoryStore started with capacity 265.4 MB
> 15/04/09 12:22:31 INFO HttpFileServer: HTTP File server directory is
> /tmp/spark-6813688b-502e-41e4-ab21-27eb4544986f
> 15/04/09 12:22:31 INFO HttpServer: Starting HTTP Server
> 15/04/09 12:22:31 INFO Utils: Successfully started service 'HTTP file server'
> on port 37771.
> 15/04/09 12:22:31 INFO Utils: Successfully started service 'SparkUI' on port
> 4040.
> 15/04/09 12:22:31 INFO SparkUI: Started SparkUI at
> http://blrwfl11189.igatecorp.com:4040
> 15/04/09 12:22:31 INFO SparkContext: Added JAR
> file:/home/aditya/engineshow.jar at
> http://10.212.51.39:37771/jars/engineshow.jar with timestamp 1428562351299
> 15/04/09 12:22:31 INFO AkkaUtils: Connecting to HeartbeatReceiver:
> akka.tcp://sparkdri...@blrwfl11189.igatecorp.com:47121/user/HeartbeatReceiver
> 15/04/09 12:22:31 INFO NettyBlockTransferService: Server created on 50256
> 15/04/09 12:22:31 INFO BlockManagerMaster: Trying to register BlockManager
> 15/04/09 12:22:31 INFO BlockManagerMasterActor: Registering block manager
> localhost:50256 with 265.4 MB RAM, BlockManagerId(<driver>, localhost, 50256)
> 15/04/09 12:22:31 INFO BlockManagerMaster: Registered BlockManager
> 15/04/09 12:22:31 INFO MemoryStore: ensureFreeSpace(32768) called with
> curMem=0, maxMem=278302556
> 15/04/09 12:22:31 INFO MemoryStore: Block broadcast_0 stored as values in
> memory (estimated size 32.0 KB, free 265.4 MB)
> 15/04/09 12:22:31 INFO MemoryStore: ensureFreeSpace(4959) called with
> curMem=32768, maxMem=278302556
> 15/04/09 12:22:31 INFO MemoryStore: Block broadcast_0_piece0 stored as bytes
> in memory (estimated size 4.8 KB, free 265.4 MB)
> 15/04/09 12:22:31 INFO BlockManagerInfo: Added broadcast_0_piece0 in memory
> on localhost:50256 (size: 4.8 KB, free: 265.4 MB)
> 15/04/09 12:22:31 INFO BlockManagerMaster: Updated info of block
> broadcast_0_piece0
> 15/04/09 12:22:31 INFO SparkContext: Created broadcast 0 from textFile at
> engineshow.java:32
> 15/04/09 12:22:32 INFO HiveMetaStore: 0: Opening raw store with implemenation
> class:org.apache.hadoop.hive.metastore.ObjectStore
> 15/04/09 12:22:32 INFO ObjectStore: ObjectStore, initialize called
> 15/04/09 12:22:32 INFO Persistence: Property datanucleus.cache.level2 unknown
> - will be ignored
> 15/04/09 12:22:32 INFO Persistence: Property
> hive.metastore.integral.jdo.pushdown unknown - will be ignored
> 15/04/09 12:22:32 WARN Connection: BoneCP specified but not present in
> CLASSPATH (or one of dependencies)
> 15/04/09 12:22:32 WARN Connection: BoneCP specified but not present in
> CLASSPATH (or one of dependencies)
> 15/04/09 12:22:33 INFO ObjectStore: Setting MetaStore object pin classes with
> hive.metastore.cache.pinobjtypes="Table,StorageDescriptor,SerDeInfo,Partition,Database,Type,FieldSchema,Order"
> 15/04/09 12:22:33 INFO MetaStoreDirectSql: MySQL check failed, assuming we
> are not on mysql: Lexical error at line 1, column 5. Encountered: "@" (64),
> after : "".
> 15/04/09 12:22:34 INFO Datastore: The class
> "org.apache.hadoop.hive.metastore.model.MFieldSchema" is tagged as
> "embedded-only" so does not have its own datastore table.
> 15/04/09 12:22:34 INFO Datastore: The class
> "org.apache.hadoop.hive.metastore.model.MOrder" is tagged as "embedded-only"
> so does not have its own datastore table.
