You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Hyukjin Kwon (JIRA)" <ji...@apache.org> on 2017/03/20 05:03:41 UTC
[jira] [Resolved] (SPARK-12124) Spark Sql MongoDB Cross Join Not
Working
[ https://issues.apache.org/jira/browse/SPARK-12124?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Hyukjin Kwon resolved SPARK-12124.
----------------------------------
Resolution: Invalid
The error messages originate from {{MongoRecordReader}} which is a thirdparty. I don't think this is an issue within Spark.
I tested this with another thirdparty datasource, Spark XML that uses {{NewHadoopRDD}}. It seems fine with cross join.
> Spark Sql MongoDB Cross Join Not Working
> ----------------------------------------
>
> Key: SPARK-12124
> URL: https://issues.apache.org/jira/browse/SPARK-12124
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.4.0, 1.4.1, 1.5.1, 1.5.2
> Environment: Linux Ubuntu 14.4
> Reporter: himanshu singhal
> Labels: test
> Original Estimate: 1,680h
> Remaining Estimate: 1,680h
>
> Cross Join In Spark Sql where source is mongo db is giving th wrong result
> 15/12/03 15:55:05 INFO Executor: Running task 0.0 in stage 2.0 (TID 2)
> 15/12/03 15:55:05 INFO NewHadoopRDD: Input split: MongoInputSplit{URI=mongodb://localhost:27017/watchtower2.Patient, authURI=null, min={ }, max={ }, query={ }, sort={ }, fields={ }, notimeout=false}
> 15/12/03 15:55:05 INFO NewHadoopRDD: Input split: MongoInputSplit{URI=mongodb://localhost:27017/watchtower2.Patient, authURI=null, min={ }, max={ }, query={ }, sort={ }, fields={ }, notimeout=false}
> 15/12/03 15:55:05 INFO MongoRecordReader: Read 1.0 documents from:
> 15/12/03 15:55:05 INFO MongoRecordReader: MongoInputSplit{URI=mongodb://localhost:27017/watchtower2.Patient, authURI=null, min={ }, max={ }, query={ }, sort={ }, fields={ }, notimeout=false}
> 15/12/03 15:55:05 ERROR Executor: Exception in task 0.0 in stage 2.0 (TID 2)
> java.lang.IllegalStateException: Iterator has been closed
> at com.mongodb.QueryResultIterator.hasNext(QueryResultIterator.java:119)
> at com.mongodb.DBCursor._hasNext(DBCursor.java:551)
> at com.mongodb.DBCursor.hasNext(DBCursor.java:571)
> at com.mongodb.hadoop.input.MongoRecordReader.nextKeyValue(MongoRecordReader.java:73)
> at org.apache.spark.rdd.NewHadoopRDD$$anon$1.hasNext(NewHadoopRDD.scala:163)
> at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:308)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> 15/12/03 15:55:05 WARN TaskSetManager: Lost task 0.0 in stage 2.0 (TID 2, localhost): java.lang.IllegalStateException: Iterator has been closed
> at com.mongodb.QueryResultIterator.hasNext(QueryResultIterator.java:119)
> at com.mongodb.DBCursor._hasNext(DBCursor.java:551)
> at com.mongodb.DBCursor.hasNext(DBCursor.java:571)
> at com.mongodb.hadoop.input.MongoRecordReader.nextKeyValue(MongoRecordReader.java:73)
> at org.apache.spark.rdd.NewHadoopRDD$$anon$1.hasNext(NewHadoopRDD.scala:163)
> at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:308)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> 15/12/03 15:55:05 ERROR TaskSetManager: Task 0 in stage 2.0 failed 1 times; aborting job
> 15/12/03 15:55:05 INFO TaskSchedulerImpl: Removed TaskSet 2.0, whose tasks have all completed, from pool
> 15/12/03 15:55:05 INFO TaskSchedulerImpl: Cancelling stage 2
> 15/12/03 15:55:05 INFO DAGScheduler: ResultStage 2 (show at DataIOMain.java:75) failed in 0.084 s
> 15/12/03 15:55:05 INFO DAGScheduler: Job 2 failed: show at DataIOMain.java:75, took 0.113304 s
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 2.0 failed 1 times, most recent failure: Lost task 0.0 in stage 2.0 (TID 2, localhost): java.lang.IllegalStateException: Iterator has been closed
> at com.mongodb.QueryResultIterator.hasNext(QueryResultIterator.java:119)
> at com.mongodb.DBCursor._hasNext(DBCursor.java:551)
> at com.mongodb.DBCursor.hasNext(DBCursor.java:571)
> at com.mongodb.hadoop.input.MongoRecordReader.nextKeyValue(MongoRecordReader.java:73)
> at org.apache.spark.rdd.NewHadoopRDD$$anon$1.hasNext(NewHadoopRDD.scala:163)
> at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:308)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> Driver stacktrace:
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1283)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1271)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1270)
> at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1270)
> 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:1496)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1458)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1447)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
> at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1824)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1837)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1850)
> at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:215)
> at org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:207)
> at org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1385)
> at org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1385)
> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
> at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1903)
> at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1384)
> at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1314)
> at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1377)
> at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:178)
> at org.apache.spark.sql.DataFrame.show(DataFrame.scala:401)
> at org.apache.spark.sql.DataFrame.show(DataFrame.scala:362)
> at org.apache.spark.sql.DataFrame.show(DataFrame.scala:370)
> at ngi.spark.manipulator.core.DataIOMain.main(DataIOMain.java:75)
> Caused by: java.lang.IllegalStateException: Iterator has been closed
> at com.mongodb.QueryResultIterator.hasNext(QueryResultIterator.java:119)
> at com.mongodb.DBCursor._hasNext(DBCursor.java:551)
> at com.mongodb.DBCursor.hasNext(DBCursor.java:571)
> at com.mongodb.hadoop.input.MongoRecordReader.nextKeyValue(MongoRecordReader.java:73)
> at org.apache.spark.rdd.NewHadoopRDD$$anon$1.hasNext(NewHadoopRDD.scala:163)
> at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:308)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> 15/12/03 15:55:05 INFO SparkContext: Invoking stop() from shutdown hook
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org