Hi ,
I am reading parquet file and creating temp table. when i am trying to
execute query outside of foreach function it is working fine.
throws nullpointerexception within data frame.foreach function.
code snippet:
String CITATION_QUERY = "select c.citation_num, c.title, c.publisher from
test c";
Dataset<Row> citation_query = spark.sql(CITATION_QUERY);
System.out.println("mistery:"+citation_query.count());
// Iterator<Row> iterofresulDF = resultDF.toLocalIterator();
resultDF.foreach(new ForeachFunction<Row>()
{
private static final long serialVersionUID = 1L;
public void call(Row line)
{
Dataset<Row> row = spark.sql(CITATION_QUERY);
System.out.println("mistery row count:"+row.count());
}
});
Error trace:
16/10/12 15:59:53 INFO CodecPool: Got brand-new decompressor [.snappy]
16/10/12 15:59:53 ERROR Executor: Exception in task 0.0 in stage 5.0 (TID 5)
java.lang.NullPointerException
at
org.apache.spark.sql.SparkSession.sessionState$lzycompute(SparkSession.scala:112)
at org.apache.spark.sql.SparkSession.sessionState(SparkSession.scala:110)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:582)
at com.elsevier.datasearch.ExecuteSQL.executeQuery(ExecuteSQL.java:11)
at com.elsevier.datasearch.ProcessPetDB$1.call(ProcessPetDB.java:53)
at com.elsevier.datasearch.ProcessPetDB$1.call(ProcessPetDB.java:1)
at org.apache.spark.sql.Dataset$$anonfun$foreach$2.apply(Dataset.scala:2118)
at org.apache.spark.sql.Dataset$$anonfun$foreach$2.apply(Dataset.scala:2118)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at
org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$27.apply(RDD.scala:894)
at
org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$27.apply(RDD.scala:894)
at
org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1916)
at
org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1916)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
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$$failJobAndIndependentStages(DAGScheduler.scala:1454)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1442)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1441)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1441)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at scala.Option.foreach(Option.scala:257)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:811)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1667)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1622)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1611)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1890)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1903)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1916)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1930)
at org.apache.spark.rdd.RDD$$anonfun$foreach$1.apply(RDD.scala:894)
at org.apache.spark.rdd.RDD$$anonfun$foreach$1.apply(RDD.scala:892)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
at org.apache.spark.rdd.RDD.foreach(RDD.scala:892)
at
org.apache.spark.sql.Dataset$$anonfun$foreach$1.apply$mcV$sp(Dataset.scala:2108)
at org.apache.spark.sql.Dataset$$anonfun$foreach$1.apply(Dataset.scala:2108)
at org.apache.spark.sql.Dataset$$anonfun$foreach$1.apply(Dataset.scala:2108)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2546)
at org.apache.spark.sql.Dataset.foreach(Dataset.scala:2107)
at org.apache.spark.sql.Dataset.foreach(Dataset.scala:2118)
at com.elsevier.datasearch.ProcessPetDB.main(ProcessPetDB.java:46)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:736)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:185)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:210)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:124)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.NullPointerException
at
org.apache.spark.sql.SparkSession.sessionState$lzycompute(SparkSession.scala:112)
at org.apache.spark.sql.SparkSession.sessionState(SparkSession.scala:110)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:582)
at com.elsevier.datasearch.ExecuteSQL.executeQuery(ExecuteSQL.java:11)
at com.elsevier.datasearch.ProcessPetDB$1.call(ProcessPetDB.java:53)
at com.elsevier.datasearch.ProcessPetDB$1.call(ProcessPetDB.java:1)
at org.apache.spark.sql.Dataset$$anonfun$foreach$2.apply(Dataset.scala:2118)
at org.apache.spark.sql.Dataset$$anonfun$foreach$2.apply(Dataset.scala:2118)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at
org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$27.apply(RDD.scala:894)
at
org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$27.apply(RDD.scala:894)
at
org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1916)
at
org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1916)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
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)
16/10/12 15:59:53 INFO SparkContext: Invoking stop() from shutdown hook
Please let me know if i am missing anything. Thank you for the help.
--
Selvam Raman
"லஞ்சம் தவிர்த்து நெஞ்சம் நிமிர்த்து"
