spark-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "guxiaobo1982" <guxiaobo1...@qq.com>
Subject Can't access remote Hive table from spark
Date Sun, 25 Jan 2015 08:18:57 GMT
Hi,
I built and started a single node standalone Spark 1.2.0 cluster along with a single node
Hive 0.14.0 instance installed by Ambari 1.17.0. On the Spark and Hive node I can create and
query tables inside Hive, and on remote machines I can submit the SparkPi example to the Spark
master. But I failed to run the following example code :


 
public class SparkTest {
 
	public static void main(String[] args)
 
	{
 
		String appName= "This is a test application";
 
		String master="spark://lix1.bh.com:7077";
 
		
 
		SparkConf conf = new SparkConf().setAppName(appName).setMaster(master);
 
		JavaSparkContext sc = new JavaSparkContext(conf);
 
		
 
		JavaHiveContext sqlCtx = new org.apache.spark.sql.hive.api.java.JavaHiveContext(sc);
 
		//sqlCtx.sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING)");
 
		//sqlCtx.sql("LOAD DATA LOCAL INPATH '/opt/spark/examples/src/main/resources/kv1.txt' INTO
TABLE src");
 
		// Queries are expressed in HiveQL.
 
List<Row> rows = sqlCtx.sql("FROM src SELECT key, value").collect();
 
System.out.print("I got " + rows.size() + " rows \r\n");
 
		sc.close();}
 
}




Exception in thread "main" org.apache.hadoop.hive.ql.metadata.InvalidTableException: Table
not found src

	at org.apache.hadoop.hive.ql.metadata.Hive.getTable(Hive.java:980)

	at org.apache.hadoop.hive.ql.metadata.Hive.getTable(Hive.java:950)

	at org.apache.spark.sql.hive.HiveMetastoreCatalog.lookupRelation(HiveMetastoreCatalog.scala:70)

	at org.apache.spark.sql.hive.HiveContext$$anon$2.org$apache$spark$sql$catalyst$analysis$OverrideCatalog$$super$lookupRelation(HiveContext.scala:253)

	at org.apache.spark.sql.catalyst.analysis.OverrideCatalog$$anonfun$lookupRelation$3.apply(Catalog.scala:141)

	at org.apache.spark.sql.catalyst.analysis.OverrideCatalog$$anonfun$lookupRelation$3.apply(Catalog.scala:141)

	at scala.Option.getOrElse(Option.scala:120)

	at org.apache.spark.sql.catalyst.analysis.OverrideCatalog$class.lookupRelation(Catalog.scala:141)

	at org.apache.spark.sql.hive.HiveContext$$anon$2.lookupRelation(HiveContext.scala:253)

	at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$5.applyOrElse(Analyzer.scala:143)

	at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$5.applyOrElse(Analyzer.scala:138)

	at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:144)

	at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:162)

	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:191)

	at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:147)

	at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:135)

	at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:138)

	at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:137)

	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:411)

	at org.apache.spark.sql.SQLContext$QueryExecution.analyzed(SQLContext.scala:411)

	at org.apache.spark.sql.SQLContext$QueryExecution.withCachedData$lzycompute(SQLContext.scala:412)

	at org.apache.spark.sql.SQLContext$QueryExecution.withCachedData(SQLContext.scala:412)

	at org.apache.spark.sql.SQLContext$QueryExecution.optimizedPlan$lzycompute(SQLContext.scala:413)

	at org.apache.spark.sql.SQLContext$QueryExecution.optimizedPlan(SQLContext.scala:413)

	at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan$lzycompute(SQLContext.scala:418)

	at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan(SQLContext.scala:416)

	at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan$lzycompute(SQLContext.scala:422)

	at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan(SQLContext.scala:422)

	at org.apache.spark.sql.SchemaRDD.collect(SchemaRDD.scala:444)

	at org.apache.spark.sql.api.java.JavaSchemaRDD.collect(JavaSchemaRDD.scala:114)

	at com.blackhorse.SparkTest.main(SparkTest.java:27)

[delete Spark temp dirs] DEBUG org.apache.spark.util.Utils - Shutdown hook called

 

[delete Spark local dirs] DEBUG org.apache.spark.storage.DiskBlockManager - Shutdown hook
calle







But if I change the query to "show tables", the program can run and got 0 rows through I have
many tables inside Hive, so I come to doubt that my program or the spark instance did not
connect to my Hive instance, maybe it started a local hive. I have put the hive-site.xml file
from Hive installation into spark's conf directory. Can you help figure out what's wrong here,
thanks.
Mime
View raw message