> 15/04/09 12:22:34 INFO Datastore: The class
> "org.apache.hadoop.hive.metastore.model.MFieldSchema" is tagged as
> "embedded-only" so does not have its own datastore table.
> 15/04/09 12:22:34 INFO Datastore: The class
> "org.apache.hadoop.hive.metastore.model.MOrder" is tagged as "embedded-only"
> so does not have its own datastore table.
> 15/04/09 12:22:34 INFO Query: Reading in results for query
> "org.datanucleus.store.rdbms.query.SQLQuery@0" since the connection used is
> closing
> 15/04/09 12:22:34 INFO ObjectStore: Initialized ObjectStore
> 15/04/09 12:22:34 INFO HiveMetaStore: Added admin role in metastore
> 15/04/09 12:22:34 INFO HiveMetaStore: Added public role in metastore
> 15/04/09 12:22:34 INFO HiveMetaStore: No user is added in admin role, since
> config is empty
> 15/04/09 12:22:34 INFO SessionState: No Tez session required at this point.
> hive.execution.engine=mr.
> 15/04/09 12:22:35 INFO ParseDriver: Parsing command: select a,b from comp1
> 15/04/09 12:22:35 INFO ParseDriver: Parse Completed
> 15/04/09 12:22:35 WARN LoadSnappy: Snappy native library is available
> 15/04/09 12:22:35 WARN NativeCodeLoader: Unable to load native-hadoop library
> for your platform... using builtin-java classes where applicable
> 15/04/09 12:22:35 WARN LoadSnappy: Snappy native library not loaded
> 15/04/09 12:22:35 INFO FileInputFormat: Total input paths to process : 1
> 15/04/09 12:22:35 INFO SparkContext: Starting job: saveAsTextFile at
> JavaSchemaRDD.scala:42
> 15/04/09 12:22:35 INFO DAGScheduler: Got job 0 (saveAsTextFile at
> JavaSchemaRDD.scala:42) with 2 output partitions (allowLocal=false)
> 15/04/09 12:22:35 INFO DAGScheduler: Final stage: Stage 0(saveAsTextFile at
> JavaSchemaRDD.scala:42)
> 15/04/09 12:22:35 INFO DAGScheduler: Parents of final stage: List()
> 15/04/09 12:22:35 INFO DAGScheduler: Missing parents: List()
> 15/04/09 12:22:35 INFO DAGScheduler: Submitting Stage 0 (MappedRDD[8] at
> saveAsTextFile at JavaSchemaRDD.scala:42), which has no missing parents
> 15/04/09 12:22:35 INFO MemoryStore: ensureFreeSpace(20896) called with
> curMem=37727, maxMem=278302556
> 15/04/09 12:22:35 INFO MemoryStore: Block broadcast_1 stored as values in
> memory (estimated size 20.4 KB, free 265.4 MB)
> 15/04/09 12:22:35 INFO MemoryStore: ensureFreeSpace(15057) called with
> curMem=58623, maxMem=278302556
> 15/04/09 12:22:35 INFO MemoryStore: Block broadcast_1_piece0 stored as bytes
> in memory (estimated size 14.7 KB, free 265.3 MB)
> 15/04/09 12:22:35 INFO BlockManagerInfo: Added broadcast_1_piece0 in memory
> on localhost:50256 (size: 14.7 KB, free: 265.4 MB)
> 15/04/09 12:22:35 INFO BlockManagerMaster: Updated info of block
> broadcast_1_piece0
> 15/04/09 12:22:35 INFO SparkContext: Created broadcast 1 from broadcast at
> DAGScheduler.scala:838
> 15/04/09 12:22:35 INFO DAGScheduler: Submitting 2 missing tasks from Stage 0
> (MappedRDD[8] at saveAsTextFile at JavaSchemaRDD.scala:42)
> 15/04/09 12:22:35 INFO TaskSchedulerImpl: Adding task set 0.0 with 2 tasks
> 15/04/09 12:22:35 INFO TaskSetManager: Starting task 0.0 in stage 0.0 (TID 0,
> localhost, PROCESS_LOCAL, 1349 bytes)
> 15/04/09 12:22:35 INFO TaskSetManager: Starting task 1.0 in stage 0.0 (TID 1,
> localhost, PROCESS_LOCAL, 1349 bytes)
> 15/04/09 12:22:35 INFO Executor: Running task 0.0 in stage 0.0 (TID 0)
> 15/04/09 12:22:35 INFO Executor: Running task 1.0 in stage 0.0 (TID 1)
> 15/04/09 12:22:35 INFO Executor: Fetching
> http://10.212.51.39:37771/jars/engineshow.jar with timestamp 1428562351299
> 15/04/09 12:22:35 INFO Utils: Fetching
> http://10.212.51.39:37771/jars/engineshow.jar to
> /tmp/fetchFileTemp3748447218639833283.tmp
> 15/04/09 12:22:35 INFO Executor: Adding
> file:/tmp/spark-0ed71155-55db-48dd-ac02-7a56fe33381b/engineshow.jar to class
> loader
> 15/04/09 12:22:35 INFO HadoopRDD: Input split:
> file:/home/aditya/stocks1.csv:0+6708709
> 15/04/09 12:22:35 INFO HadoopRDD: Input split:
> file:/home/aditya/stocks1.csv:6708709+6708709
> 15/04/09 12:22:36 ERROR Executor: Exception in task 1.0 in stage 0.0 (TID 1)
> java.lang.ArrayIndexOutOfBoundsException: 1
> at
> org.apache.spark.sql.catalyst.expressions.GenericRow.apply(Row.scala:142)
> at
> org.apache.spark.sql.catalyst.expressions.BoundReference.eval(BoundAttribute.scala:37)
> at
> org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:68)
> at
> org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:52)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at
> org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1060)
> at
> org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1047)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 15/04/09 12:22:36 WARN TaskSetManager: Lost task 1.0 in stage 0.0 (TID 1,
> localhost): java.lang.ArrayIndexOutOfBoundsException: 1
> at
> org.apache.spark.sql.catalyst.expressions.GenericRow.apply(Row.scala:142)
> at
> org.apache.spark.sql.catalyst.expressions.BoundReference.eval(BoundAttribute.scala:37)
> at
> org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:68)
> at
> org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:52)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at
> org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1060)
> at
> org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1047)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> 15/04/09 12:22:36 ERROR TaskSetManager: Task 1 in stage 0.0 failed 1 times;
> aborting job
> 15/04/09 12:22:36 INFO TaskSchedulerImpl: Cancelling stage 0
> 15/04/09 12:22:36 INFO Executor: Executor is trying to kill task 0.0 in stage
> 0.0 (TID 0)
> 15/04/09 12:22:36 INFO TaskSchedulerImpl: Stage 0 was cancelled
> 15/04/09 12:22:36 INFO Executor: Executor killed task 0.0 in stage 0.0 (TID 0)
> 15/04/09 12:22:36 INFO DAGScheduler: Job 0 failed: saveAsTextFile at
> JavaSchemaRDD.scala:42, took 0.616858 s
> Exception in thread "main" org.apache.spark.SparkException: Job aborted due
> to stage failure: Task 1 in stage 0.0 failed 1 times, most recent failure:
> Lost task 1.0 in stage 0.0 (TID 1, localhost):
> java.lang.ArrayIndexOutOfBoundsException: 1
> at
> org.apache.spark.sql.catalyst.expressions.GenericRow.apply(Row.scala:142)
> at
> org.apache.spark.sql.catalyst.expressions.BoundReference.eval(BoundAttribute.scala:37)
> at
> org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:68)
> at
> org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.apply(Projection.scala:52)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at
> org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1060)
> at
> org.apache.spark.rdd.PairRDDFunctions$$anonfun$13.apply(PairRDDFunctions.scala:1047)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> Driver stacktrace:
> at
> org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1214)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at
> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
> at scala.Option.foreach(Option.scala:236)
> at
> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420)
> at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1375)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
> at akka.actor.ActorCell.invoke(ActorCell.scala:487)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
> at akka.dispatch.Mailbox.run(Mailbox.scala:220)
> at
> akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:393)
> at
> scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> at
> scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> at
> scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> at
> scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
> 15/04/09 12:22:36 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0,
> localhost): TaskKilled (killed intentionally)
> 15/04/09 12:22:36 INFO TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks
> have all completed, from pool
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
