Why your Spark job is failing
•
107 likes•69,078 views
The document discusses Spark exceptions and errors related to shuffling data between nodes. It notes that tasks can fail due to out of memory errors or files being closed prematurely. It also provides explanations of Spark's shuffle operations and how data is written and merged across nodes during shuffles.
Report
Share
Why your Spark job is failing
- 2. ● Data science at Cloudera ● Recently lead Apache Spark development at Cloudera ● Before that, committing on Apache YARN and MapReduce ● Hadoop project management committee
- 3. com.esotericsoftware.kryo. KryoException: Unable to find class: $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC $$iwC$$iwC$$anonfun$4$$anonfun$apply$3
- 7. org.apache.spark.SparkException: Job aborted due to stage failure: Task 0.0:0 failed 4 times, most recent failure: Exception failure in TID 6 on host bottou02-10g.pa.cloudera.com: java.lang.ArithmeticException: / by zero $iwC$$iwC$$iwC$$iwC$$anonfun$1.apply$mcII$sp(<console>:13) $iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:13) $iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:13) scala.collection.Iterator$$anon$11.next(Iterator.scala:328) org.apache.spark.util.Utils$.getIteratorSize(Utils.scala:1016) [...] Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler. org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages (DAGScheduler.scala:1033) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1. apply(DAGScheduler.scala:1017) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1. apply(DAGScheduler.scala:1015) [...]
- 8. org.apache.spark.SparkException: Job aborted due to stage failure: Task 0.0:0 failed 4 times, most recent failure: Exception failure in TID 6 on host bottou02-10g.pa.cloudera.com: java.lang.ArithmeticException: / by zero $iwC$$iwC$$iwC$$iwC$$anonfun$1.apply$mcII$sp(<console>:13) $iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:13) $iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:13) scala.collection.Iterator$$anon$11.next(Iterator.scala:328) org.apache.spark.util.Utils$.getIteratorSize(Utils.scala:1016) [...]
- 9. org.apache.spark.SparkException: Job aborted due to stage failure: Task 0.0:0 failed 4 times, most recent failure: Exception failure in TID 6 on host bottou02-10g.pa.cloudera.com: java.lang.ArithmeticException: / by zero $iwC$$iwC$$iwC$$iwC$$anonfun$1.apply$mcII$sp(<console>:13) $iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:13) $iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:13) scala.collection.Iterator$$anon$11.next(Iterator.scala:328) org.apache.spark.util.Utils$.getIteratorSize(Utils.scala:1016) [...]
- 10. val file = sc.textFile("hdfs://...") file.filter(_.startsWith(“banana”)) .count()
- 11. Job Stage Task Task Task Task Stage Task Task Task Task
- 13. val rdd1 = sc.textFile(“hdfs://...”) .map(someFunc) .filter(filterFunc) textFile map filter
- 14. val rdd2 = sc.hadoopFile(“hdfs: //...”) .groupByKey() .map(someOtherFunc) hadoopFile groupByKey map
- 15. val rdd3 = rdd1.join(rdd2) .map(someFunc) join map
- 16. rdd3.collect()
- 17. textFile map filter hadoop group File ByKey map join map
- 18. textFile map filter hadoop group File ByKey map join map
- 19. Stage Task Task Task Task
- 20. Stage Task Task Task Task
- 21. Stage Task Task Task Task
- 22. org.apache.spark.SparkException: Job aborted due to stage failure: Task 0.0:0 failed 4 times, most recent failure: Exception failure in TID 6 on host bottou02-10g.pa.cloudera.com: java.lang.ArithmeticException: / by zero $iwC$$iwC$$iwC$$iwC$$anonfun$1.apply$mcII$sp(<console>:13) $iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:13) $iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:13) scala.collection.Iterator$$anon$11.next(Iterator.scala:328) org.apache.spark.util.Utils$.getIteratorSize(Utils.scala:1016) [...]
