Within a pyspark shell, both of these work for me:
print hc.sql("SELECT * from raw.location_tbl LIMIT 10").collect()
print sqlCtx.sql("SELECT * from raw.location_tbl LIMIT 10").collect()
But when I submit both of those in batch mode (hc and sqlCtx both exist), I
get the following error. Why is this happening? I'll note that I'm running
on YARN (CDH) and connecting to the Hive Metastore by setting an environment
variable with export HADOOP_CONF_DIR=/etc/hive/conf/
An error occurred while calling o39.sql.
: java.lang.RuntimeException: Table Not Found: raw.location_tbl
at scala.sys.package$.error(package.scala:27)
at
org.apache.spark.sql.catalyst.analysis.SimpleCatalog$$anonfun$1.apply(Catalog.scala:111)
at
org.apache.spark.sql.catalyst.analysis.SimpleCatalog$$anonfun$1.apply(Catalog.scala:111)
at scala.collection.MapLike$class.getOrElse(MapLike.scala:128)
at scala.collection.AbstractMap.getOrElse(Map.scala:58)
at
org.apache.spark.sql.catalyst.analysis.SimpleCatalog.lookupRelation(Catalog.scala:111)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.getTable(Analyzer.scala:175)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$6.applyOrElse(Analyzer.scala:187)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$6.applyOrElse(Analyzer.scala:182)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:50)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:186)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:207)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$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.catalyst.trees.TreeNode.transformChildrenDown(TreeNode.scala:236)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:192)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:207)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$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$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildrenDown(TreeNode.scala:236)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:192)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:177)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:182)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:172)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1$$anonfun$apply$2.apply(RuleExecutor.scala:61)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1$$anonfun$apply$2.apply(RuleExecutor.scala:59)
at
scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:111)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1.apply(RuleExecutor.scala:59)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1.apply(RuleExecutor.scala:51)
at scala.collection.immutable.List.foreach(List.scala:318)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.apply(RuleExecutor.scala:51)
at
org.apache.spark.sql.SQLContext$QueryExecution.analyzed$lzycompute(SQLContext.scala:1071)
at
org.apache.spark.sql.SQLContext$QueryExecution.analyzed(SQLContext.scala:1071)
at
org.apache.spark.sql.SQLContext$QueryExecution.assertAnalyzed(SQLContext.scala:1069)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:133)
at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:915)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379)
at py4j.Gateway.invoke(Gateway.java:259)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:207)
at java.lang.Thread.run(Thread.java:745)
False
Traceback (most recent call last):
File "/home/me/pyspark/pyspark_library_walkthrough.py", line 46, in
<module>
print row_objects[0].dma_code
--
View this message in context:
http://apache-spark-user-list.1001560.n3.nabble.com/sqlCtx-sql-some-hive-table-works-in-pyspark-but-not-spark-submit-tp25314.html
Sent from the Apache Spark User List mailing list archive at Nabble.com.
---------------------------------------------------------------------
To unsubscribe, e-mail: user-unsubscr...@spark.apache.org
For additional commands, e-mail: user-h...@spark.apache.org