- 23. 14/04/22 11:59:58 ERROR executor.Executor: Exception in task ID 286 6 java.io.IOException: Filesystem closed at org.apache.hadoop.hdfs.DFSClient.checkOpen(DFSClient.java:565 ) at org.apache.hadoop.hdfs.DFSInputStream.readWithStrategy(DFSInputStream.java:64 8) at org.apache.hadoop.hdfs.DFSInputStream.read(DFSInputStream.java:706 ) at java.io.DataInputStream.read(DataInputStream.java:100 ) at org.apache.hadoop.util.LineReader.readDefaultLine(LineReader.java:20 9) at org.apache.hadoop.util.LineReader.readLine(LineReader.java:173 ) at org.apache.hadoop.mapred.LineRecordReader.next(LineRecordReader.java:20 6) at org.apache.hadoop.mapred.LineRecordReader.next(LineRecordReader.java:4 5) at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:164 ) at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:149 ) at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:71 ) at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:2 7) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327 ) at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:388 ) at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:388 ) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327 ) at scala.collection.Iterator$class.foreach(Iterator.scala:727 ) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157 ) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:16 1) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:10 2) at org.apache.spark.scheduler.Task.run(Task.scala:53 ) at org.apache.spark.executor.Executor$TaskRunner$$anonfun$run$1.apply$mcV$sp(Executor.scala:21 1) at org.apache.spark.deploy.SparkHadoopUtil$$anon$1.run(SparkHadoopUtil.scala:4 2) at org.apache.spark.deploy.SparkHadoopUtil$$anon$1.run(SparkHadoopUtil.scala:4 1) at java.security.AccessController.doPrivileged(Native Method ) at javax.security.auth.Subject.doAs(Subject.java:415 ) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:140 8) at org.apache.spark.deploy.SparkHadoopUtil.runAsUser(SparkHadoopUtil.scala:4 1) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:176 ) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:114 5) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:61 5) at java.lang.Thread.run(Thread.java:724)
- 25. ResourceManager NodeManager NodeManager Container Container Application Master Container Client
- 26. ResourceManager Client NodeManager NodeManager Container Map Task Container Application Master Container Reduce Task
- 27. ResourceManager Client NodeManager NodeManager Container Map Task Container Application Master Container Reduce Task
- 28. ResourceManager Client NodeManager NodeManager Container Map Task Container Application Master Container Reduce Task
- 29. Container [pid=63375, containerID=container_1388158490598_0001_01_00 0003] is running beyond physical memory limits. Current usage: 2.1 GB of 2 GB physical memory used; 2.8 GB of 4.2 GB virtual memory used. Killing container.
- 30. yarn.nodemanager.resource.memory-mb Executor container spark.yarn.executor.memoryOverhead spark.executor.memory spark.shuffle.memoryFraction spark.storage.memoryFraction
- 36. ExternalAppend OnlyMap Block Block deserialize deserialize
- 37. ExternalAppend OnlyMap key1 -> values key2 -> values key3 -> values
- 38. ExternalAppend OnlyMap key1 -> values key2 -> values key3 -> values
- 39. ExternalAppend OnlyMap Sort & Spill key1 -> values key2 -> values key3 -> values
- 42. java.io.FileNotFoundException: /dn6/spark/local/spark-local- 20140610134115- 2cee/30/merged_shuffle_0_368_14 (Too many open files)
- 43. Task Task Write stuff key1 -> values key2 -> values key3 -> values out key1 -> values key2 -> values key3 -> values Task
- 44. Task Task Write stuff key1 -> values key2 -> values key3 -> values out key1 -> values key2 -> values key3 -> values Task
- 45. Partition 1 File Partition 2 File Partition 3 File Records
- 46. Records Buffer
- 47. Single file Buffer Sort & Spill Partition 1 Records Partition 2 Records Partition 3 Records Index file
- 49. ● No ● Distributed systems are complicated